Merge pull request #88 from wtlyu/feat-clean-after-regenerate-pr

Feat clean after regenerate pr

.circleci/requirements.txt

@@ -1,13 +0,0 @@
-# used by CI/CD testing
-openai==1.67.0
-python-dotenv
-tiktoken
-importlib_metadata
-cohere
-redis
-anthropic
-orjson==3.9.15
-pydantic==2.7.1
-google-cloud-aiplatform==1.43.0
-fastapi-sso==0.10.0
-uvloop==0.21.0

.devcontainer/devcontainer.json

@@ -1,52 +0,0 @@
-{
-	"name": "Python 3.11",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
-	"image": "mcr.microsoft.com/devcontainers/python:3.11-bookworm",
-	// https://github.com/devcontainers/images/tree/main/src/python
-	// https://mcr.microsoft.com/en-us/product/devcontainers/python/tags
-
-	// "build": {
-	// 	"dockerfile": "Dockerfile",
-	// 	"context": ".."
-	// },
-
-	// Features to add to the dev container. More info: https://containers.dev/features.
-	// "features": {},
-
-	// Configure tool-specific properties.
-	"customizations": {
-		// Configure properties specific to VS Code.
-		"vscode": {
-			"settings": {},
-			"extensions": [
-				"ms-python.python",
-				"ms-python.vscode-pylance",
-				"GitHub.copilot",
-				"GitHub.copilot-chat",
-				"ms-python.autopep8"
-			]
-		}
-	},
-	
-	// Use 'forwardPorts' to make a list of ports inside the container available locally.
-	"forwardPorts": [4000],
-
-	"containerEnv": {
-		"LITELLM_LOG": "DEBUG"
-	},
-
-	// Use 'portsAttributes' to set default properties for specific forwarded ports. 
-	// More info: https://containers.dev/implementors/json_reference/#port-attributes
-	"portsAttributes": {
-		"4000": {
-			"label": "LiteLLM Server",
-			"onAutoForward": "notify"
-		}
-	},
-
-	// More info: https://aka.ms/dev-containers-non-root.
-	// "remoteUser": "litellm",
-
-	// Use 'postCreateCommand' to run commands after the container is created.
-	"postCreateCommand": "pipx install poetry && poetry install -E extra_proxy -E proxy"
-}

.dockerignore

@@ -1,12 +0,0 @@
-docs
-cookbook
-.circleci
-.github
-tests
-.git
-.github
-.circleci
-.devcontainer
-*.tgz
-log.txt
-docker/Dockerfile.*

.env.example

@@ -1,27 +0,0 @@
-# OpenAI
-OPENAI_API_KEY = ""
-OPENAI_API_BASE = ""
-# Cohere
-COHERE_API_KEY = ""
-# OpenRouter
-OR_SITE_URL = ""
-OR_APP_NAME = "LiteLLM Example app"
-OR_API_KEY = ""
-# Azure API base URL
-AZURE_API_BASE = ""
-# Azure API version
-AZURE_API_VERSION = ""
-# Azure API key
-AZURE_API_KEY = ""
-# Replicate
-REPLICATE_API_KEY = ""
-REPLICATE_API_TOKEN = ""
-# Anthropic
-ANTHROPIC_API_KEY = ""
-# Infisical
-INFISICAL_TOKEN = ""
-
-# Development Configs
-LITELLM_MASTER_KEY = "sk-1234"
-DATABASE_URL = "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
-STORE_MODEL_IN_DB = "True"

.flake8

@@ -1,46 +0,0 @@
-[flake8]
-ignore =
-    # The following ignores can be removed when formatting using black
-    W191,W291,W292,W293,W391,W504
-    E101,E111,E114,E116,E117,E121,E122,E123,E124,E125,E126,E127,E128,E129,E131,
-    E201,E202,E221,E222,E225,E226,E231,E241,E251,E252,E261,E265,E271,E272,E275,
-    E301,E302,E303,E305,E306,
-    # line break before binary operator
-    W503,
-    # inline comment should start with '# '
-    E262,
-    # too many leading '#' for block comment
-    E266,
-    # multiple imports on one line
-    E401,
-    # module level import not at top of file
-    E402,
-    # Line too long (82 > 79 characters)
-    E501,
-    # comparison to None should be 'if cond is None:'
-    E711,
-    # comparison to True should be 'if cond is True:' or 'if cond:'
-    E712,
-    # do not compare types, for exact checks use `is` / `is not`, for instance checks use `isinstance()`
-    E721,
-    # do not use bare 'except'
-    E722,
-    # x is imported but unused
-    F401,
-    # 'from . import *' used; unable to detect undefined names
-    F403,
-    # x may be undefined, or defined from star imports:
-    F405,
-    # f-string is missing placeholders
-    F541,
-    # dictionary key '' repeated with different values
-    F601,
-    # redefinition of unused x from line 123
-    F811,
-    # undefined name x
-    F821,
-    # local variable x is assigned to but never used
-    F841,
-
-# https://black.readthedocs.io/en/stable/guides/using_black_with_other_tools.html#flake8
-extend-ignore = E203

.git-blame-ignore-revs

@@ -1,10 +0,0 @@
-# Add the commit hash of any commit you want to ignore in `git blame` here.
-# One commit hash per line.
-#
-# The GitHub Blame UI will use this file automatically!
-#
-# Run this command to always ignore formatting commits in `git blame`
-#     git config blame.ignoreRevsFile .git-blame-ignore-revs
-
-# Update pydantic code to fix warnings (GH-3600)
-876840e9957bc7e9f7d6a2b58c4d7c53dad16481

.gitattributes

@@ -1 +0,0 @@
-*.ipynb linguist-vendored

.github/FUNDING.yml

@@ -1,13 +0,0 @@
-# These are supported funding model platforms
-
-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
-patreon: # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
-custom: https://buy.stripe.com/9AQ03Kd3P91o0Q8bIS

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,49 +0,0 @@
-name: Bug Report
-description: File a bug report
-title: "[Bug]: "
-labels: ["bug"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for taking the time to fill out this bug report!
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: What happened?
-      description: Also tell us, what did you expect to happen?
-      placeholder: Tell us what you see!
-      value: "A bug happened!"
-    validations:
-      required: true
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output
-      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
-      render: shell
-  - type: dropdown
-    id: ml-ops-team
-    attributes:
-      label: Are you a ML Ops Team?
-      description: This helps us prioritize your requests correctly 
-      options:
-        - "No"
-        - "Yes"
-    validations:
-      required: true
-  - type: input
-    id: version
-    attributes:
-      label: What LiteLLM version are you on ? 
-      placeholder: v1.53.1
-    validations:
-      required: true
-  - type: input
-    id: contact
-    attributes:
-      label: Twitter / LinkedIn details 
-      description: We announce new features on Twitter + LinkedIn. If this issue leads to an announcement, and you'd like a mention, we'll gladly shout you out!
-      placeholder: ex. @krrish_dh / https://www.linkedin.com/in/krish-d/
-    validations:
-      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -1,8 +0,0 @@
-blank_issues_enabled: true
-contact_links:
-  - name: Schedule Demo
-    url: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat
-    about: Speak directly with Krrish and Ishaan, the founders, to discuss issues, share feedback, or explore improvements for LiteLLM
-  - name: Discord
-    url: https://discord.com/invite/wuPM9dRgDw
-    about: Join 250+ LiteLLM community members! 

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,42 +0,0 @@
-name: 🚀 Feature Request 
-description: Submit a proposal/request for a new LiteLLM feature.
-title: "[Feature]: "
-labels: ["enhancement"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for making LiteLLM better! 
-  - type: textarea
-    id: the-feature
-    attributes:
-      label: The Feature
-      description: A clear and concise description of the feature proposal
-      placeholder: Tell us what you want!
-    validations:
-      required: true
-  - type: textarea
-    id: motivation
-    attributes:
-      label: Motivation, pitch
-      description: Please outline the motivation for the proposal. Is your feature request related to a specific problem? e.g., "I'm working on X and would like Y to be possible". If this is related to another GitHub issue, please link here too.
-    validations:
-      required: true
-  - type: dropdown
-    id: ml-ops-team
-    attributes:
-      label: Are you a ML Ops Team?
-      description: This helps us prioritize your requests correctly 
-      options:
-        - "No"
-        - "Yes"
-    validations:
-      required: true
-  - type: input
-    id: contact
-    attributes:
-      label: Twitter / LinkedIn details 
-      description: We announce new features on Twitter + LinkedIn. When this is announced, and you'd like a mention, we'll gladly shout you out!
-      placeholder: ex. @krrish_dh / https://www.linkedin.com/in/krish-d/
-    validations:
-      required: false

.github/actions/helm-oci-chart-releaser/action.yml

@@ -1,77 +0,0 @@
-name: Helm OCI Chart Releaser
-description: Push Helm charts to OCI-based (Docker) registries
-author: sergeyshaykhullin
-branding:
-  color: yellow
-  icon: upload-cloud
-inputs:
-  name:
-    required: true
-    description: Chart name
-  repository:
-    required: true
-    description: Chart repository name
-  tag:
-    required: true
-    description: Chart version
-  app_version:
-    required: true
-    description: App version
-  path:
-    required: false
-    description: Chart path (Default 'charts/{name}')
-  registry:
-    required: true
-    description: OCI registry
-  registry_username:
-    required: true
-    description: OCI registry username
-  registry_password:
-    required: true
-    description: OCI registry password
-  update_dependencies:
-    required: false
-    default: 'false'
-    description: Update chart dependencies before packaging (Default 'false')
-outputs:
-  image:
-    value: ${{ steps.output.outputs.image }}
-    description: Chart image (Default '{registry}/{repository}/{image}:{tag}')
-runs:
-  using: composite
-  steps:
-    - name: Helm | Login
-      shell: bash
-      run: echo ${{ inputs.registry_password }} | helm registry login -u ${{ inputs.registry_username }} --password-stdin ${{ inputs.registry }}
-      env:
-        HELM_EXPERIMENTAL_OCI: '1'
-    
-    - name: Helm | Dependency
-      if: inputs.update_dependencies == 'true'
-      shell: bash
-      run: helm dependency update ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
-      env:
-        HELM_EXPERIMENTAL_OCI: '1'
-
-    - name: Helm | Package
-      shell: bash
-      run: helm package ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }} --version ${{ inputs.tag }} --app-version ${{ inputs.app_version }}
-      env:
-        HELM_EXPERIMENTAL_OCI: '1'
-
-    - name: Helm | Push
-      shell: bash
-      run: helm push ${{ inputs.name }}-${{ inputs.tag }}.tgz oci://${{ inputs.registry }}/${{ inputs.repository }}
-      env:
-        HELM_EXPERIMENTAL_OCI: '1'
-
-    - name: Helm | Logout
-      shell: bash
-      run: helm registry logout ${{ inputs.registry }}
-      env:
-        HELM_EXPERIMENTAL_OCI: '1'
-
-    - name: Helm | Output
-      id: output
-      shell: bash
-      run: echo "image=${{ inputs.registry }}/${{ inputs.repository }}/${{ inputs.name }}:${{ inputs.tag }}" >> $GITHUB_OUTPUT

.github/dependabot.yaml

@@ -1,10 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "daily"
-    groups:
-      github-actions:
-        patterns:
-          - "*"

.github/pull_request_template.md

@@ -1,33 +0,0 @@
-## Title
-
-<!-- e.g. "Implement user authentication feature" -->
-
-## Relevant issues
-
-<!-- e.g. "Fixes #000" -->
-
-## Pre-Submission checklist
-
-**Please complete all items before asking a LiteLLM maintainer to review your PR**
-
-- [ ] I have Added testing in the [`tests/litellm/`](https://github.com/BerriAI/litellm/tree/main/tests/litellm) directory, **Adding at least 1 test is a hard requirement** - [see details](https://docs.litellm.ai/docs/extras/contributing_code)
-- [ ] I have added a screenshot of my new test passing locally 
-- [ ] My PR passes all unit tests on (`make test-unit`)[https://docs.litellm.ai/docs/extras/contributing_code]
-- [ ] My PR's scope is as isolated as possible, it only solves 1 specific problem
-
-
-## Type
-
-<!-- Select the type of Pull Request -->
-<!-- Keep only the necessary ones -->
-
-🆕 New Feature
-🐛 Bug Fix
-🧹 Refactoring
-📖 Documentation
-🚄 Infrastructure
-✅ Test
-
-## Changes
-
-

.github/template.yaml

@@ -1,94 +0,0 @@
-AWSTemplateFormatVersion: '2010-09-09'
-Transform: AWS::Serverless-2016-10-31
-Description: >
-  llmlite-service
-
-  SAM Template for llmlite-service
-
-# More info about Globals: https://github.com/awslabs/serverless-application-model/blob/master/docs/globals.rst
-Globals:
-  Function:
-    Timeout: 600
-    MemorySize: 128
-    Environment:
-      Variables:
-        WORKER_CONFIG: !Ref WorkerConfigParameter
-
-Parameters:
-  AliasParameter:
-    Type: String
-    Default: live
-  WorkerConfigParameter:
-    Type: String
-    Description: Sample environment variable
-    Default: '{"model": null, "alias": null, "api_base": null, "api_version": "2023-07-01-preview", "debug": false, "temperature": null, "max_tokens": null, "request_timeout": 600, "max_budget": null, "telemetry": true, "drop_params": false, "add_function_to_prompt": false, "headers": null, "save": false, "config": null, "use_queue": false}'
-
-Resources:
-  MyUrlFunctionPermissions:
-    Type: AWS::Lambda::Permission
-    Properties:
-      FunctionName: !Ref URL
-      Action: lambda:InvokeFunctionUrl
-      Principal: "*"
-      FunctionUrlAuthType: NONE
-
-  Function:
-    Type: AWS::Serverless::Function
-    Properties:
-      FunctionName: !Sub "${AWS::StackName}-function"
-      CodeUri: "./litellm"
-      Handler: proxy/lambda.handler
-      Runtime: python3.11
-      AutoPublishAlias: !Ref AliasParameter
-      Architectures:
-       - x86_64
-      DeploymentPreference:
-        Type: AllAtOnce
-        Alarms:
-          - !Ref NewVersionErrorMetricGreaterThanZeroAlarm
-
-  NewVersionErrorMetricGreaterThanZeroAlarm:
-    Type: "AWS::CloudWatch::Alarm"
-    Properties:
-      AlarmDescription: Lambda Function Error > 0
-      ComparisonOperator: GreaterThanThreshold
-      Dimensions:
-        - Name: Resource
-          Value: !Sub "${Function}:live"
-        - Name: FunctionName
-          Value: !Ref Function
-        - Name: ExecutedVersion
-          Value: !GetAtt Function.Version.Version
-      EvaluationPeriods: 1
-      Unit: Count
-      MetricName: Errors
-      Namespace: AWS/Lambda
-      Period: 60
-      Statistic: Sum
-      Threshold: 0
-
-  URL:
-    Type: AWS::Lambda::Url
-    DependsOn: FunctionAliaslive
-    Properties:
-      AuthType: NONE
-      Qualifier: live
-      TargetFunctionArn: !GetAtt Function.Arn
-
-Outputs:
-  FunctionARN:
-    Description: "Lambda Function ARN"
-    Value: !GetAtt Function.Arn
-
-  FunctionUrl:
-    Description: "Lambda Function URL Endpoint"
-    Value:
-      Fn::GetAtt: URL.FunctionUrl
-
-  FunctionVersion:
-    Description: "Lambda Function Version"
-    Value: !GetAtt Function.Version.Version
-  
-  FunctionNewAlarmARN:
-    Description: "Lambda Function New Alarm ARN"
-    Value: !GetAtt NewVersionErrorMetricGreaterThanZeroAlarm.Arn

.github/workflows/auto_update_price_and_context_window.yml

@@ -1,28 +0,0 @@
-name: Updates model_prices_and_context_window.json and Create Pull Request
-
-on:
-  schedule:
-    - cron: "0 0 * * 0"  # Run every Sundays at midnight
-    #- cron: "0 0 * * *" # Run daily at midnight
-
-jobs:
-  auto_update_price_and_context_window:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install Dependencies
-        run: |
-          pip install aiohttp
-      - name: Update JSON Data
-        run: |
-          python ".github/workflows/auto_update_price_and_context_window_file.py"
-      - name: Create Pull Request
-        run: |
-          git add model_prices_and_context_window.json 
-          git commit -m "Update model_prices_and_context_window.json file: $(date +'%Y-%m-%d')" 
-          gh pr create --title "Update model_prices_and_context_window.json file" \
-            --body "Automated update for model_prices_and_context_window.json" \
-            --head auto-update-price-and-context-window-$(date +'%Y-%m-%d') \
-            --base main
-        env:
-          GH_TOKEN: ${{ secrets.GH_TOKEN }}

.github/workflows/auto_update_price_and_context_window_file.py

@@ -1,121 +0,0 @@
-import asyncio
-import aiohttp
-import json
-
-# Asynchronously fetch data from a given URL
-async def fetch_data(url):
-    try:
-        # Create an asynchronous session
-        async with aiohttp.ClientSession() as session:
-            # Send a GET request to the URL
-            async with session.get(url) as resp:
-                # Raise an error if the response status is not OK
-                resp.raise_for_status()
-                # Parse the response JSON
-                resp_json = await resp.json()
-                print("Fetch the data from URL.")
-                # Return the 'data' field from the JSON response
-                return resp_json['data']
-    except Exception as e:
-        # Print an error message if fetching data fails
-        print("Error fetching data from URL:", e)
-        return None
-
-# Synchronize local data with remote data
-def sync_local_data_with_remote(local_data, remote_data):
-    # Update existing keys in local_data with values from remote_data
-    for key in (set(local_data) & set(remote_data)):
-        local_data[key].update(remote_data[key])
-
-    # Add new keys from remote_data to local_data
-    for key in (set(remote_data) - set(local_data)):
-        local_data[key] = remote_data[key]
-
-# Write data to the json file
-def write_to_file(file_path, data):
-    try:
-        # Open the file in write mode
-        with open(file_path, "w") as file:
-            # Dump the data as JSON into the file
-            json.dump(data, file, indent=4)
-        print("Values updated successfully.")
-    except Exception as e:
-        # Print an error message if writing to file fails
-        print("Error updating JSON file:", e)
-
-# Update the existing models and add the missing models
-def transform_remote_data(data):
-    transformed = {}
-    for row in data:
-        # Add the fields 'max_tokens' and 'input_cost_per_token'
-        obj = {
-            "max_tokens": row["context_length"],
-            "input_cost_per_token": float(row["pricing"]["prompt"]),
-        }
-
-        # Add 'max_output_tokens' as a field if it is not None
-        if "top_provider" in row and "max_completion_tokens" in row["top_provider"] and row["top_provider"]["max_completion_tokens"] is not None:
-            obj['max_output_tokens'] = int(row["top_provider"]["max_completion_tokens"])
-
-        # Add the field 'output_cost_per_token'
-        obj.update({
-            "output_cost_per_token": float(row["pricing"]["completion"]),
-        })
-
-        # Add field 'input_cost_per_image' if it exists and is non-zero
-        if "pricing" in row and "image" in row["pricing"] and float(row["pricing"]["image"]) != 0.0:
-            obj['input_cost_per_image'] = float(row["pricing"]["image"])
-
-        # Add the fields 'litellm_provider' and 'mode'
-        obj.update({
-            "litellm_provider": "openrouter",
-            "mode": "chat"
-        })
-
-        # Add the 'supports_vision' field if the modality is 'multimodal'
-        if row.get('architecture', {}).get('modality') == 'multimodal':
-            obj['supports_vision'] = True
-
-        # Use a composite key to store the transformed object
-        transformed[f'openrouter/{row["id"]}'] = obj
-
-    return transformed
-
-
-# Load local data from a specified file
-def load_local_data(file_path):
-    try:
-        # Open the file in read mode
-        with open(file_path, "r") as file:
-            # Load and return the JSON data
-            return json.load(file)
-    except FileNotFoundError:
-        # Print an error message if the file is not found
-        print("File not found:", file_path)
-        return None
-    except json.JSONDecodeError as e:
-        # Print an error message if JSON decoding fails
-        print("Error decoding JSON:", e)
-        return None
-
-def main():
-    local_file_path = "model_prices_and_context_window.json"  # Path to the local data file
-    url = "https://openrouter.ai/api/v1/models"  # URL to fetch remote data
-
-    # Load local data from file
-    local_data = load_local_data(local_file_path)
-    # Fetch remote data asynchronously
-    remote_data = asyncio.run(fetch_data(url))
-    # Transform the fetched remote data
-    remote_data = transform_remote_data(remote_data)
-
-    # If both local and remote data are available, synchronize and save
-    if local_data and remote_data:
-        sync_local_data_with_remote(local_data, remote_data)
-        write_to_file(local_file_path, local_data)
-    else:
-        print("Failed to fetch model data from either local file or URL.")
-
-# Entry point of the script
-if __name__ == "__main__":
-    main()

.github/workflows/ghcr_deploy.yml

@@ -1,389 +0,0 @@
-# this workflow is triggered by an API call when there is a new PyPI release of LiteLLM
-name: Build, Publish LiteLLM Docker Image. New Release
-on:
-  workflow_dispatch:
-    inputs:
-      tag:
-        description: "The tag version you want to build"
-      release_type:
-        description: "The release type you want to build. Can be 'latest', 'stable', 'dev'"
-        type: string
-        default: "latest"
-      commit_hash:
-        description: "Commit hash"
-        required: true
-
-# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
-  CHART_NAME: litellm-helm
-
-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
-jobs:
-  # print commit hash, tag, and release type
-  print:
-    runs-on: ubuntu-latest
-    steps:
-      - run: |
-          echo "Commit hash: ${{ github.event.inputs.commit_hash }}"
-          echo "Tag: ${{ github.event.inputs.tag }}"
-          echo "Release type: ${{ github.event.inputs.release_type }}"
-  docker-hub-deploy:
-    if: github.repository == 'BerriAI/litellm'
-    runs-on: ubuntu-latest
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      -
-        name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          tags: litellm/litellm:${{ github.event.inputs.tag || 'latest' }} 
-      -
-        name: Build and push litellm-database image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          file: ./docker/Dockerfile.database
-          tags: litellm/litellm-database:${{ github.event.inputs.tag || 'latest' }}
-      -
-        name: Build and push litellm-spend-logs image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          file: ./litellm-js/spend-logs/Dockerfile
-          tags: litellm/litellm-spend_logs:${{ github.event.inputs.tag || 'latest' }}
-      
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
-      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
-      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
-      - name: Build and push Docker image
-        uses: docker/build-push-action@4976231911ebf5f32aad765192d35f942aa48cb8
-        with:
-          context: .
-          push: true
-          tags: |
-            ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta.outputs.labels }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-          
-  build-and-push-image-database:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for database Dockerfile
-        id: meta-database
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-database
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push Database Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./docker/Dockerfile.database
-          push: true
-          tags: |
-            ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta-database.outputs.labels }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-            
-  build-and-push-image-non_root:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for non_root Dockerfile
-        id: meta-non_root
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-non_root
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push non_root Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./docker/Dockerfile.non_root
-          push: true
-          tags: |
-            ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta-non_root.outputs.labels }} 
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-  
-  build-and-push-image-spend-logs:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for spend-logs Dockerfile
-        id: meta-spend-logs
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-spend_logs
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push Database Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./litellm-js/spend-logs/Dockerfile
-          push: true
-          tags: |
-            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-stable', env.REGISTRY) || '' }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-
-  build-and-push-helm-chart:
-    if: github.event.inputs.release_type  != 'dev'
-    needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: lowercase github.repository_owner
-        run: |
-          echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
-    
-      - name: Get LiteLLM Latest Tag
-        id: current_app_tag
-        shell: bash
-        run: |
-          LATEST_TAG=$(git describe --tags --exclude "*dev*" --abbrev=0)
-          if [ -z "${LATEST_TAG}" ]; then
-            echo "latest_tag=latest" | tee -a $GITHUB_OUTPUT
-          else
-            echo "latest_tag=${LATEST_TAG}" | tee -a $GITHUB_OUTPUT
-          fi
-
-      - name: Get last published chart version
-        id: current_version
-        shell: bash
-        run: |
-          CHART_LIST=$(helm show chart oci://${{ env.REGISTRY }}/${{ env.REPO_OWNER }}/${{ env.CHART_NAME }} 2>/dev/null || true)
-          if [ -z "${CHART_LIST}" ]; then
-            echo "current-version=0.1.0" | tee -a $GITHUB_OUTPUT
-          else
-            printf '%s' "${CHART_LIST}" | grep '^version:' | awk 'BEGIN{FS=":"}{print "current-version="$2}' | tr -d " " | tee -a $GITHUB_OUTPUT
-          fi
-        env:
-          HELM_EXPERIMENTAL_OCI: '1'
-
-      # Automatically update the helm chart version one "patch" level
-      - name: Bump release version
-        id: bump_version
-        uses: christian-draeger/increment-semantic-version@1.1.0
-        with:
-          current-version: ${{ steps.current_version.outputs.current-version || '0.1.0' }}
-          version-fragment: 'bug'
-
-      - uses: ./.github/actions/helm-oci-chart-releaser
-        with:
-          name: ${{ env.CHART_NAME }}
-          repository: ${{ env.REPO_OWNER }}
-          tag: ${{ github.event.inputs.chartVersion || steps.bump_version.outputs.next-version || '0.1.0' }}
-          app_version: ${{ steps.current_app_tag.outputs.latest_tag }}
-          path: deploy/charts/${{ env.CHART_NAME }}
-          registry: ${{ env.REGISTRY }}
-          registry_username: ${{ github.actor }}
-          registry_password: ${{ secrets.GITHUB_TOKEN }}
-          update_dependencies: true
-
-  release:
-    name: "New LiteLLM Release"
-    needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
-
-    runs-on: "ubuntu-latest"
-   
-    steps:
-      - name: Display version
-        run: echo "Current version is ${{ github.event.inputs.tag }}"
-      - name: "Set Release Tag"
-        run: echo "RELEASE_TAG=${{ github.event.inputs.tag }}" >> $GITHUB_ENV
-      - name: Display release tag
-        run: echo "RELEASE_TAG is $RELEASE_TAG"
-      - name: "Create release"
-        uses: "actions/github-script@v6"
-        with:
-          github-token: "${{ secrets.GITHUB_TOKEN }}"
-          script: |
-            const commitHash = "${{ github.event.inputs.commit_hash}}";
-            console.log("Commit Hash:", commitHash); // Add this line for debugging
-            try {
-              const response = await github.rest.repos.createRelease({
-                draft: false,
-                generate_release_notes: true,
-                target_commitish: commitHash,
-                name: process.env.RELEASE_TAG,
-                owner: context.repo.owner,
-                prerelease: false,
-                repo: context.repo.repo,
-                tag_name: process.env.RELEASE_TAG,
-              });
-      
-              core.exportVariable('RELEASE_ID', response.data.id);
-              core.exportVariable('RELEASE_UPLOAD_URL', response.data.upload_url);
-            } catch (error) {
-              core.setFailed(error.message);
-            }
-      - name: Fetch Release Notes
-        id: release-notes
-        uses: actions/github-script@v6
-        with:
-          github-token: "${{ secrets.GITHUB_TOKEN }}"
-          script: |
-            try {
-              const response = await github.rest.repos.getRelease({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                release_id: process.env.RELEASE_ID,
-              });
-              const formattedBody = JSON.stringify(response.data.body).slice(1, -1);
-              return formattedBody;
-            } catch (error) {
-              core.setFailed(error.message);
-            }
-        env:
-          RELEASE_ID: ${{ env.RELEASE_ID }}
-      - name: Github Releases To Discord
-        env:
-          WEBHOOK_URL: ${{ secrets.WEBHOOK_URL }}
-          REALEASE_TAG: ${{ env.RELEASE_TAG }}
-          RELEASE_NOTES: ${{ steps.release-notes.outputs.result }}
-        run: |
-          curl -H "Content-Type: application/json" -X POST -d '{
-            "content": "New LiteLLM release '"${RELEASE_TAG}"'",
-            "username": "Release Changelog",
-            "avatar_url": "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png",
-            "embeds": [
-              {
-                "title": "Changelog for LiteLLM '"${RELEASE_TAG}"'",
-                "description": "'"${RELEASE_NOTES}"'",
-                "color": 2105893
-              }
-            ]
-          }' $WEBHOOK_URL
-

.github/workflows/ghcr_helm_deploy.yml

@@ -1,67 +0,0 @@
-# this workflow is triggered by an API call when there is a new PyPI release of LiteLLM
-name: Build, Publish LiteLLM Helm Chart. New Release
-on:
-  workflow_dispatch:
-    inputs:
-      chartVersion:
-        description: "Update the helm chart's version to this"
-
-# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
-  REPO_OWNER: ${{github.repository_owner}}
-
-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
-jobs:        
-  build-and-push-helm-chart:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      
-      - name: lowercase github.repository_owner
-        run: |
-          echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
-
-      - name: Get LiteLLM Latest Tag
-        id: current_app_tag
-        uses: WyriHaximus/github-action-get-previous-tag@v1.3.0
-
-      - name: Get last published chart version
-        id: current_version
-        shell: bash
-        run: helm show chart oci://${{ env.REGISTRY }}/${{ env.REPO_OWNER }}/litellm-helm | grep '^version:' | awk 'BEGIN{FS=":"}{print "current-version="$2}' | tr -d " " | tee -a $GITHUB_OUTPUT
-        env:
-          HELM_EXPERIMENTAL_OCI: '1'
-
-      # Automatically update the helm chart version one "patch" level
-      - name: Bump release version
-        id: bump_version
-        uses: christian-draeger/increment-semantic-version@1.1.0
-        with:
-          current-version: ${{ steps.current_version.outputs.current-version || '0.1.0' }}
-          version-fragment: 'bug'
-
-      - name: Lint helm chart
-        run: helm lint deploy/charts/litellm-helm
-
-      - uses: ./.github/actions/helm-oci-chart-releaser
-        with:
-          name: litellm-helm
-          repository: ${{ env.REPO_OWNER }}
-          tag: ${{ github.event.inputs.chartVersion || steps.bump_version.outputs.next-version || '0.1.0' }}
-          app_version: ${{ steps.current_app_tag.outputs.tag || 'latest' }}
-          path: deploy/charts/litellm-helm
-          registry: ${{ env.REGISTRY }}
-          registry_username: ${{ github.actor }}
-          registry_password: ${{ secrets.GITHUB_TOKEN }}
-          update_dependencies: true
-  

.github/workflows/helm_unit_test.yml

@@ -1,27 +0,0 @@
-name: Helm unit test
-
-on:
-  pull_request:
-  push:
-    branches:
-      - main
-
-jobs:
-  unit-test:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Set up Helm 3.11.1
-        uses: azure/setup-helm@v1
-        with:
-          version: '3.11.1'
-
-      - name: Install Helm Unit Test Plugin
-        run: |
-          helm plugin install https://github.com/helm-unittest/helm-unittest --version v0.4.4
-
-      - name: Run unit tests
-        run:
-          helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm

.github/workflows/interpret_load_test.py

@@ -1,138 +0,0 @@
-import csv
-import os
-from github import Github
-
-
-def interpret_results(csv_file):
-    with open(csv_file, newline="") as csvfile:
-        csvreader = csv.DictReader(csvfile)
-        rows = list(csvreader)
-        """
-        in this csv reader
-        - Create 1 new column "Status"
-        - if a row has a median response time < 300 and an average response time < 300, Status = "Passed ✅"
-        - if a row has a median response time >= 300 or an average response time >= 300, Status = "Failed ❌"
-        - Order the table in this order Name, Status, Median Response Time, Average Response Time, Requests/s,Failures/s, Min Response Time, Max Response Time, all other columns
-        """
-
-        # Add a new column "Status"
-        for row in rows:
-            median_response_time = float(
-                row["Median Response Time"].strip().rstrip("ms")
-            )
-            average_response_time = float(
-                row["Average Response Time"].strip().rstrip("s")
-            )
-
-            request_count = int(row["Request Count"])
-            failure_count = int(row["Failure Count"])
-
-            failure_percent = round((failure_count / request_count) * 100, 2)
-
-            # Determine status based on conditions
-            if (
-                median_response_time < 300
-                and average_response_time < 300
-                and failure_percent < 5
-            ):
-                row["Status"] = "Passed ✅"
-            else:
-                row["Status"] = "Failed ❌"
-
-        # Construct Markdown table header
-        markdown_table = "| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |"
-        markdown_table += (
-            "\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |"
-        )
-
-        # Construct Markdown table rows
-        for row in rows:
-            markdown_table += f"\n| {row['Name']} | {row['Status']} | {row['Median Response Time']} | {row['Average Response Time']} | {row['Requests/s']} | {row['Failures/s']} | {row['Request Count']} | {row['Failure Count']} | {row['Min Response Time']} | {row['Max Response Time']} |"
-    print("markdown table: ", markdown_table)
-    return markdown_table
-
-
-def _get_docker_run_command_stable_release(release_version):
-    return f"""
-\n\n
-## Docker Run LiteLLM Proxy
-
-```
-docker run \\
--e STORE_MODEL_IN_DB=True \\
--p 4000:4000 \\
-ghcr.io/berriai/litellm:litellm_stable_release_branch-{release_version}
-```
-    """
-
-
-def _get_docker_run_command(release_version):
-    return f"""
-\n\n
-## Docker Run LiteLLM Proxy
-
-```
-docker run \\
--e STORE_MODEL_IN_DB=True \\
--p 4000:4000 \\
-ghcr.io/berriai/litellm:main-{release_version}
-```
-    """
-
-
-def get_docker_run_command(release_version):
-    if "stable" in release_version:
-        return _get_docker_run_command_stable_release(release_version)
-    else:
-        return _get_docker_run_command(release_version)
-
-
-if __name__ == "__main__":
-    csv_file = "load_test_stats.csv"  # Change this to the path of your CSV file
-    markdown_table = interpret_results(csv_file)
-
-    # Update release body with interpreted results
-    github_token = os.getenv("GITHUB_TOKEN")
-    g = Github(github_token)
-    repo = g.get_repo(
-        "BerriAI/litellm"
-    )  # Replace with your repository's username and name
-    latest_release = repo.get_latest_release()
-    print("got latest release: ", latest_release)
-    print(latest_release.title)
-    print(latest_release.tag_name)
-
-    release_version = latest_release.title
-
-    print("latest release body: ", latest_release.body)
-    print("markdown table: ", markdown_table)
-
-    # check if "Load Test LiteLLM Proxy Results" exists
-    existing_release_body = latest_release.body
-    if "Load Test LiteLLM Proxy Results" in latest_release.body:
-        # find the "Load Test LiteLLM Proxy Results" section and delete it
-        start_index = latest_release.body.find("Load Test LiteLLM Proxy Results")
-        existing_release_body = latest_release.body[:start_index]
-
-    docker_run_command = get_docker_run_command(release_version)
-    print("docker run command: ", docker_run_command)
-
-    new_release_body = (
-        existing_release_body
-        + docker_run_command
-        + "\n\n"
-        + "### Don't want to maintain your internal proxy? get in touch 🎉"
-        + "\nHosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat"
-        + "\n\n"
-        + "## Load Test LiteLLM Proxy Results"
-        + "\n\n"
-        + markdown_table
-    )
-    print("new release body: ", new_release_body)
-    try:
-        latest_release.update_release(
-            name=latest_release.tag_name,
-            message=new_release_body,
-        )
-    except Exception as e:
-        print(e)

.github/workflows/label-mlops.yml

@@ -1,17 +0,0 @@
-name: Label ML Ops Team Issues
-
-on:
-  issues:
-    types:
-      - opened
-
-jobs:
-  add-mlops-label:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check if ML Ops Team is selected
-        uses: actions-ecosystem/action-add-labels@v1
-        if: contains(github.event.issue.body, '### Are you a ML Ops Team?') && contains(github.event.issue.body, 'Yes')
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          labels: "mlops user request"

.github/workflows/load_test.yml

@@ -1,59 +0,0 @@
-name: Test Locust Load Test
-
-on:
-  workflow_run:
-    workflows: ["Build, Publish LiteLLM Docker Image. New Release"]
-    types:
-      - completed
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v1
-      - name: Setup Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: '3.x'
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install PyGithub
-      - name: re-deploy proxy
-        run: |
-          echo "Current working directory: $PWD"
-          ls
-          python ".github/workflows/redeploy_proxy.py"
-        env:
-          LOAD_TEST_REDEPLOY_URL1: ${{ secrets.LOAD_TEST_REDEPLOY_URL1 }}
-          LOAD_TEST_REDEPLOY_URL2: ${{ secrets.LOAD_TEST_REDEPLOY_URL2 }}
-        working-directory: ${{ github.workspace }}
-      - name: Run Load Test
-        id: locust_run
-        uses: BerriAI/locust-github-action@master
-        with:
-          LOCUSTFILE: ".github/workflows/locustfile.py"
-          URL:  "https://post-release-load-test-proxy.onrender.com/"
-          USERS: "20"
-          RATE: "20"
-          RUNTIME: "300s"
-      - name: Process Load Test Stats
-        run: |
-          echo "Current working directory: $PWD"
-          ls
-          python ".github/workflows/interpret_load_test.py"
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        working-directory: ${{ github.workspace }}
-      - name: Upload CSV as Asset to Latest Release
-        uses: xresloader/upload-to-github-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          file: "load_test_stats.csv;load_test.html"
-          update_latest_release: true
-          tag_name: "load-test"
-          overwrite: true

.github/workflows/locustfile.py

@@ -1,28 +0,0 @@
-from locust import HttpUser, task, between
-
-
-class MyUser(HttpUser):
-    wait_time = between(1, 5)
-
-    @task
-    def chat_completion(self):
-        headers = {
-            "Content-Type": "application/json",
-            "Authorization": "Bearer sk-8N1tLOOyH8TIxwOLahhIVg",
-            # Include any additional headers you may need for authentication, etc.
-        }
-
-        # Customize the payload with "model" and "messages" keys
-        payload = {
-            "model": "fake-openai-endpoint",
-            "messages": [
-                {"role": "system", "content": "You are a chat bot."},
-                {"role": "user", "content": "Hello, how are you?"},
-            ],
-            # Add more data as necessary
-        }
-
-        # Make a POST request to the "chat/completions" endpoint
-        response = self.client.post("chat/completions", json=payload, headers=headers)
-
-        # Print or log the response if needed

.github/workflows/main.yml

@@ -1,34 +0,0 @@
-name: Publish Dev Release to PyPI
-
-on:
-  workflow_dispatch:
-  
-jobs:
-  publish-dev-release:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v2
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8  # Adjust the Python version as needed
-
-      - name: Install dependencies
-        run: pip install toml twine
-
-      - name: Read version from pyproject.toml
-        id: read-version
-        run: |
-          version=$(python -c 'import toml; print(toml.load("pyproject.toml")["tool"]["commitizen"]["version"])')
-          printf "LITELLM_VERSION=%s" "$version" >> $GITHUB_ENV
-
-      - name: Check if version exists on PyPI
-        id: check-version
-        run: |
-          set -e
-          if twine check --repository-url https://pypi.org/simple/ "litellm==$LITELLM_VERSION" >/dev/null 2>&1; then
-            echo "Version $LITELLM_VERSION already exists on PyPI. Skipping publish."
-     

.github/workflows/read_pyproject_version.yml

@@ -1,31 +0,0 @@
-name: Read Version from pyproject.toml
-
-on:
-  push:
-    branches:
-      - main  # Change this to the default branch of your repository
-
-jobs:
-  read-version:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v2
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8  # Adjust the Python version as needed
-
-      - name: Install dependencies
-        run: pip install toml
-
-      - name: Read version from pyproject.toml
-        id: read-version
-        run: |
-          version=$(python -c 'import toml; print(toml.load("pyproject.toml")["tool"]["commitizen"]["version"])')
-          printf "LITELLM_VERSION=%s" "$version" >> $GITHUB_ENV
-
-      - name: Display version
-        run: echo "Current version is $LITELLM_VERSION"

.github/workflows/redeploy_proxy.py

@@ -1,20 +0,0 @@
-"""
-
-redeploy_proxy.py
-"""
-
-import os
-import requests
-import time
-
-# send a get request to this endpoint
-deploy_hook1 = os.getenv("LOAD_TEST_REDEPLOY_URL1")
-response = requests.get(deploy_hook1, timeout=20)
-
-
-deploy_hook2 = os.getenv("LOAD_TEST_REDEPLOY_URL2")
-response = requests.get(deploy_hook2, timeout=20)
-
-print("SENT GET REQUESTS to re-deploy proxy")
-print("sleeeping.... for 60s")
-time.sleep(60)

.github/workflows/reset_stable.yml

@@ -1,39 +0,0 @@
-name: Reset litellm_stable branch
-
-on:
-  release:
-    types: [published, created]
-jobs:
-  update-stable-branch:
-    if: ${{ startsWith(github.event.release.tag_name, 'v') && !endsWith(github.event.release.tag_name, '-stable') }}
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      - name: Reset litellm_stable_release_branch branch to the release commit
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          # Configure Git user
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-          
-          # Fetch all branches and tags
-          git fetch --all
-
-          # Check if the litellm_stable_release_branch branch exists
-          if git show-ref --verify --quiet refs/remotes/origin/litellm_stable_release_branch; then
-            echo "litellm_stable_release_branch branch exists."
-            git checkout litellm_stable_release_branch
-          else
-            echo "litellm_stable_release_branch branch does not exist. Creating it."
-            git checkout -b litellm_stable_release_branch
-          fi
-
-          # Reset litellm_stable_release_branch branch to the release commit
-          git reset --hard $GITHUB_SHA
-
-          # Push the updated litellm_stable_release_branch branch
-          git push origin litellm_stable_release_branch --force

.github/workflows/results_stats.csv

@@ -1,27 +0,0 @@
-Date,"Ben 
-Ashley",Tom Brooks,Jimmy Cooney,"Sue 
-Daniels",Berlinda Fong,Terry Jones,Angelina Little,Linda Smith
-10/1,FALSE,TRUE,TRUE,TRUE,TRUE,TRUE,FALSE,TRUE
-10/2,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/3,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/4,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/5,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/6,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/7,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/8,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/9,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/10,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/11,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/12,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/13,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/14,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/15,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/16,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/17,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/18,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/19,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/20,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/21,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/22,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-10/23,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE,FALSE
-Total,0,1,1,1,1,1,0,1

.github/workflows/stale.yml

@@ -1,20 +0,0 @@
-name: "Stale Issue Management"
-
-on:
-  schedule:
-    - cron: '0 0 * * *' # Runs daily at midnight UTC
-  workflow_dispatch:
-
-jobs:
-  stale:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/stale@v8
-        with:
-          repo-token: "${{ secrets.GITHUB_TOKEN }}"
-          stale-issue-message: "This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs."
-          stale-pr-message: "This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs."
-          days-before-stale: 90        # Revert to 60 days
-          days-before-close: 7         # Revert to 7 days
-          stale-issue-label: "stale"
-          operations-per-run: 1000

.github/workflows/update_release.py

@@ -1,54 +0,0 @@
-import os
-import requests
-from datetime import datetime
-
-# GitHub API endpoints
-GITHUB_API_URL = "https://api.github.com"
-REPO_OWNER = "BerriAI"
-REPO_NAME = "litellm"
-
-# GitHub personal access token (required for uploading release assets)
-GITHUB_ACCESS_TOKEN = os.environ.get("GITHUB_ACCESS_TOKEN")
-
-# Headers for GitHub API requests
-headers = {
-    "Accept": "application/vnd.github+json",
-    "Authorization": f"Bearer {GITHUB_ACCESS_TOKEN}",
-    "X-GitHub-Api-Version": "2022-11-28",
-}
-
-# Get the latest release
-releases_url = f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/releases/latest"
-response = requests.get(releases_url, headers=headers)
-latest_release = response.json()
-print("Latest release:", latest_release)
-
-# Upload an asset to the latest release
-upload_url = latest_release["upload_url"].split("{?")[0]
-asset_name = "results_stats.csv"
-asset_path = os.path.join(os.getcwd(), asset_name)
-print("upload_url:", upload_url)
-
-with open(asset_path, "rb") as asset_file:
-    asset_data = asset_file.read()
-
-upload_payload = {
-    "name": asset_name,
-    "label": "Load test results",
-    "created_at": datetime.utcnow().isoformat() + "Z",
-}
-
-upload_headers = headers.copy()
-upload_headers["Content-Type"] = "application/octet-stream"
-
-upload_response = requests.post(
-    upload_url,
-    headers=upload_headers,
-    data=asset_data,
-    params=upload_payload,
-)
-
-if upload_response.status_code == 201:
-    print(f"Asset '{asset_name}' uploaded successfully to the latest release.")
-else:
-    print(f"Failed to upload asset. Response: {upload_response.text}")

.gitignore

@@ -1,85 +1,55 @@
-.venv
-.env
-.newenv
-newenv/*
-litellm/proxy/myenv/*
-litellm_uuid.txt
-__pycache__/
-*.pyc
-bun.lockb
-**/.DS_Store
-.aider*
-litellm_results.jsonl
-secrets.toml
-.gitignore
-litellm/proxy/litellm_secrets.toml
-litellm/proxy/api_log.json
-.idea/
-router_config.yaml
-litellm_server/config.yaml
-litellm/proxy/_secret_config.yaml
-.aws-sam/
-litellm/tests/aiologs.log
-litellm/tests/exception_data.txt
-litellm/tests/config_*.yaml
-litellm/tests/langfuse.log
-langfuse.log
-.langfuse.log
-litellm/tests/test_custom_logger.py
-litellm/tests/langfuse.log
-litellm/tests/dynamo*.log
-.vscode/settings.json
-litellm/proxy/log.txt
-proxy_server_config_@.yaml
-.gitignore
-proxy_server_config_2.yaml
-litellm/proxy/secret_managers/credentials.json
-hosted_config.yaml
-litellm/proxy/tests/node_modules
-litellm/proxy/tests/package.json
-litellm/proxy/tests/package-lock.json
-ui/litellm-dashboard/.next
-ui/litellm-dashboard/node_modules
-ui/litellm-dashboard/next-env.d.ts
-ui/litellm-dashboard/package.json
-ui/litellm-dashboard/package-lock.json
-deploy/charts/litellm/*.tgz
-deploy/charts/litellm/charts/*
-deploy/charts/*.tgz
-litellm/proxy/vertex_key.json
-**/.vim/
-**/node_modules
-kub.yaml
-loadtest_kub.yaml
-litellm/proxy/_new_secret_config.yaml
-litellm/proxy/_new_secret_config.yaml
-litellm/proxy/_super_secret_config.yaml
-litellm/proxy/_super_secret_config.yaml
-litellm/proxy/myenv/bin/activate
-litellm/proxy/myenv/bin/Activate.ps1
-myenv/*
-litellm/proxy/_experimental/out/404/index.html
-litellm/proxy/_experimental/out/model_hub/index.html
-litellm/proxy/_experimental/out/onboarding/index.html
-litellm/tests/log.txt
-litellm/tests/langfuse.log
-litellm/tests/langfuse.log
-litellm/proxy/google-cloud-sdk/*
-tests/llm_translation/log.txt
-venv/
-tests/local_testing/log.txt
+### node etc ###
 
-.codegpt
-litellm/proxy/_new_new_secret_config.yaml
-litellm/proxy/custom_guardrail.py
-litellm/proxy/_experimental/out/404.html
-litellm/proxy/_experimental/out/404.html
-litellm/proxy/_experimental/out/model_hub.html
-.mypy_cache/*
-litellm/proxy/application.log
-tests/llm_translation/vertex_test_account.json
-tests/llm_translation/test_vertex_key.json
-litellm/proxy/migrations/0_init/migration.sql
-litellm/proxy/db/migrations/0_init/migration.sql
-litellm/proxy/db/migrations/*
-litellm/proxy/migrations/*
+# Logs
+data-node
+logs
+*.log
+
+# Runtime data
+pids
+*.pid
+*.seed
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+
+# Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Compiled Dirs (http://nodejs.org/api/addons.html)
+build/
+dist/
+public/main.js
+public/main.js.map
+public/main.js.LICENSE.txt
+client/public/main.js
+client/public/main.js.map
+client/public/main.js.LICENSE.txt
+
+# Dependency directorys
+# Deployed apps should consider commenting these lines out:
+# see https://npmjs.org/doc/faq.html#Should-I-check-my-node_modules-folder-into-git
+node_modules/
+meili_data/
+api/node_modules/
+client/node_modules/
+bower_components/
+
+# Floobits
+.floo
+.floobit
+.floo
+.flooignore
+
+# Environment
+.env
+cache.json
+api/data/
+owner.yml
+archive
+.vscode/settings.json
+
+src/style - official.css

.pre-commit-config.yaml

@@ -1,49 +0,0 @@
-repos:
--   repo: local
-    hooks:
-    -   id: pyright
-        name: pyright
-        entry: pyright
-        language: system
-        types: [python]
-        files: ^litellm/
-    -   id: isort
-        name: isort
-        entry: isort
-        language: system
-        types: [python]
-        files: litellm/.*\.py
-        exclude: ^litellm/__init__.py$
--   repo: https://github.com/psf/black
-    rev: 24.2.0
-    hooks:
-    - id: black
--   repo: https://github.com/pycqa/flake8
-    rev: 7.0.0  # The version of flake8 to use
-    hooks:
-    -  id: flake8
-       exclude: ^litellm/tests/|^litellm/proxy/tests/|^litellm/tests/litellm/|^tests/litellm/
-       additional_dependencies: [flake8-print]
-       files: litellm/.*\.py
-    # -  id: flake8
-    #    name: flake8 (router.py function length)
-    #    files: ^litellm/router\.py$
-    #    args: [--max-function-length=40]
-    # #    additional_dependencies: [flake8-functions]
--   repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
-    hooks:
-      - id: poetry-check
--   repo: local
-    hooks:
-    -   id: check-files-match
-        name: Check if files match
-        entry: python3 ci_cd/check_files_match.py
-        language: system
-    # -   id: check-file-length
-    #     name: Check file length
-    #     entry: python check_file_length.py
-    #     args: ["10000"]  # set your desired maximum number of lines
-    #     language: python
-    #     files: litellm/.*\.py
-    #     exclude: ^litellm/tests/

Dockerfile

@@ -1,83 +0,0 @@
-# Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/python:latest-dev
-
-# Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/python:latest-dev
-# Builder stage
-FROM $LITELLM_BUILD_IMAGE AS builder
-
-# Set the working directory to /app
-WORKDIR /app
-
-USER root
-
-# Install build dependencies
-RUN apk update && \
-    apk add --no-cache gcc python3-dev openssl openssl-dev
-
-
-RUN pip install --upgrade pip && \
-    pip install build
-
-# Copy the current directory contents into the container at /app
-COPY . .
-
-# Build Admin UI
-RUN chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
-
-# Build the package
-RUN rm -rf dist/* && python -m build
-
-# There should be only one wheel file now, assume the build only creates one
-RUN ls -1 dist/*.whl | head -1
-
-# Install the package
-RUN pip install dist/*.whl
-
-# install dependencies as wheels
-RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
-
-# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0 
-RUN pip install redisvl==0.0.7 --no-deps
-
-# ensure pyjwt is used, not jwt
-RUN pip uninstall jwt -y
-RUN pip uninstall PyJWT -y
-RUN pip install PyJWT==2.9.0 --no-cache-dir
-
-# Build Admin UI
-RUN chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
-
-# Runtime stage
-FROM $LITELLM_RUNTIME_IMAGE AS runtime
-
-# Ensure runtime stage runs as root
-USER root
-
-# Install runtime dependencies
-RUN apk update && \
-    apk add --no-cache openssl
-
-WORKDIR /app
-# Copy the current directory contents into the container at /app
-COPY . .
-RUN ls -la /app
-
-# Copy the built wheel from the builder stage to the runtime stage; assumes only one wheel file is present
-COPY --from=builder /app/dist/*.whl .
-COPY --from=builder /wheels/ /wheels/
-
-# Install the built wheel using pip; again using a wildcard if it's the only file
-RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ && rm -f *.whl && rm -rf /wheels
-
-# Generate prisma client
-RUN prisma generate
-RUN chmod +x docker/entrypoint.sh
-RUN chmod +x docker/prod_entrypoint.sh
-
-EXPOSE 4000/tcp
-
-ENTRYPOINT ["docker/prod_entrypoint.sh"]
-
-# Append "--detailed_debug" to the end of CMD to view detailed debug logs 
-CMD ["--port", "4000"]

LICENSE.md

@@ -1,11 +1,6 @@
-Portions of this software are licensed as follows:
-
-* All content that resides under the "enterprise/" directory of this repository, if that directory exists, is licensed under the license defined in "enterprise/LICENSE".
-* Content outside of the above mentioned directories or restrictions above is available under the MIT license as defined below.
----
 MIT License
 
-Copyright (c) 2023 Berri AI
+Copyright (c) 2023 Danny Avila
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

Makefile

@@ -1,32 +0,0 @@
-# LiteLLM Makefile
-# Simple Makefile for running tests and basic development tasks
-
-.PHONY: help test test-unit test-integration lint format
-
-# Default target
-help:
-	@echo "Available commands:"
-	@echo "  make test               - Run all tests"
-	@echo "  make test-unit          - Run unit tests"
-	@echo "  make test-integration   - Run integration tests"
-	@echo "  make test-unit-helm     - Run helm unit tests"
-
-install-dev:
-	poetry install --with dev
-
-lint: install-dev
-	poetry run pip install types-requests types-setuptools types-redis types-PyYAML
-	cd litellm && poetry run mypy . --ignore-missing-imports
-
-# Testing
-test:
-	poetry run pytest tests/
-
-test-unit:
-	poetry run pytest tests/litellm/
-
-test-integration:
-	poetry run pytest tests/ -k "not litellm"
-
-test-unit-helm:
-	helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm

README.md

@@ -1,413 +1,311 @@
-<h1 align="center">
-        🚅 LiteLLM
-    </h1>
-    <p align="center">
-        <p align="center">
-        <a href="https://render.com/deploy?repo=https://github.com/BerriAI/litellm" target="_blank" rel="nofollow"><img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to Render"></a>
-        <a href="https://railway.app/template/HLP0Ub?referralCode=jch2ME">
-          <img src="https://railway.app/button.svg" alt="Deploy on Railway">
-        </a>
-        </p>
-        <p align="center">Call all LLM APIs using the OpenAI format [Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, Groq etc.]
-        <br>
-    </p>
-<h4 align="center"><a href="https://docs.litellm.ai/docs/simple_proxy" target="_blank">LiteLLM Proxy Server (LLM Gateway)</a> | <a href="https://docs.litellm.ai/docs/hosted" target="_blank"> Hosted Proxy (Preview)</a> | <a href="https://docs.litellm.ai/docs/enterprise"target="_blank">Enterprise Tier</a></h4>
-<h4 align="center">
-    <a href="https://pypi.org/project/litellm/" target="_blank">
-        <img src="https://img.shields.io/pypi/v/litellm.svg" alt="PyPI Version">
-    </a>
-    <a href="https://dl.circleci.com/status-badge/redirect/gh/BerriAI/litellm/tree/main" target="_blank">
-        <img src="https://dl.circleci.com/status-badge/img/gh/BerriAI/litellm/tree/main.svg?style=svg" alt="CircleCI">
-    </a>
-    <a href="https://www.ycombinator.com/companies/berriai">
-        <img src="https://img.shields.io/badge/Y%20Combinator-W23-orange?style=flat-square" alt="Y Combinator W23">
-    </a>
-    <a href="https://wa.link/huol9n">
-        <img src="https://img.shields.io/static/v1?label=Chat%20on&message=WhatsApp&color=success&logo=WhatsApp&style=flat-square" alt="Whatsapp">
-    </a>
-    <a href="https://discord.gg/wuPM9dRgDw">
-        <img src="https://img.shields.io/static/v1?label=Chat%20on&message=Discord&color=blue&logo=Discord&style=flat-square" alt="Discord">
-    </a>
-</h4>
+# ChatGPT Clone #
+https://user-images.githubusercontent.com/110412045/223754183-8b7f45ce-6517-4bd5-9b39-c624745bf399.mp4
 
-LiteLLM manages:
+## All AI Conversations under One Roof. ##
+  Assistant AIs are the future and OpenAI revolutionized this movement with ChatGPT. While numerous methods exist to integrate them, this app commemorates the original styling of ChatGPT, with the ability to integrate any current/future AI models, while improving upon original client features, such as conversation search and prompt templates (currently WIP).
 
-- Translate inputs to provider's `completion`, `embedding`, and `image_generation` endpoints
-- [Consistent output](https://docs.litellm.ai/docs/completion/output), text responses will always be available at `['choices'][0]['message']['content']`
-- Retry/fallback logic across multiple deployments (e.g. Azure/OpenAI) - [Router](https://docs.litellm.ai/docs/routing)
-- Set Budgets & Rate limits per project, api key, model [LiteLLM Proxy Server (LLM Gateway)](https://docs.litellm.ai/docs/simple_proxy)
+  This project was started early in Feb '23, anticipating the release of the official ChatGPT API from OpenAI, and now uses it. Through this clone, you can avoid ChatGPT Plus in favor of free or pay-per-call APIs. I will soon deploy a demo of this app. Feel free to contribute, clone, or fork. Currently dockerized.
 
-[**Jump to LiteLLM Proxy (LLM Gateway) Docs**](https://github.com/BerriAI/litellm?tab=readme-ov-file#openai-proxy---docs) <br>
-[**Jump to Supported LLM Providers**](https://github.com/BerriAI/litellm?tab=readme-ov-file#supported-providers-docs)
-
-🚨 **Stable Release:** Use docker images with the `-stable` tag. These have undergone 12 hour load tests, before being published. [More information about the release cycle here](https://docs.litellm.ai/docs/proxy/release_cycle)
-
-Support for more providers. Missing a provider or LLM Platform, raise a [feature request](https://github.com/BerriAI/litellm/issues/new?assignees=&labels=enhancement&projects=&template=feature_request.yml&title=%5BFeature%5D%3A+).
-
-# Usage ([**Docs**](https://docs.litellm.ai/docs/))
-
-> [!IMPORTANT]
-> LiteLLM v1.0.0 now requires `openai>=1.0.0`. Migration guide [here](https://docs.litellm.ai/docs/migration)  
-> LiteLLM v1.40.14+ now requires `pydantic>=2.0.0`. No changes required.
-
-<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/liteLLM_Getting_Started.ipynb">
-  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
-</a>
-
-```shell
-pip install litellm
-```
-
-```python
-from litellm import completion
-import os
-
-## set ENV variables
-os.environ["OPENAI_API_KEY"] = "your-openai-key"
-os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"
-
-messages = [{ "content": "Hello, how are you?","role": "user"}]
-
-# openai call
-response = completion(model="openai/gpt-4o", messages=messages)
-
-# anthropic call
-response = completion(model="anthropic/claude-3-sonnet-20240229", messages=messages)
-print(response)
-```
-
-### Response (OpenAI Format)
-
-```json
-{
-    "id": "chatcmpl-565d891b-a42e-4c39-8d14-82a1f5208885",
-    "created": 1734366691,
-    "model": "claude-3-sonnet-20240229",
-    "object": "chat.completion",
-    "system_fingerprint": null,
-    "choices": [
-        {
-            "finish_reason": "stop",
-            "index": 0,
-            "message": {
-                "content": "Hello! As an AI language model, I don't have feelings, but I'm operating properly and ready to assist you with any questions or tasks you may have. How can I help you today?",
-                "role": "assistant",
-                "tool_calls": null,
-                "function_call": null
-            }
-        }
-    ],
-    "usage": {
-        "completion_tokens": 43,
-        "prompt_tokens": 13,
-        "total_tokens": 56,
-        "completion_tokens_details": null,
-        "prompt_tokens_details": {
-            "audio_tokens": null,
-            "cached_tokens": 0
-        },
-        "cache_creation_input_tokens": 0,
-        "cache_read_input_tokens": 0
-    }
-}
-```
-
-Call any model supported by a provider, with `model=<provider_name>/<model_name>`. There might be provider-specific details here, so refer to [provider docs for more information](https://docs.litellm.ai/docs/providers)
-
-## Async ([Docs](https://docs.litellm.ai/docs/completion/stream#async-completion))
-
-```python
-from litellm import acompletion
-import asyncio
-
-async def test_get_response():
-    user_message = "Hello, how are you?"
-    messages = [{"content": user_message, "role": "user"}]
-    response = await acompletion(model="openai/gpt-4o", messages=messages)
-    return response
-
-response = asyncio.run(test_get_response())
-print(response)
-```
-
-## Streaming ([Docs](https://docs.litellm.ai/docs/completion/stream))
-
-liteLLM supports streaming the model response back, pass `stream=True` to get a streaming iterator in response.  
-Streaming is supported for all models (Bedrock, Huggingface, TogetherAI, Azure, OpenAI, etc.)
-
-```python
-from litellm import completion
-response = completion(model="openai/gpt-4o", messages=messages, stream=True)
-for part in response:
-    print(part.choices[0].delta.content or "")
-
-# claude 2
-response = completion('anthropic/claude-3-sonnet-20240229', messages, stream=True)
-for part in response:
-    print(part)
-```
-
-### Response chunk (OpenAI Format)
-
-```json
-{
-    "id": "chatcmpl-2be06597-eb60-4c70-9ec5-8cd2ab1b4697",
-    "created": 1734366925,
-    "model": "claude-3-sonnet-20240229",
-    "object": "chat.completion.chunk",
-    "system_fingerprint": null,
-    "choices": [
-        {
-            "finish_reason": null,
-            "index": 0,
-            "delta": {
-                "content": "Hello",
-                "role": "assistant",
-                "function_call": null,
-                "tool_calls": null,
-                "audio": null
-            },
-            "logprobs": null
-        }
-    ]
-}
-```
-
-## Logging Observability ([Docs](https://docs.litellm.ai/docs/observability/callbacks))
-
-LiteLLM exposes pre defined callbacks to send data to Lunary, MLflow, Langfuse, DynamoDB, s3 Buckets, Helicone, Promptlayer, Traceloop, Athina, Slack
-
-```python
-from litellm import completion
-
-## set env variables for logging tools (when using MLflow, no API key set up is required)
-os.environ["LUNARY_PUBLIC_KEY"] = "your-lunary-public-key"
-os.environ["HELICONE_API_KEY"] = "your-helicone-auth-key"
-os.environ["LANGFUSE_PUBLIC_KEY"] = ""
-os.environ["LANGFUSE_SECRET_KEY"] = ""
-os.environ["ATHINA_API_KEY"] = "your-athina-api-key"
-
-os.environ["OPENAI_API_KEY"] = "your-openai-key"
-
-# set callbacks
-litellm.success_callback = ["lunary", "mlflow", "langfuse", "athina", "helicone"] # log input/output to lunary, langfuse, supabase, athina, helicone etc
-
-#openai call
-response = completion(model="openai/gpt-4o", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
-```
-
-# LiteLLM Proxy Server (LLM Gateway) - ([Docs](https://docs.litellm.ai/docs/simple_proxy))
-
-Track spend + Load Balance across multiple projects
-
-[Hosted Proxy (Preview)](https://docs.litellm.ai/docs/hosted)
-
-The proxy provides:
-
-1. [Hooks for auth](https://docs.litellm.ai/docs/proxy/virtual_keys#custom-auth)
-2. [Hooks for logging](https://docs.litellm.ai/docs/proxy/logging#step-1---create-your-custom-litellm-callback-class)
-3. [Cost tracking](https://docs.litellm.ai/docs/proxy/virtual_keys#tracking-spend)
-4. [Rate Limiting](https://docs.litellm.ai/docs/proxy/users#set-rate-limits)
-
-## 📖 Proxy Endpoints - [Swagger Docs](https://litellm-api.up.railway.app/)
+## Updates
+<details open>
+<summary><strong>2023-03-16</strong></summary>
 
 
-## Quick Start Proxy - CLI
 
-```shell
-pip install 'litellm[proxy]'
-```
+[Latest release (v0.0.4)](https://github.com/danny-avila/chatgpt-clone/releases/tag/v0.0.4) includes Resubmitting messages & Branching messages, which mirrors official ChatGPT feature of editing a sent message, that then branches the conversation into separate message paths (works only with ChatGPT)
 
-### Step 1: Start litellm proxy
+Full details and [example here](https://github.com/danny-avila/chatgpt-clone/releases/tag/v0.0.4). Message search is on the docket
 
-```shell
-$ litellm --model huggingface/bigcode/starcoder
+</details>
 
-#INFO: Proxy running on http://0.0.0.0:4000
-```
-
-### Step 2: Make ChatCompletions Request to Proxy
+<details>
+<details>
+<summary><strong>2023-03-12</strong></summary>
 
 
-> [!IMPORTANT]
-> 💡 [Use LiteLLM Proxy with Langchain (Python, JS), OpenAI SDK (Python, JS) Anthropic SDK, Mistral SDK, LlamaIndex, Instructor, Curl](https://docs.litellm.ai/docs/proxy/user_keys)  
 
-```python
-import openai # openai v1.0.0+
-client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:4000") # set proxy to base_url
-# request sent to model set on litellm proxy, `litellm --model`
-response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
-    {
-        "role": "user",
-        "content": "this is a test request, write a short poem"
-    }
-])
 
-print(response)
-```
+Really thankful for all the issues reported and contributions made, the project's features and improvements have accelerated as result. Honorable mention is [wtlyu](https://github.com/wtlyu) for contributing a lot of mindful code, namely hostname configuration and mobile styling. I will upload images on next release for faster docker setup, and starting updating them simultaneously with this repo.
 
-## Proxy Key Management ([Docs](https://docs.litellm.ai/docs/proxy/virtual_keys))
 
-Connect the proxy with a Postgres DB to create proxy keys
 
+Many improvements across the board, the biggest is being able to start conversations simultaneously (again thanks to [wtlyu](https://github.com/wtlyu) for bringing it to my attention), as you can switch conversations or start a new chat without any response streaming from a prior one, as the backend will still process/save client responses. Just watch out for any rate limiting from OpenAI/Microsoft if this is done excessively.
+
+
+Adding support for conversation search is next! Thank you [mysticaltech](https://github.com/mysticaltech) for bringing up a method I can use for this.
+</details>
+<details>
+<summary><strong>2023-03-09</strong></summary>
+Released v.0.0.2
+
+Adds Sydney (jailbroken Bing AI) to the model menu. Thank you [DavesDevFails](https://github.com/DavesDevFails) for bringing it to my attention in this [issue](https://github.com/danny-avila/chatgpt-clone/issues/13). Bing/Sydney now correctly cite links, more styling to come. Fix some overlooked bugs, and model menu doesn't close upon deleting a customGpt.
+
+
+I've re-enabled the ChatGPT browser client (free version) since it might be working for most people, it no longer works for me. Sydney is the best free route anyway.
+</details>
+<details>
+<summary><strong>2023-03-07</strong></summary>
+Due to increased interest in the repo, I've dockerized the app as of this update for quick setup! See setup instructions below. I realize this still takes some time with installing docker dependencies, so it's on the roadmap to have a deployed demo. Besides this, I've made major improvements for a lot of the existing features across the board, mainly UI/UX.
+
+
+Also worth noting, the method to access the Free Version is no longer working, so I've removed it from model selection until further notice.
+</details>
+<summary><strong>Previous Updates</strong></summary>
+
+<details>
+<summary><strong>2023-03-04</strong></summary>
+Custom prompt prefixing and labeling is now supported through the official API. This nets some interesting results when you need ChatGPT for specific uses or entertainment. Select 'CustomGPT' in the model menu to configure this, and you can choose to save the configuration or reference it by conversation. Model selection will change by conversation.
+</details>
+<details>
+<summary><strong>2023-03-01</strong></summary>
+Official ChatGPT API is out! Removed davinci since the official API is extremely fast and 10x less expensive. Since user labeling and prompt prefixing is officially supported, I will add a View feature so you can set this within chat, which gives the UI an added use case. I've kept the BrowserClient, since it's free to use like the official site.
+
+The Messages UI correctly mirrors code syntax highlighting. The exact replication of the cursor is not 1-to-1 yet, but pretty close. Later on in the project, I'll implement tests for code edge cases and explore the possibility of running code in-browser. Right now, unknown code defaults to javascript, but will detect language as close as possible.
+</details>
+<details>
+<summary><strong>2023-02-21</strong></summary>
+BingAI is integrated (although sadly limited by Microsoft with the 5 msg/convo limit, 50 msgs/day). I will need to handle the case when Bing refuses to give more answers on top of the other styling features I have in mind. Official ChatGPT use is back with the new BrowserClient. Brainstorming how to handle the UI when the Ai model changes, since conversations can't be persisted between them (or perhaps build a way to achieve this at some level).
+</details>
+<details >
+<summary><strong>2023-02-15</strong></summary>
+Just got access to Bing AI so I'll be focusing on integrating that through waylaidwanderer's 'experimental' BingAIClient.
+</details>
+<details>
+<summary><strong>2023-02-14</strong></summary>
+
+Official ChatGPT use is no longer possible though I recently used it with waylaidwanderer's [reverse proxy method](https://github.com/waylaidwanderer/node-chatgpt-api/blob/main/README.md#using-a-reverse-proxy), and before that, through leaked models he also discovered.
+
+Currently, this project is only functional with the `text-davinci-003` model.
+</details>
+</details>
+
+# Table of Contents
+- [ChatGPT Clone](#chatgpt-clone)
+  - [All AI Conversations under One Roof.](#all-ai-conversations-under-one-roof)
+  - [Updates](#updates)
+- [Table of Contents](#table-of-contents)
+  - [Roadmap](#roadmap)
+    - [Features](#features)
+    - [Tech Stack](#tech-stack)
+  - [Getting Started](#getting-started)
+    - [Prerequisites](#prerequisites)
+  - [Usage](#usage)
+    - [Local](#local)
+    - [Docker](#docker)
+    - [Access Tokens](#access-tokens)
+    - [Proxy](#proxy)
+    - [User System](#user-system)
+    - [Updating](#updating)
+  - [Use Cases](#use-cases)
+  - [Origin](#origin)
+  - [Caveats](#caveats)
+    - [Regarding use of Official ChatGPT API](#regarding-use-of-official-chatgpt-api)
+  - [Contributing](#contributing)
+  - [License](#license)
+
+## Roadmap
+
+> **Warning**
+
+>  This is a work in progress. I'm building this in public. FYI there is still a lot of tech debt to cleanup. You can follow the progress here or on my [Linkedin](https://www.linkedin.com/in/danny-avila).
+
+Here are my recently completed and planned features:
+
+- [x] Persistent conversation
+- [x] Rename, delete conversations
+- [x] UI Error handling
+- [x] Bing AI integration
+- [x] AI model change handling (start new convos within existing, remembers last selected)
+- [x] Code block handling (highlighting, markdown, clipboard, language detection)
+- [x] Markdown handling
+- [x] Customize prompt prefix/label (custom ChatGPT using official API)
+- [x] Server convo pagination (limit fetch and load more with 'show more' button)
+- [x] Config file for easy startup (docker compose)
+- [x] Mobile styling (thanks to [wtlyu](https://github.com/wtlyu))
+- [x] Resubmit/edit sent messages (thanks to [wtlyu](https://github.com/wtlyu))
+- [ ] Message Search
+- [ ] Custom params for ChatGPT API (temp, top_p, presence_penalty)
+- [ ] Bing AI Styling (params, suggested responses, convo end, etc.) - **In progress**
+- [ ] Add warning before clearing convos
+- [ ] Build test suite for CI/CD
+- [ ] Prompt Templates/Search
+- [ ] Refactor/clean up code (tech debt)
+- [ ] Optional use of local storage for credentials
+- [ ] Deploy demo
+
+### Features
+
+- Response streaming identical to ChatGPT through server-sent events
+- UI from original ChatGPT, including Dark mode
+- AI model selection (official ChatGPT API, BingAI, ChatGPT Free)
+- Create and Save custom ChatGPTs*
+
+^* ChatGPT can be 'customized' by setting a system message or prompt prefix and alternate 'role' to the API request
+
+[More info here](https://platform.openai.com/docs/guides/chat/instructing-chat-models). Here's an [example from this app.]()
+
+### Tech Stack
+
+- Utilizes [node-chatgpt-api](https://github.com/waylaidwanderer/node-chatgpt-api)
+- No React boilerplate/toolchain/clone tutorials, created from scratch with react@latest
+- Use of Tailwind CSS and [shadcn/ui](https://github.com/shadcn/ui) components
+- Docker, useSWR, Redux, Express, MongoDB, [Keyv](https://www.npmjs.com/package/keyv)
+
+## Getting Started
+
+### Prerequisites
+- npm
+- Node.js >= 19.0.0
+- MongoDB installed or [MongoDB Atlas](https://account.mongodb.com/account/login) (required if not using Docker)
+- [Docker (optional)](https://www.docker.com/get-started/)
+- [OpenAI API key](https://platform.openai.com/account/api-keys)
+- BingAI, ChatGPT access tokens (optional, free AIs)
+
+## Usage
+
+- **Clone/download** the repo down where desired
 ```bash
-# Get the code
-git clone https://github.com/BerriAI/litellm
+  git clone https://github.com/danny-avila/chatgpt-clone.git
+```
+- If using MongoDB Atlas, remove `&w=majority` from default connection string.
 
-# Go to folder
-cd litellm
+### Local
+- **Run npm** install in both the api and client directories
+- **Provide** all credentials, (API keys, access tokens, and Mongo Connection String) in api/.env [(see .env example)](api/.env.example)
+- **Run** `npm run build` in /client/ dir, `npm start` in /api/ dir
+- **Visit** http://localhost:3080 (default port) & enjoy
 
-# Add the master key - you can change this after setup
-echo 'LITELLM_MASTER_KEY="sk-1234"' > .env
+By default, only local machine can access this server. To share within network or serve as a public server, set `HOST` to `0.0.0.0` in `.env` file
 
-# Add the litellm salt key - you cannot change this after adding a model
-# It is used to encrypt / decrypt your LLM API Key credentials
-# We recommend - https://1password.com/password-generator/ 
-# password generator to get a random hash for litellm salt key
-echo 'LITELLM_SALT_KEY="sk-1234"' > .env
+### Docker
 
-source .env
+- **Provide** all credentials, (API keys, access tokens, and Mongo Connection String) in [docker-compose.yml](docker-compose.yml) under api service
+- **Run** `docker-compose up` to start the app
 
-# Start
-docker-compose up
+### Access Tokens
+
+<details>
+<summary><strong>ChatGPT Free Instructions</strong></summary>
+
+To get your Access token For ChatGPT 'Free Version', login to chat.openai.com, then visit https://chat.openai.com/api/auth/session.
+
+
+**Warning:** There may be a high chance of your account being banned with this method. Continue doing so at your own risk.
+
+</details>
+
+<details>
+<summary><strong>BingAI Instructions</strong></summary>
+The Bing Access Token is the "_U" cookie from bing.com. Use dev tools or an extension while logged into the site to view it.
+
+**Note:** Specific error handling and styling for this model is still in progress.
+</details>
+
+### Proxy
+
+If your server cannot connect to the chatGPT API server by some reason, (eg in China). You can set a environment variable `PROXY`. This will be transmitted to `node-chatgpt-api` interface.
+
+**Warning:** `PROXY` is not `reverseProxyUrl` in `node-chatgpt-api`
+
+<details>
+<summary><strong>Set up proxy in local environment </strong></summary>
+
+Here is two ways to set proxy.
+- Option 1: system level environment
+`export PROXY="http://127.0.0.1:7890"`
+- Option 2: set in .env file
+`PROXY="http://127.0.0.1:7890"`
+
+**Change `http://127.0.0.1:7890` to your proxy server**
+</details>
+
+<details>
+<summary><strong>Set up proxy in docker environment </strong></summary>
+
+set in docker-compose.yml file, under services - api - environment
+
+```
+    api:
+        ...
+        environment:
+                ...
+                - "PROXY=http://127.0.0.1:7890"
+                # add this line ↑
 ```
 
+**Change `http://127.0.0.1:7890` to your proxy server**
 
-UI on `/ui` on your proxy server
-![ui_3](https://github.com/BerriAI/litellm/assets/29436595/47c97d5e-b9be-4839-b28c-43d7f4f10033)
+</details>
 
-Set budgets and rate limits across multiple projects
-`POST /key/generate`
+### User System
 
-### Request
+By default, there is no user system enabled, so anyone can access your server.
 
-```shell
-curl 'http://0.0.0.0:4000/key/generate' \
---header 'Authorization: Bearer sk-1234' \
---header 'Content-Type: application/json' \
---data-raw '{"models": ["gpt-3.5-turbo", "gpt-4", "claude-2"], "duration": "20m","metadata": {"user": "ishaan@berri.ai", "team": "core-infra"}}'
-```
+**This project is not designed to provide a complete and full-featured user system.** It's not high priority task and might never be provided.
 
-### Expected Response
+[wtlyu](https://github.com/wtlyu) provide a sample user system structure, that you can implement your own user system. It's simple and not a ready-for-use edition. 
 
-```shell
-{
-    "key": "sk-kdEXbIqZRwEeEiHwdg7sFA", # Bearer token
-    "expires": "2023-11-19T01:38:25.838000+00:00" # datetime object
-}
-```
+(If you want to implement your user system, open this ↓)
 
-## Supported Providers ([Docs](https://docs.litellm.ai/docs/providers))
+<details>
+<summary><strong>Implement your own user system </strong></summary>
 
-| Provider                                                                            | [Completion](https://docs.litellm.ai/docs/#basic-usage) | [Streaming](https://docs.litellm.ai/docs/completion/stream#streaming-responses) | [Async Completion](https://docs.litellm.ai/docs/completion/stream#async-completion) | [Async Streaming](https://docs.litellm.ai/docs/completion/stream#async-streaming) | [Async Embedding](https://docs.litellm.ai/docs/embedding/supported_embedding) | [Async Image Generation](https://docs.litellm.ai/docs/image_generation) |
-|-------------------------------------------------------------------------------------|---------------------------------------------------------|---------------------------------------------------------------------------------|-------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------|-------------------------------------------------------------------------|
-| [openai](https://docs.litellm.ai/docs/providers/openai)                             | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             | ✅                                                                       |
-| [azure](https://docs.litellm.ai/docs/providers/azure)                               | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             | ✅                                                                       |
-| [AI/ML API](https://docs.litellm.ai/docs/providers/aiml)                               | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             | ✅                                                                       |
-| [aws - sagemaker](https://docs.litellm.ai/docs/providers/aws_sagemaker)             | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [aws - bedrock](https://docs.litellm.ai/docs/providers/bedrock)                     | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [google - vertex_ai](https://docs.litellm.ai/docs/providers/vertex)                 | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             | ✅                                                                       |
-| [google - palm](https://docs.litellm.ai/docs/providers/palm)                        | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [google AI Studio - gemini](https://docs.litellm.ai/docs/providers/gemini)          | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [mistral ai api](https://docs.litellm.ai/docs/providers/mistral)                    | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [cloudflare AI Workers](https://docs.litellm.ai/docs/providers/cloudflare_workers)  | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [cohere](https://docs.litellm.ai/docs/providers/cohere)                             | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [anthropic](https://docs.litellm.ai/docs/providers/anthropic)                       | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [empower](https://docs.litellm.ai/docs/providers/empower)                    | ✅                                                      | ✅                                                                              | ✅                                                                                  | ✅                                                                                |
-| [huggingface](https://docs.litellm.ai/docs/providers/huggingface)                   | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [replicate](https://docs.litellm.ai/docs/providers/replicate)                       | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [together_ai](https://docs.litellm.ai/docs/providers/togetherai)                    | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [openrouter](https://docs.litellm.ai/docs/providers/openrouter)                     | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [ai21](https://docs.litellm.ai/docs/providers/ai21)                                 | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [baseten](https://docs.litellm.ai/docs/providers/baseten)                           | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [vllm](https://docs.litellm.ai/docs/providers/vllm)                                 | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [nlp_cloud](https://docs.litellm.ai/docs/providers/nlp_cloud)                       | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [aleph alpha](https://docs.litellm.ai/docs/providers/aleph_alpha)                   | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [petals](https://docs.litellm.ai/docs/providers/petals)                             | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [ollama](https://docs.litellm.ai/docs/providers/ollama)                             | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [deepinfra](https://docs.litellm.ai/docs/providers/deepinfra)                       | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [perplexity-ai](https://docs.litellm.ai/docs/providers/perplexity)                  | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [Groq AI](https://docs.litellm.ai/docs/providers/groq)                              | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [Deepseek](https://docs.litellm.ai/docs/providers/deepseek)                         | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [anyscale](https://docs.litellm.ai/docs/providers/anyscale)                         | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [IBM - watsonx.ai](https://docs.litellm.ai/docs/providers/watsonx)                  | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 | ✅                                                                             |                                                                         |
-| [voyage ai](https://docs.litellm.ai/docs/providers/voyage)                          |                                                         |                                                                                 |                                                                                     |                                                                                   | ✅                                                                             |                                                                         |
-| [xinference [Xorbits Inference]](https://docs.litellm.ai/docs/providers/xinference) |                                                         |                                                                                 |                                                                                     |                                                                                   | ✅                                                                             |                                                                         |
-| [FriendliAI](https://docs.litellm.ai/docs/providers/friendliai)                              | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
-| [Galadriel](https://docs.litellm.ai/docs/providers/galadriel)                              | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
+To enable the user system, set `ENABLE_USER_SYSTEM=1` in your `.env` file.
 
-[**Read the Docs**](https://docs.litellm.ai/docs/)
+The sample structure is simple. It provide three basic endpoint:
+
+1. `/auth/login` will redirect to your own login url. In the sample code, it's `/auth/your_login_page`.
+2. `/auth/logout` will redirect to your own logout url. In the sample code, it's `/auth/your_login_page/logout`.
+3. `/api/me` will return the userinfo: `{ username, display }`.
+   1. `username` will be used in db, used to distinguish between users.
+   2. `display` will be displayed in UI.
+
+The only one thing that drive user system work is `req.session.user`. Once it's set, the client will be trusted. Set to `null` if logout.
+
+Please refer to `/api/server/routes/authYoutLogin.js` file. It's very clear and simple to tell you how to implement your user system.
+
+</details>
+
+
+### Updating
+- As the project is still a work-in-progress, you should pull the latest and run the steps over. Reset your browser cache/clear site data.
+
+## Use Cases ##
+
+  - One stop shop for all conversational AIs, with the added bonus of searching past conversations.
+  - Using the official API, you'd have to generate 7.5 million words to expense the same cost as ChatGPT Plus ($20).
+  - ChatGPT/Google Bard/Bing AI conversations are lost in space or
+  cannot be searched past a certain timeframe.
+  - **Customize ChatGPT**
+
+    ![use case example](./images/use_case3.png "Make a Custom GPT")
+
+  - **API is not as limited as ChatGPT Free (at [chat.openai.com](https://chat.openai.com/chat))**
+
+    ![use case example](./images/use_case2.png "chat.openai.com is getting more limited by the day!")
+
+  - **ChatGPT Free is down.**
+
+    ![use case example](./images/use_case.png "GPT is down! Plus is too expensive!")
+
+
+## Origin ##
+  This project was originally created as a Minimum Viable Product (or MVP) for the [@HackReactor](https://github.com/hackreactor/) Bootcamp. It was built with OpenAI response streaming and most of the UI completed in under 20 hours. During the end of that time, I had most of the UI and basic functionality done. This was created without using any boilerplates or templates, including create-react-app and other toolchains. I didn't follow any 'un-official chatgpt' video tutorials, and simply referenced the official site for the UI. The purpose of the exercise was to learn setting up a full stack project from scratch. Please feel free to give feedback, suggestions, or fork the project for your own use.
+
+
+## Caveats
+### Regarding use of Official ChatGPT API
+From [@waylaidwanderer](https://github.com/waylaidwanderer/node-chatgpt-api/blob/main/README.md#caveats):
+
+Since `gpt-3.5-turbo` is ChatGPT's underlying model, I had to do my best to replicate the way the official ChatGPT website uses it.
+This means my implementation or the underlying model may not behave exactly the same in some ways:
+- Conversations are not tied to any user IDs, so if that's important to you, you should implement your own user ID system.
+- ChatGPT's model parameters (temperature, frequency penalty, etc.) are unknown, so I set some defaults that I thought would be reasonable.
+- Conversations are limited to roughly the last 3000 tokens, so earlier messages may be forgotten during longer conversations.
+  - This works in a similar way to ChatGPT, except I'm pretty sure they have some additional way of retrieving context from earlier messages when needed (which can probably be achieved with embeddings, but I consider that out-of-scope for now).
 
 ## Contributing
+If you'd like to contribute, please create a pull request with a detailed description of your changes.
 
-Interested in contributing? Contributions to LiteLLM Python SDK, Proxy Server, and contributing LLM integrations are both accepted and highly encouraged! [See our Contribution Guide for more details](https://docs.litellm.ai/docs/extras/contributing_code)
-
-# Enterprise
-For companies that need better security, user management and professional support
-
-[Talk to founders](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)
-
-This covers: 
-- ✅ **Features under the [LiteLLM Commercial License](https://docs.litellm.ai/docs/proxy/enterprise):**
-- ✅ **Feature Prioritization**
-- ✅ **Custom Integrations**
-- ✅ **Professional Support - Dedicated discord + slack**
-- ✅ **Custom SLAs**
-- ✅ **Secure access with Single Sign-On**
-
-# Code Quality / Linting
-
-LiteLLM follows the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html).
-
-We run: 
-- Ruff for [formatting and linting checks](https://github.com/BerriAI/litellm/blob/e19bb55e3b4c6a858b6e364302ebbf6633a51de5/.circleci/config.yml#L320)
-- Mypy + Pyright for typing [1](https://github.com/BerriAI/litellm/blob/e19bb55e3b4c6a858b6e364302ebbf6633a51de5/.circleci/config.yml#L90), [2](https://github.com/BerriAI/litellm/blob/e19bb55e3b4c6a858b6e364302ebbf6633a51de5/.pre-commit-config.yaml#L4)
-- Black for [formatting](https://github.com/BerriAI/litellm/blob/e19bb55e3b4c6a858b6e364302ebbf6633a51de5/.circleci/config.yml#L79)
-- isort for [import sorting](https://github.com/BerriAI/litellm/blob/e19bb55e3b4c6a858b6e364302ebbf6633a51de5/.pre-commit-config.yaml#L10)
-
-
-If you have suggestions on how to improve the code quality feel free to open an issue or a PR.
-
-
-# Support / talk with founders
-
-- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
-- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
-- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
-- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
-
-# Why did we build this
-
-- **Need for simplicity**: Our code started to get extremely complicated managing & translating calls between Azure, OpenAI and Cohere.
-
-# Contributors
-
-<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->
-<!-- prettier-ignore-start -->
-<!-- markdownlint-disable -->
-
-<!-- markdownlint-restore -->
-<!-- prettier-ignore-end -->
-
-<!-- ALL-CONTRIBUTORS-LIST:END -->
-
-<a href="https://github.com/BerriAI/litellm/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=BerriAI/litellm" />
-</a>
-
-
-## Run in Developer mode
-### Services
-1. Setup .env file in root
-2. Run dependant services `docker-compose up db prometheus`
-
-### Backend
-1. (In root) create virtual environment `python -m venv .venv`
-2. Activate virtual environment `source .venv/bin/activate`
-3. Install dependencies `pip install -e ".[all]"`
-4. Start proxy backend `uvicorn litellm.proxy.proxy_server:app --host localhost --port 4000 --reload`
-
-### Frontend
-1. Navigate to `ui/litellm-dashboard`
-2. Install dependencies `npm install`
-3. Run `npm run dev` to start the dashboard
+## License
+This project is licensed under the MIT License.

api/.dockerignore

@@ -0,0 +1,2 @@
+/node_modules
+.env

api/.env.example

@@ -0,0 +1,29 @@
+# Server configuration. 
+# The server will listen to localhost:3080 request by default. You can set the target ip as you want.
+# If you want this server can be used outside your local machine, for example to share with other 
+# machine or expose this from a docker container, set HOST=0.0.0.0 or your external ip interface.
+#
+# Tips: HOST=0.0.0.0 means listening on all interface. It's not a real ip. Use localhost:port rather
+# than 0.0.0.0:port to open it.
+HOST=localhost 
+PORT=3080
+NODE_ENV=development
+
+# Change this to proxy any API request. It's useful if your machine have difficulty calling the original API server.
+# PROXY="http://YOUR_PROXY_SERVER"
+
+# Change this to your MongoDB URI if different and I recommend appending chatgpt-clone
+MONGO_URI="mongodb://127.0.0.1:27017/chatgpt-clone"
+
+# API key configuration.
+# Leave blank if you don't want them.
+OPENAI_KEY=
+CHATGPT_TOKEN=
+BING_TOKEN=
+
+# User System
+
+# global enable/disable the sample user system.
+# this is not a ready to use user system.
+# dont't use it, unless you can write your own code.
+ENABLE_USER_SYSTEM=

api/Dockerfile

@@ -0,0 +1,16 @@
+FROM node:19-alpine
+WORKDIR /api
+# copy package.json into the container at /api
+COPY package*.json /api/
+# install dependencies
+RUN npm install
+# Copy the current directory contents into the container at /api
+COPY . /api/
+# Make port 3080 available to the world outside this container
+EXPOSE 3080
+# Expose the server to 0.0.0.0
+ENV HOST=0.0.0.0
+# Run the app when the container launches
+CMD ["npm", "start"]
+
+# docker build -t node-api .

api/app/bingai.js

@@ -0,0 +1,55 @@
+require('dotenv').config();
+const { KeyvFile } = require('keyv-file');
+
+const askBing = async ({ text, onProgress, convo }) => {
+  const { BingAIClient } = (await import('@waylaidwanderer/chatgpt-api'));
+
+  const bingAIClient = new BingAIClient({
+    // "_U" cookie from bing.com
+    userToken: process.env.BING_TOKEN,
+    // If the above doesn't work, provide all your cookies as a string instead
+    // cookies: '',
+    debug: false,
+    cache: { store: new KeyvFile({ filename: './data/cache.json' }) },
+    proxy: process.env.PROXY || null,
+  });
+
+  let options = { onProgress };
+  if (convo) {
+    options = { ...options, ...convo };
+  }
+
+  if (options?.jailbreakConversationId == 'false')
+    options.jailbreakConversationId = false
+
+  const res = await bingAIClient.sendMessage(text, options);
+
+  return res;
+
+  // Example response for reference
+  // {
+  //   conversationSignature: 'wwZ2GC/qRgEqP3VSNIhbPGwtno5RcuBhzZFASOM+Sxg=',
+  //   conversationId: '51D|BingProd|026D3A4017554DE6C446798144B6337F4D47D5B76E62A31F31D0B1D0A95ED868',
+  //   clientId: '914800201536527',
+  //   invocationId: 1,
+  //   conversationExpiryTime: '2023-02-15T21:48:46.2892088Z',
+  //   response: 'Hello, this is Bing. Nice to meet you. 😊',
+  //   details: {
+  //     text: 'Hello, this is Bing. Nice to meet you. 😊',
+  //     author: 'bot',
+  //     createdAt: '2023-02-15T15:48:43.0631898+00:00',
+  //     timestamp: '2023-02-15T15:48:43.0631898+00:00',
+  //     messageId: '9d0c9a80-91b1-49ab-b9b1-b457dc3fe247',
+  //     requestId: '5b252ef8-4f09-4c08-b6f5-4499d2e12fba',
+  //     offense: 'None',
+  //     adaptiveCards: [ [Object] ],
+  //     sourceAttributions: [],
+  //     feedback: { tag: null, updatedOn: null, type: 'None' },
+  //     contentOrigin: 'DeepLeo',
+  //     privacy: null,
+  //     suggestedResponses: [ [Object], [Object], [Object] ]
+  //   }
+  // }
+};
+
+module.exports = { askBing };

api/app/chatgpt-browser.js

@@ -0,0 +1,31 @@
+require('dotenv').config();
+const { KeyvFile } = require('keyv-file');
+
+const clientOptions = {
+  // Warning: This will expose your access token to a third party. Consider the risks before using this.
+  reverseProxyUrl: 'https://bypass.duti.tech/api/conversation',
+  // Access token from https://chat.openai.com/api/auth/session
+  accessToken: process.env.CHATGPT_TOKEN,
+  // debug: true
+  proxy: process.env.PROXY || null,
+};
+
+const browserClient = async ({ text, onProgress, convo, abortController }) => {
+  const { ChatGPTBrowserClient } = await import('@waylaidwanderer/chatgpt-api');
+
+  const store = {
+    store: new KeyvFile({ filename: './data/cache.json' })
+  };
+
+  const client = new ChatGPTBrowserClient(clientOptions, store);
+  let options = { onProgress, abortController };
+
+  if (!!convo.parentMessageId && !!convo.conversationId) {
+    options = { ...options, ...convo };
+  }
+
+  const res = await client.sendMessage(text, options);
+  return res;
+};
+
+module.exports = { browserClient };

api/app/chatgpt-client.js

@@ -0,0 +1,29 @@
+require('dotenv').config();
+const { KeyvFile } = require('keyv-file');
+
+const clientOptions = {
+  modelOptions: {
+    model: 'gpt-3.5-turbo'
+  },
+  proxy: process.env.PROXY || null,
+  debug: false
+};
+
+const askClient = async ({ text, onProgress, convo, abortController }) => {
+  const ChatGPTClient = (await import('@waylaidwanderer/chatgpt-api')).default;
+  const store = {
+    store: new KeyvFile({ filename: './data/cache.json' })
+  };
+
+  const client = new ChatGPTClient(process.env.OPENAI_KEY, clientOptions, store);
+  let options = { onProgress, abortController };
+
+  if (!!convo.parentMessageId && !!convo.conversationId) {
+    options = { ...options, ...convo };
+  }
+
+  const res = await client.sendMessage(text, options);
+  return res;
+};
+
+module.exports = { askClient };

api/app/chatgpt-custom.js

@@ -0,0 +1,35 @@
+require('dotenv').config();
+const { KeyvFile } = require('keyv-file');
+
+const clientOptions = {
+  modelOptions: {
+    model: 'gpt-3.5-turbo'
+  },
+  proxy: process.env.PROXY || null,
+  debug: false
+};
+
+const customClient = async ({ text, onProgress, convo, promptPrefix, chatGptLabel, abortController }) => {
+  const ChatGPTClient = (await import('@waylaidwanderer/chatgpt-api')).default;
+  const store = {
+    store: new KeyvFile({ filename: './data/cache.json' })
+  };
+
+  clientOptions.chatGptLabel = chatGptLabel;
+
+  if (promptPrefix?.length > 0) {
+    clientOptions.promptPrefix = promptPrefix;
+  }
+
+  const client = new ChatGPTClient(process.env.OPENAI_KEY, clientOptions, store);
+
+  let options = { onProgress, abortController };
+  if (!!convo.parentMessageId && !!convo.conversationId) {
+    options = { ...options, ...convo };
+  }
+
+  const res = await client.sendMessage(text, options);
+  return res;
+};
+
+module.exports = customClient;

api/app/citeText.js

@@ -0,0 +1,29 @@
+const citationRegex = /\[\^\d+?\^]/g;
+
+const citeText = (res, noLinks = false) => {
+  let result = res.text || res;
+  const citations = Array.from(new Set(result.match(citationRegex)));
+  if (citations?.length === 0) return result;
+
+  if (noLinks) {
+    citations.forEach((citation) => {
+      const digit = citation.match(/\d+?/g)[0];
+      result = result.replaceAll(citation, `<sup>[${digit}](#)  </sup>`);
+    });
+
+    return result;
+  }
+
+  let sources = res.details.sourceAttributions;
+  if (sources?.length === 0) return result;
+  sources = sources.map((source) => source.seeMoreUrl);
+
+  citations.forEach((citation) => {
+    const digit = citation.match(/\d+?/g)[0];
+    result = result.replaceAll(citation, `<sup>[${digit}](${sources[digit - 1]})  </sup>`);
+  });
+
+  return result;
+};
+
+module.exports = citeText;

api/app/detectCode.js

@@ -0,0 +1,52 @@
+const { ModelOperations } = require('@vscode/vscode-languagedetection');
+const languages = require('../utils/languages.js');
+const codeRegex = /(```[\s\S]*?```)/g;
+// const languageMatch = /```(\w+)/;
+const replaceRegex = /```\w+\n/g;
+
+const detectCode = async (input) => {
+  try {
+    let text = input;
+    if (!text.match(codeRegex)) {
+      return text;
+    }
+
+    const langMatches = text.match(replaceRegex);
+
+    if (langMatches?.length > 0) {
+      langMatches.forEach(match => {
+        let lang = match.split('```')[1].trim();
+
+        if (languages.has(lang)) {
+          return;
+        }
+
+        console.log('[detectCode.js] replacing', match, 'with', '```shell');
+        text = text.replace(match, '```shell\n');
+      });
+
+      return text;
+    }
+
+    const modelOperations = new ModelOperations();
+    const regexSplit = (await import('./regexSplit.mjs')).default;
+    const parts = regexSplit(text, codeRegex);
+
+    const output = parts.map(async (part) => {
+      if (part.match(codeRegex)) {
+        const code = part.slice(3, -3);
+        let lang = (await modelOperations.runModel(code))[0].languageId;
+        return part.replace(/^```/, `\`\`\`${languages.has(lang) ? lang : 'shell'}`);
+      } else {
+        return part;
+      }
+    });
+
+    return (await Promise.all(output)).join('');
+  } catch (e) {
+    console.log('Error in detectCode function\n', e);
+    return input;
+  }
+};
+
+module.exports = detectCode;

api/app/getCitations.js

@@ -0,0 +1,13 @@
+// const regex = / \[\d+\..*?\]\(.*?\)/g;
+const regex = / \[.*?]\(.*?\)/g;
+
+const getCitations = (res) => {
+  const textBlocks = res.details.adaptiveCards[0].body;
+  if (!textBlocks) return '';
+  let links = textBlocks[textBlocks.length - 1]?.text.match(regex);
+  if (links?.length === 0 || !links) return '';
+  links = links.map((link) => link.trim());
+  return links.join('\n');
+};
+
+module.exports = getCitations;

api/app/index.js

@@ -0,0 +1,21 @@
+const { askClient } = require('./chatgpt-client');
+const { browserClient } = require('./chatgpt-browser');
+const customClient = require('./chatgpt-custom');
+const { askBing } = require('./bingai');
+const { askSydney } = require('./sydney');
+const titleConvo = require('./titleConvo');
+const getCitations = require('./getCitations');
+const citeText = require('./citeText');
+const detectCode = require('./detectCode');
+
+module.exports = {
+  askClient,
+  browserClient,
+  customClient,
+  askBing,
+  askSydney,
+  titleConvo,
+  getCitations,
+  citeText,
+  detectCode
+};

api/app/regexSplit.mjs

@@ -0,0 +1,46 @@
+const primaryRegex = /```([^`\n]*?)\n([\s\S]*?)\n```/g;
+const secondaryRegex = /```([^`\n]*?)\n?([\s\S]*?)\n?```/g;
+
+const unenclosedCodeTest = (text) => {
+  let workingText = text;
+  // if (workingText.startsWith('<') || (!workingText.startsWith('`') && workingText.match(/```/g)?.length === 1)) {
+  //   workingText = `\`\`\`${workingText}`
+  // }
+
+  return workingText.trim();
+};
+
+export default function regexSplit(string) {
+  let matches = [...string.matchAll(primaryRegex)];
+
+  if (!matches[0]) {
+    matches = [...string.matchAll(secondaryRegex)];
+  }
+
+  const output = [matches[0].input.slice(0, matches[0].index)];
+
+  // console.log(matches);
+
+  for (let i = 0; i < matches.length; i++) {
+    const [fullMatch, language, code] = matches[i];
+    // const formattedCode = code.replace(/`+/g, '\\`');
+    output.push(`\`\`\`${language}\n${code}\n\`\`\``);
+    if (i < matches.length - 1) {
+      let nextText = string.slice(matches[i].index + fullMatch.length, matches[i + 1].index);
+      nextText = unenclosedCodeTest(nextText);
+      output.push(nextText);
+    } else {
+      const lastMatch = matches[matches.length - 1][0];
+      // console.log(lastMatch);
+      // console.log(matches[0].input.split(lastMatch));
+      let rest = matches[0].input.split(lastMatch)[1]
+
+      if (rest) {
+        rest = unenclosedCodeTest(rest);
+        output.push(rest);
+      }
+    }
+  }
+
+  return output;
+}

api/app/sydney.js

@@ -0,0 +1,36 @@
+require('dotenv').config();
+const { KeyvFile } = require('keyv-file');
+
+const askSydney = async ({ text, onProgress, convo }) => {
+  const { BingAIClient } = (await import('@waylaidwanderer/chatgpt-api'));
+
+  const sydneyClient = new BingAIClient({
+    // "_U" cookie from bing.com
+    userToken: process.env.BING_TOKEN,
+    // If the above doesn't work, provide all your cookies as a string instead
+    // cookies: '',
+    debug: false,
+    cache: { store: new KeyvFile({ filename: './data/cache.json' }) }
+  });
+
+  let options = {
+    jailbreakConversationId: true,
+    onProgress,
+  };
+
+  if (convo.jailbreakConversationId) {
+    options = { ...options, jailbreakConversationId: convo.jailbreakConversationId, parentMessageId: convo.parentMessageId };
+  }
+
+  console.log('sydney options', options);
+
+  const res = await sydneyClient.sendMessage(text, options
+  );
+
+  return res;
+
+  // for reference:
+  // https://github.com/waylaidwanderer/node-chatgpt-api/blob/main/demos/use-bing-client.js
+};
+
+module.exports = { askSydney };

api/app/titleConvo.js

@@ -0,0 +1,62 @@
+const { Configuration, OpenAIApi } = require('openai');
+const _ = require('lodash');
+
+const proxyEnvToAxiosProxy = (proxyString) => {
+  if (!proxyString) return null;
+
+  const regex = /^([^:]+):\/\/(?:([^:@]*):?([^:@]*)@)?([^:]+)(?::(\d+))?/;
+  const [, protocol, username, password, host, port] = proxyString.match(regex);
+  const proxyConfig = {
+    protocol,
+    host,
+    port: port ? parseInt(port) : undefined,
+    auth: username && password ? { username, password } : undefined
+  };
+
+  return proxyConfig;
+};
+
+const titleConvo = async ({ model, text, response }) => {
+  let title = 'New Chat';
+  try {
+    const configuration = new Configuration({
+      apiKey: process.env.OPENAI_KEY
+    });
+    const openai = new OpenAIApi(configuration);
+    const completion = await openai.createChatCompletion(
+      {
+        model: 'gpt-3.5-turbo',
+        messages: [
+          {
+            role: 'system',
+            content:
+              'You are a title-generator with one job: giving a conversation, detect the language and titling the conversation provided by a user in title case, using the same language.'
+          },
+          {
+            role: 'user',
+            content: `In 5 words or less, summarize the conversation below with a title in title case using the language the user writes in. Don't refer to the participants of the conversation nor the language. Do not include punctuation or quotation marks. Your response should be in title case, exclusively containing the title. Conversation:\n\nUser: "${text}"\n\n${model}: "${JSON.stringify(
+              response?.text
+            )}"\n\nTitle: `
+          }
+        ],
+        temperature: 0,
+        presence_penalty: 0,
+        frequency_penalty: 0,
+      },
+      { proxy: proxyEnvToAxiosProxy(process.env.PROXY || null) }
+    );
+
+    //eslint-disable-next-line
+    title = completion.data.choices[0].message.content.replace(/["\.]/g, '');
+  } catch (e) {
+    console.error(e);
+    console.log('There was an issue generating title, see error above');
+  }
+
+  console.log('CONVERSATION TITLE', title);
+  return title;
+};
+
+const throttledTitleConvo = _.throttle(titleConvo, 1000);
+
+module.exports = throttledTitleConvo;

api/models/Conversation.js

@@ -0,0 +1,194 @@
+const mongoose = require('mongoose');
+const crypto = require('crypto');
+const { getMessages, deleteMessages } = require('./Message');
+
+const convoSchema = mongoose.Schema(
+  {
+    conversationId: {
+      type: String,
+      unique: true,
+      required: true
+    },
+    parentMessageId: {
+      type: String,
+      required: true
+    },
+    title: {
+      type: String,
+      default: 'New Chat'
+    },
+    jailbreakConversationId: {
+      type: String,
+      default: null
+    },
+    conversationSignature: {
+      type: String,
+      default: null
+    },
+    clientId: {
+      type: String
+    },
+    invocationId: {
+      type: String
+    },
+    chatGptLabel: {
+      type: String,
+      default: null
+    },
+    promptPrefix: {
+      type: String,
+      default: null
+    },
+    model: {
+      type: String,
+      required: true
+    },
+    user: {
+      type: String
+    },
+    suggestions: [{ type: String }],
+    messages: [{ type: mongoose.Schema.Types.ObjectId, ref: 'Message' }]
+  },
+  { timestamps: true }
+);
+
+const Conversation =
+  mongoose.models.Conversation || mongoose.model('Conversation', convoSchema);
+
+const getConvo = async (user, conversationId) => {
+  try {
+    return await Conversation.findOne({ user, conversationId }).exec();
+  } catch (error) {
+    console.log(error);
+    return { message: 'Error getting single conversation' };
+  }
+};
+
+module.exports = {
+  saveConvo: async (user, { conversationId, newConversationId, title, ...convo }) => {
+    try {
+      const messages = await getMessages({ conversationId });
+      const update = { ...convo, messages };
+      if (title) {
+        update.title = title;
+        update.user = user
+      }
+      if (newConversationId) {
+        update.conversationId = newConversationId;
+      }
+      if (!update.jailbreakConversationId) {
+        update.jailbreakConversationId = null;
+      }
+      if (update.model !== 'chatgptCustom' && update.chatGptLabel && update.promptPrefix) {
+        console.log('Validation error: resetting chatgptCustom fields', update);
+        update.chatGptLabel = null;
+        update.promptPrefix = null;
+      }
+
+      return await Conversation.findOneAndUpdate(
+        { conversationId: conversationId, user },
+        { $set: update },
+        { new: true, upsert: true }
+      ).exec();
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error saving conversation' };
+    }
+  },
+  updateConvo: async (user, { conversationId, ...update }) => {
+    try {
+      return await Conversation.findOneAndUpdate({ conversationId: conversationId, user }, update, {
+        new: true
+      }).exec();
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error updating conversation' };
+    }
+  },
+  getConvosByPage: async (user, pageNumber = 1, pageSize = 12) => {
+    try {
+      const totalConvos = (await Conversation.countDocuments({ user })) || 1;
+      const totalPages = Math.ceil(totalConvos / pageSize);
+      const convos = await Conversation.find({ user })
+        .sort({ createdAt: -1, created: -1 })
+        .skip((pageNumber - 1) * pageSize)
+        .limit(pageSize)
+        .exec();
+
+      return { conversations: convos, pages: totalPages, pageNumber, pageSize };
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error getting conversations' };
+    }
+  },
+  getConvo,
+  getConvoTitle: async (user, conversationId) => {
+    try {
+      const convo = await getConvo(user, conversationId);
+      return convo.title;
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error getting conversation title' };
+    }
+  },
+  deleteConvos: async (user, filter) => {
+    let deleteCount = await Conversation.deleteMany({...filter, user}).exec();
+    deleteCount.messages = await deleteMessages(filter);
+    return deleteCount;
+  },
+  migrateDb: async () => {
+    try {
+      const conversations = await Conversation.find({ model: null }).exec();
+
+      if (!conversations || conversations.length === 0)
+        return { message: '[Migrate] No conversations to migrate' };
+
+      for (let convo of conversations) {
+        const messages = await getMessages({
+          conversationId: convo.conversationId,
+          messageId: { $exists: false }
+        });
+
+        let model;
+        let oldId;
+        const promises = [];
+        messages.forEach((message, i) => {
+          const msgObj = message.toObject();
+          const newId = msgObj.id;
+          if (i === 0) {
+            message.parentMessageId = '00000000-0000-0000-0000-000000000000';
+          } else {
+            message.parentMessageId = oldId;
+          }
+
+          oldId = newId;
+          message.messageId = newId;
+          if (message.sender.toLowerCase() !== 'user' && !model) {
+            model = message.sender.toLowerCase();
+          }
+
+          if (message.sender.toLowerCase() === 'user') {
+            message.isCreatedByUser = true;
+          }
+          promises.push(message.save());
+        });
+        await Promise.all(promises);
+
+        await Conversation.findOneAndUpdate(
+          { conversationId: convo.conversationId },
+          { model },
+          { new: true }
+        ).exec();
+      }
+
+      try {
+        await mongoose.connection.db.collection('messages').dropIndex('id_1');
+      } catch (error) {
+        console.log("[Migrate] Index doesn't exist or already dropped");
+      }
+    } catch (error) {
+      console.log(error);
+      return { message: '[Migrate] Error migrating conversations' };
+    }
+  }
+};

api/models/CustomGpt.js

@@ -0,0 +1,82 @@
+const mongoose = require('mongoose');
+
+const customGptSchema = mongoose.Schema({
+  chatGptLabel: {
+    type: String,
+    required: true
+  },
+  promptPrefix: {
+    type: String
+  },
+  value: {
+    type: String,
+    required: true
+  },
+  user: {
+    type: String
+  },
+}, { timestamps: true });
+
+const CustomGpt = mongoose.models.CustomGpt || mongoose.model('CustomGpt', customGptSchema);
+
+const createCustomGpt = async ({ chatGptLabel, promptPrefix, value, user }) => {
+  try {
+    await CustomGpt.create({
+      chatGptLabel,
+      promptPrefix,
+      value,
+      user
+    });
+    return { chatGptLabel, promptPrefix, value };
+  } catch (error) {
+    console.error(error);
+    return { customGpt: 'Error saving customGpt' };
+  }
+};
+
+module.exports = {
+  getCustomGpts: async (user, filter) => {
+    try {
+      return await CustomGpt.find({ ...filter, user }).exec();
+    } catch (error) {
+      console.error(error);
+      return { customGpt: 'Error getting customGpts' };
+    }
+  },
+  updateCustomGpt: async (user, { value, ...update }) => {
+    try {
+      const customGpt = await CustomGpt.findOne({ value, user }).exec();
+
+      if (!customGpt) {
+        return await createCustomGpt({ value, ...update, user });
+      } else {
+        return await CustomGpt.findOneAndUpdate({ value, user }, update, {
+          new: true,
+          upsert: true
+        }).exec();
+      }
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error updating customGpt' };
+    }
+  },
+  updateByLabel: async (user, { prevLabel, ...update }) => {
+    try {
+      return await CustomGpt.findOneAndUpdate({ chatGptLabel: prevLabel, user }, update, {
+        new: true,
+        upsert: true
+      }).exec();
+    } catch (error) {
+      console.log(error);
+      return { message: 'Error updating customGpt' };
+    }
+  },
+  deleteCustomGpts: async (user, filter) => {
+    try {
+      return await CustomGpt.deleteMany({ ...filter, user }).exec();
+    } catch (error) {
+      console.error(error);
+      return { customGpt: 'Error deleting customGpts' };
+    }
+  }
+};

api/models/Message.js

@@ -0,0 +1,92 @@
+const mongoose = require('mongoose');
+
+const messageSchema = mongoose.Schema({
+  messageId: {
+    type: String,
+    unique: true,
+    required: true
+  },
+  conversationId: {
+    type: String,
+    required: true
+  },
+  conversationSignature: {
+    type: String,
+    // required: true
+  },
+  clientId: {
+    type: String,
+  },
+  invocationId: {
+    type: String,
+  },
+  parentMessageId: {
+    type: String,
+    // required: true
+  },
+  sender: {
+    type: String,
+    required: true
+  },
+  text: {
+    type: String,
+    required: true
+  },
+  isCreatedByUser: {
+    type: Boolean,
+    required: true,
+    default: false
+  },
+  error: {
+    type: Boolean,
+    default: false
+  },
+}, { timestamps: true });
+
+const Message = mongoose.models.Message || mongoose.model('Message', messageSchema);
+
+module.exports = {
+  saveMessage: async ({ messageId, conversationId, parentMessageId, sender, text, isCreatedByUser=false, error }) => {
+    try {
+      await Message.findOneAndUpdate({ messageId }, {
+        conversationId,
+        parentMessageId,
+        sender,
+        text,
+        isCreatedByUser,
+        error
+      }, { upsert: true, new: true });
+      return { messageId, conversationId, parentMessageId, sender, text, isCreatedByUser };
+    } catch (error) {
+      console.error(error);
+      return { message: 'Error saving message' };
+    }
+  },
+  deleteMessagesSince: async ({ messageId, conversationId }) => {
+    try {
+      const message = await Message.findOne({ messageId }).exec()
+
+      if (message) 
+        return await Message.find({ conversationId }).deleteMany({ createdAt: { $gt: message.createdAt } }).exec();
+    } catch (error) {
+      console.error(error);
+      return { message: 'Error deleting messages' };
+    }
+  },
+  getMessages: async (filter) => {
+    try {
+      return await Message.find(filter).sort({createdAt: 1}).exec()
+    } catch (error) {
+      console.error(error);
+      return { message: 'Error getting messages' };
+    }
+  },
+  deleteMessages: async (filter) => {
+    try {
+      return await Message.deleteMany(filter).exec()
+    } catch (error) {
+      console.error(error);
+      return { message: 'Error deleting messages' };
+    }
+  }
+}

api/models/Prompt.js

@@ -0,0 +1,48 @@
+const mongoose = require('mongoose');
+
+const promptSchema = mongoose.Schema({
+  title: {
+    type: String,
+    required: true
+  },
+  prompt: {
+    type: String,
+    required: true
+  },
+  category: {
+    type: String,
+  },
+}, { timestamps: true });
+
+const Prompt = mongoose.models.Prompt || mongoose.model('Prompt', promptSchema);
+
+module.exports = {
+  savePrompt: async ({ title, prompt }) => {
+    try {
+      await Prompt.create({
+        title,
+        prompt
+      });
+      return { title, prompt };
+    } catch (error) {
+      console.error(error);
+      return { prompt: 'Error saving prompt' };
+    }
+  },
+  getPrompts: async (filter) => {
+    try {
+      return await Prompt.find(filter).exec()
+    } catch (error) {
+      console.error(error);
+      return { prompt: 'Error getting prompts' };
+    }
+  },
+  deletePrompts: async (filter) => {
+    try {
+      return await Prompt.deleteMany(filter).exec()
+    } catch (error) {
+      console.error(error);
+      return { prompt: 'Error deleting prompts' };
+    }
+  }
+}

api/models/dbConnect.js

@@ -0,0 +1,44 @@
+require('dotenv').config();
+const mongoose = require('mongoose');
+const MONGO_URI = process.env.MONGO_URI;
+
+if (!MONGO_URI) {
+  throw new Error('Please define the MONGO_URI environment variable inside .env.local');
+}
+
+/**
+ * Global is used here to maintain a cached connection across hot reloads
+ * in development. This prevents connections growing exponentially
+ * during API Route usage.
+ */
+let cached = global.mongoose;
+
+if (!cached) {
+  cached = global.mongoose = { conn: null, promise: null };
+}
+
+async function dbConnect() {
+  if (cached.conn) {
+    return cached.conn;
+  }
+
+  if (!cached.promise) {
+    const opts = {
+      useNewUrlParser: true,
+      useUnifiedTopology: true,
+      bufferCommands: false
+      // bufferMaxEntries: 0,
+      // useFindAndModify: true,
+      // useCreateIndex: true
+    };
+
+    mongoose.set('strictQuery', true);
+    cached.promise = mongoose.connect(MONGO_URI, opts).then((mongoose) => {
+      return mongoose;
+    });
+  }
+  cached.conn = await cached.promise;
+  return cached.conn;
+}
+
+module.exports = dbConnect;

api/models/index.js

@@ -0,0 +1,17 @@
+const { saveMessage, deleteMessagesSince, deleteMessages } = require('./Message');
+const { getCustomGpts, updateCustomGpt, updateByLabel, deleteCustomGpts } = require('./CustomGpt');
+const { getConvoTitle, getConvo, saveConvo, migrateDb } = require('./Conversation');
+
+module.exports = {
+  saveMessage,
+  deleteMessagesSince,
+  deleteMessages,
+  getConvoTitle,
+  getConvo,
+  saveConvo,
+  migrateDb,
+  getCustomGpts,
+  updateCustomGpt,
+  updateByLabel,
+  deleteCustomGpts
+};

api/nodemon.json

@@ -0,0 +1,6 @@
+{
+  "ignore": [
+    "api/data/",
+    "data"
+  ]
+}

api/package.json

@@ -0,0 +1,42 @@
+{
+  "name": "chatgpt-clone",
+  "version": "1.0.0",
+  "description": "",
+  "main": "server/index.js",
+  "scripts": {
+    "start": "node server/index.js",
+    "server-dev": "npx nodemon server/index.js"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/danny-avila/chatgpt-clone.git"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "bugs": {
+    "url": "https://github.com/danny-avila/chatgpt-clone/issues"
+  },
+  "homepage": "https://github.com/danny-avila/chatgpt-clone#readme",
+  "dependencies": {
+    "@keyv/mongo": "^2.1.8",
+    "@vscode/vscode-languagedetection": "^1.0.22",
+    "@waylaidwanderer/chatgpt-api": "^1.28.2",
+    "axios": "^1.3.4",
+    "cors": "^2.8.5",
+    "crypto": "^1.0.1",
+    "dotenv": "^16.0.3",
+    "express": "^4.18.2",
+    "express-session": "^1.17.3",
+    "keyv": "^4.5.2",
+    "keyv-file": "^0.2.0",
+    "lodash": "^4.17.21",
+    "mongoose": "^6.9.0",
+    "openai": "^3.1.0",
+    "sanitize-html": "^2.10.0"
+  },
+  "devDependencies": {
+    "nodemon": "^2.0.20",
+    "path": "^0.12.7"
+  }
+}

api/server/index.js

@@ -0,0 +1,67 @@
+const express = require('express');
+const session = require('express-session')
+const dbConnect = require('../models/dbConnect');
+const { migrateDb } = require('../models');
+const path = require('path');
+const cors = require('cors');
+const routes = require('./routes');
+const app = express();
+const port = process.env.PORT || 3080;
+const host = process.env.HOST || 'localhost'
+const userSystemEnabled = process.env.ENABLE_USER_SYSTEM || false
+const projectPath = path.join(__dirname, '..', '..', 'client');
+dbConnect().then(() => {
+  console.log('Connected to MongoDB');
+  migrateDb();
+});
+
+app.use(cors());
+app.use(express.json());
+app.use(express.static(path.join(projectPath, 'public')));
+app.set('trust proxy', 1) // trust first proxy
+app.use(session({
+  secret: 'chatgpt-clone-random-secrect',
+  resave: false,
+  saveUninitialized: true,
+}))
+
+app.get('/', routes.authenticatedOrRedirect, function (req, res) {
+  console.log(path.join(projectPath, 'public', 'index.html'));
+  res.sendFile(path.join(projectPath, 'public', 'index.html'));
+});
+
+app.get('/api/me', function (req, res) {
+  if (userSystemEnabled) {
+    const user = req?.session?.user
+    
+    if (user) 
+      res.send(JSON.stringify({username: user?.username, display: user?.display}));
+    else
+      res.send(JSON.stringify(null));
+  } else {
+    res.send(JSON.stringify({username: 'anonymous_user', display: 'Anonymous User'})); 
+  }
+});
+
+app.use('/api/ask', routes.authenticatedOr401, routes.ask);
+app.use('/api/messages', routes.authenticatedOr401, routes.messages);
+app.use('/api/convos', routes.authenticatedOr401, routes.convos);
+app.use('/api/customGpts', routes.authenticatedOr401, routes.customGpts);
+app.use('/api/prompts', routes.authenticatedOr401, routes.prompts);
+app.use('/auth', routes.auth);
+
+
+app.get('/api/models', function (req, res) {
+  const hasOpenAI = !!process.env.OPENAI_KEY;
+  const hasChatGpt = !!process.env.CHATGPT_TOKEN;
+  const hasBing = !!process.env.BING_TOKEN;
+
+  res.send(JSON.stringify({ hasOpenAI, hasChatGpt, hasBing }));
+});
+
+app.listen(port, host,  () => {
+  if (host=='0.0.0.0')
+    console.log(`Server listening on all interface at port ${port}. Use http://localhost:${port} to access it`);
+  else
+    console.log(`Server listening at http://${host=='0.0.0.0'?'localhost':host}:${port}`);
+});

api/server/routes/ask.js

@@ -0,0 +1,195 @@
+const express = require('express');
+const crypto = require('crypto');
+const router = express.Router();
+const askBing = require('./askBing');
+const askSydney = require('./askSydney');
+const { titleConvo, askClient, browserClient, customClient } = require('../../app/');
+const { getConvo, saveMessage, getConvoTitle, saveConvo } = require('../../models');
+const { handleError, sendMessage, createOnProgress, handleText } = require('./handlers');
+const { getMessages } = require('../../models/Message');
+
+router.use('/bing', askBing);
+router.use('/sydney', askSydney);
+
+router.post('/', async (req, res) => {
+  let { model, text, overrideParentMessageId=null, parentMessageId, conversationId: oldConversationId, ...convo } = req.body;
+  if (text.length === 0) {
+    return handleError(res, { text: 'Prompt empty or too short' });
+  }
+
+  const conversationId = oldConversationId || crypto.randomUUID();
+
+  const userMessageId = crypto.randomUUID();
+  const userParentMessageId = parentMessageId || '00000000-0000-0000-0000-000000000000';
+  let userMessage = {
+    messageId: userMessageId,
+    sender: 'User',
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    isCreatedByUser: true
+  };
+
+  console.log('ask log', {
+    model,
+    ...userMessage,
+    ...convo
+  });
+
+  if (!overrideParentMessageId) {
+    await saveMessage(userMessage);
+    await saveConvo(req?.session?.user?.username, { ...userMessage, model, ...convo });
+  }
+
+  return await ask({
+    userMessage,
+    model,
+    convo,
+    preSendRequest: true,
+    overrideParentMessageId,
+    req,
+    res
+  });
+});
+
+const ask = async ({
+  userMessage,
+  overrideParentMessageId = null,
+  model,
+  convo,
+  preSendRequest = true,
+  req,
+  res
+}) => {
+  let {
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    messageId: userMessageId
+  } = userMessage;
+
+  let client;
+
+  if (model === 'chatgpt') {
+    client = askClient;
+  } else if (model === 'chatgptCustom') {
+    client = customClient;
+  } else {
+    client = browserClient;
+  }
+
+  res.writeHead(200, {
+    Connection: 'keep-alive',
+    'Content-Type': 'text/event-stream',
+    'Cache-Control': 'no-cache, no-transform',
+    'Access-Control-Allow-Origin': '*',
+    'X-Accel-Buffering': 'no'
+  });
+
+  if (preSendRequest) sendMessage(res, { message: userMessage, created: true });
+
+  try {
+    const progressCallback = createOnProgress();
+
+    const abortController = new AbortController();
+    res.on('close', () => {
+      console.log('The client has disconnected.');
+      // 执行其他操作
+      abortController.abort();
+    })
+
+    let gptResponse = await client({
+      text,
+      onProgress: progressCallback.call(null, model, { res, text }),
+      convo: {
+        parentMessageId: userParentMessageId,
+        conversationId,
+        ...convo
+      },
+      ...convo,
+      abortController
+    });
+
+    console.log('CLIENT RESPONSE', gptResponse);
+
+    if (!gptResponse.parentMessageId) {
+      gptResponse.text = gptResponse.response;
+      // gptResponse.id = gptResponse.messageId;
+      gptResponse.parentMessageId = overrideParentMessageId || userMessageId;
+      // userMessage.conversationId = conversationId
+      //   ? conversationId
+      //   : gptResponse.conversationId;
+      // await saveMessage(userMessage);
+      delete gptResponse.response;
+    }
+
+    if (
+      (gptResponse.text.includes('2023') && !gptResponse.text.trim().includes(' ')) ||
+      gptResponse.text.toLowerCase().includes('no response') ||
+      gptResponse.text.toLowerCase().includes('no answer')
+    ) {
+      await saveMessage({
+        messageId: crypto.randomUUID(),
+        sender: model,
+        conversationId,
+        parentMessageId: overrideParentMessageId || userMessageId,
+        error: true,
+        text: 'Prompt empty or too short'
+      });
+      return handleError(res, { text: 'Prompt empty or too short' });
+    }
+
+    gptResponse.sender = model === 'chatgptCustom' ? convo.chatGptLabel : model;
+    gptResponse.model = model;
+    // gptResponse.final = true;
+    gptResponse.text = await handleText(gptResponse);
+
+    if (convo.chatGptLabel?.length > 0 && model === 'chatgptCustom') {
+      gptResponse.chatGptLabel = convo.chatGptLabel;
+    }
+
+    if (convo.promptPrefix?.length > 0 && model === 'chatgptCustom') {
+      gptResponse.promptPrefix = convo.promptPrefix;
+    }
+
+    // override the parentMessageId, for the regeneration.
+    gptResponse.parentMessageId = overrideParentMessageId || userMessageId;
+
+    await saveMessage(gptResponse);
+    await saveConvo(req?.session?.user?.username, gptResponse);
+    sendMessage(res, {
+      title: await getConvoTitle(req?.session?.user?.username, conversationId),
+      final: true,
+      requestMessage: userMessage,
+      responseMessage: gptResponse
+    });
+    res.end();
+
+    if (userParentMessageId == '00000000-0000-0000-0000-000000000000') {
+      const title = await titleConvo({ model, text, response: gptResponse });
+
+      await saveConvo(
+        req?.session?.user?.username,
+        {
+          conversationId,
+          title
+        }
+      );
+    }
+  } catch (error) {
+    console.log(error);
+    // await deleteMessages({ messageId: userMessageId });
+    const errorMessage = {
+      messageId: crypto.randomUUID(),
+      sender: model,
+      conversationId,
+      parentMessageId: overrideParentMessageId || userMessageId,
+      error: true,
+      text: error.message
+    };
+    await saveMessage(errorMessage);
+    handleError(res, errorMessage);
+  }
+};
+
+module.exports = router;

api/server/routes/askBing.js

@@ -0,0 +1,186 @@
+const express = require('express');
+const crypto = require('crypto');
+const router = express.Router();
+const { titleConvo, askBing } = require('../../app/');
+const { saveMessage, getConvoTitle, saveConvo } = require('../../models');
+const { handleError, sendMessage, createOnProgress, handleText } = require('./handlers');
+
+router.post('/', async (req, res) => {
+  const {
+    model,
+    text,
+    overrideParentMessageId=null,
+    parentMessageId,
+    conversationId: oldConversationId,
+    ...convo
+  } = req.body;
+  if (text.length === 0) {
+    return handleError(res, { text: 'Prompt empty or too short' });
+  }
+
+  const conversationId = oldConversationId || crypto.randomUUID();
+  const isNewConversation = !oldConversationId;
+
+  const userMessageId = crypto.randomUUID();
+  const userParentMessageId = parentMessageId || '00000000-0000-0000-0000-000000000000';
+  let userMessage = {
+    messageId: userMessageId,
+    sender: 'User',
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    isCreatedByUser: true
+  };
+
+  console.log('ask log', {
+    model,
+    ...userMessage,
+    ...convo
+  });
+
+  if (!overrideParentMessageId) {
+    await saveMessage(userMessage);
+    await saveConvo(req?.session?.user?.username, { ...userMessage, model, ...convo });
+  }
+
+  return await ask({
+    isNewConversation,
+    userMessage,
+    model,
+    convo,
+    preSendRequest: true,
+    overrideParentMessageId,
+    req,
+    res
+  });
+});
+
+const ask = async ({
+  isNewConversation,
+  overrideParentMessageId = null,
+  userMessage,
+  model,
+  convo,
+  preSendRequest = true,
+  req,
+  res
+}) => {
+  let {
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    messageId: userMessageId
+  } = userMessage;
+
+  res.writeHead(200, {
+    Connection: 'keep-alive',
+    'Content-Type': 'text/event-stream',
+    'Cache-Control': 'no-cache, no-transform',
+    'Access-Control-Allow-Origin': '*',
+    'X-Accel-Buffering': 'no'
+  });
+
+  if (preSendRequest) sendMessage(res, { message: userMessage, created: true });
+
+  try {
+    const progressCallback = createOnProgress();
+
+    const abortController = new AbortController();
+    res.on('close', () => {
+      console.log('The client has disconnected.');
+      // 执行其他操作
+      abortController.abort();
+    })
+
+    let response = await askBing({
+      text,
+      onProgress: progressCallback.call(null, model, {
+        res,
+        text,
+        parentMessageId: overrideParentMessageId || userMessageId
+      }),
+      convo: {
+        ...convo,
+        parentMessageId: userParentMessageId,
+        conversationId
+      },
+      abortController
+    });
+
+    console.log('BING RESPONSE', response);
+    // console.dir(response, { depth: null });
+
+    userMessage.conversationSignature =
+      convo.conversationSignature || response.conversationSignature;
+    userMessage.conversationId = response.conversationId || conversationId;
+    userMessage.invocationId = response.invocationId;
+    if (!overrideParentMessageId)
+      await saveMessage(userMessage);
+
+    // Bing API will not use our conversationId at the first time,
+    // so change the placeholder conversationId to the real one.
+    // Attition: the api will also create new conversationId while using invalid userMessage.parentMessageId,
+    // but in this situation, don't change the conversationId, but create new convo.
+    if (conversationId != userMessage.conversationId && isNewConversation)
+      await saveConvo(
+        req?.session?.user?.username,
+        {
+          conversationId: conversationId,
+          newConversationId: userMessage.conversationId
+        }
+      );
+    conversationId = userMessage.conversationId;
+
+    response.text = response.response || response.details.spokenText || '**Bing refused to answer.**';
+    // delete response.response;
+    // response.id = response.details.messageId;
+    response.suggestions =
+      response.details.suggestedResponses &&
+      response.details.suggestedResponses.map((s) => s.text);
+    response.sender = model;
+    // response.final = true;
+
+    // override the parentMessageId, for the regeneration.
+    response.parentMessageId =
+      overrideParentMessageId || response.parentMessageId || userMessageId;
+
+    response.text = await handleText(response, true);
+    await saveMessage(response);
+    await saveConvo(req?.session?.user?.username, { ...response, model, chatGptLabel: null, promptPrefix: null, ...convo });
+
+    sendMessage(res, {
+      title: await getConvoTitle(req?.session?.user?.username, conversationId),
+      final: true,
+      requestMessage: userMessage,
+      responseMessage: response
+    });
+    res.end();
+
+    if (userParentMessageId == '00000000-0000-0000-0000-000000000000') {
+      const title = await titleConvo({ model, text, response });
+
+      await saveConvo(
+        req?.session?.user?.username,
+        {
+          conversationId,
+          title
+        }
+      );
+    }
+  } catch (error) {
+    console.log(error);
+    // await deleteMessages({ messageId: userMessageId });
+    const errorMessage = {
+      messageId: crypto.randomUUID(),
+      sender: model,
+      conversationId,
+      parentMessageId: overrideParentMessageId || userMessageId,
+      error: true,
+      text: error.message
+    };
+    await saveMessage(errorMessage);
+    handleError(res, errorMessage);
+  }
+};
+
+module.exports = router;

api/server/routes/askSydney.js

@@ -0,0 +1,199 @@
+const express = require('express');
+const crypto = require('crypto');
+const router = express.Router();
+const { titleConvo, askSydney } = require('../../app/');
+const { saveMessage, saveConvo, getConvoTitle } = require('../../models');
+const { handleError, sendMessage, createOnProgress, handleText } = require('./handlers');
+
+router.post('/', async (req, res) => {
+  const {
+    model,
+    text,
+    overrideParentMessageId=null,
+    parentMessageId,
+    conversationId: oldConversationId,
+    ...convo
+  } = req.body;
+  if (text.length === 0) {
+    return handleError(res, { text: 'Prompt empty or too short' });
+  }
+
+  const conversationId = oldConversationId || crypto.randomUUID();
+  const isNewConversation = !oldConversationId;
+
+  const userMessageId = crypto.randomUUID();
+  const userParentMessageId = parentMessageId || '00000000-0000-0000-0000-000000000000';
+  let userMessage = {
+    messageId: userMessageId,
+    sender: 'User',
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    isCreatedByUser: true
+  };
+
+  console.log('ask log', {
+    model,
+    ...userMessage,
+    ...convo
+  });
+
+  if (!overrideParentMessageId) {
+    await saveMessage(userMessage);
+    await saveConvo(req?.session?.user?.username, { ...userMessage, model, ...convo });
+  }
+
+  return await ask({
+    isNewConversation,
+    userMessage,
+    model,
+    convo,
+    preSendRequest: true,
+    overrideParentMessageId,
+    req,
+    res
+  });
+});
+
+const ask = async ({
+  isNewConversation,
+  overrideParentMessageId = null,
+  userMessage,
+  model,
+  convo,
+  preSendRequest = true,
+  req,
+  res
+}) => {
+  let {
+    text,
+    parentMessageId: userParentMessageId,
+    conversationId,
+    messageId: userMessageId
+  } = userMessage;
+
+  res.writeHead(200, {
+    Connection: 'keep-alive',
+    'Content-Type': 'text/event-stream',
+    'Cache-Control': 'no-cache, no-transform',
+    'Access-Control-Allow-Origin': '*',
+    'X-Accel-Buffering': 'no'
+  });
+
+  if (preSendRequest) sendMessage(res, { message: userMessage, created: true });
+
+  try {
+    const progressCallback = createOnProgress();
+
+    const abortController = new AbortController();
+    res.on('close', () => {
+      console.log('The client has disconnected.');
+      // 执行其他操作
+      abortController.abort();
+    })
+
+    let response = await askSydney({
+      text,
+      onProgress: progressCallback.call(null, model, {
+        res,
+        text,
+        parentMessageId: overrideParentMessageId || userMessageId
+      }),
+      convo: {
+        parentMessageId: userParentMessageId,
+        conversationId,
+        ...convo
+      },
+      abortController
+    });
+
+    console.log('SYDNEY RESPONSE', response);
+    // console.dir(response, { depth: null });
+
+    userMessage.conversationSignature =
+      convo.conversationSignature || response.conversationSignature;
+    userMessage.conversationId = response.conversationId || conversationId;
+    userMessage.invocationId = response.invocationId;
+    // Unlike gpt and bing, Sydney will never accept our given userMessage.messageId, it will generate its own one.
+    if (!overrideParentMessageId)
+      await saveMessage(userMessage);
+
+    // Save sydney response
+    // response.id = response.messageId;
+    response.invocationId = convo.invocationId ? convo.invocationId + 1 : 1;
+    response.conversationId = conversationId ? conversationId : crypto.randomUUID();
+    response.conversationSignature = convo.conversationSignature
+      ? convo.conversationSignature
+      : crypto.randomUUID();
+    response.text = response.response || response.details.spokenText || '**Bing refused to answer.**';
+    // delete response.response;
+    response.suggestions =
+      response.details.suggestedResponses &&
+      response.details.suggestedResponses.map((s) => s.text);
+    response.sender = model;
+    // response.final = true;
+
+    // override the parentMessageId, for the regeneration.
+    response.parentMessageId =
+      overrideParentMessageId || response.parentMessageId || userMessageId;
+
+    // Save user message
+    userMessage.conversationId = response.conversationId || conversationId;
+    if (!overrideParentMessageId)
+      await saveMessage(userMessage);
+
+    // Bing API will not use our conversationId at the first time,
+    // so change the placeholder conversationId to the real one.
+    // Attition: the api will also create new conversationId while using invalid userMessage.parentMessageId,
+    // but in this situation, don't change the conversationId, but create new convo.
+    if (conversationId != userMessage.conversationId && isNewConversation)
+      await saveConvo(
+        req?.session?.user?.username,
+        {
+          conversationId: conversationId,
+          newConversationId: userMessage.conversationId
+        }
+      );
+    conversationId = userMessage.conversationId;
+
+    response.text = await handleText(response, true);
+    // Save sydney response & convo, then send
+    await saveMessage(response);
+    await saveConvo(req?.session?.user?.username, { ...response, model, chatGptLabel: null, promptPrefix: null, ...convo });
+    
+    sendMessage(res, {
+      title: await getConvoTitle(req?.session?.user?.username, conversationId),
+      final: true,
+      requestMessage: userMessage,
+      responseMessage: response
+    });
+    res.end();
+
+    if (userParentMessageId == '00000000-0000-0000-0000-000000000000') {
+      const title = await titleConvo({ model, text, response });
+
+      await saveConvo(
+        req?.session?.user?.username,
+        {
+          conversationId,
+          title
+        }
+      );
+    }
+  } catch (error) {
+    console.log(error);
+    // await deleteMessages({ messageId: userMessageId });
+    const errorMessage = {
+      messageId: crypto.randomUUID(),
+      sender: model,
+      conversationId,
+      parentMessageId: overrideParentMessageId || userMessageId,
+      error: true,
+      text: error.message
+    };
+    await saveMessage(errorMessage);
+    handleError(res, errorMessage);
+  }
+};
+
+module.exports = router;

api/server/routes/auth.js

@@ -0,0 +1,46 @@
+const express = require('express');
+const router = express.Router();
+const authYourLogin = require('./authYourLogin');
+const userSystemEnabled = process.env.ENABLE_USER_SYSTEM || false
+
+router.get('/login', function (req, res) {
+  if (userSystemEnabled)
+    res.redirect('/auth/your_login_page')
+  else
+    res.redirect('/')  
+})
+  
+router.get('/logout', function (req, res) {
+  // clear the session
+  req.session.user = null
+
+  req.session.save(function (error) {
+    if (userSystemEnabled)
+      res.redirect('/auth/your_login_page/logout')
+    else
+      res.redirect('/') 
+  })  
+})
+
+const authenticatedOr401 = (req, res, next) => {
+  if (userSystemEnabled) {
+    const user = req?.session?.user;
+
+    if (user) next();
+    else res.status(401).end();
+  } else next();
+}
+
+const authenticatedOrRedirect = (req, res, next) => {
+  if (userSystemEnabled) {
+    const user = req?.session?.user;
+
+    if (user) next();
+    else res.redirect('/auth/login').end();
+  } else next();
+}
+
+if (userSystemEnabled)
+  router.use('/your_login_page', authYourLogin);
+
+module.exports = { router, authenticatedOr401, authenticatedOrRedirect };

api/server/routes/authYourLogin.js

@@ -0,0 +1,40 @@
+const express = require('express');
+const router = express.Router();
+
+// WARNING!
+// THIS IS NOT A READY TO USE USER SYSTEM
+// PLEASE IMPLEMENT YOUR OWN USER SYSTEM
+
+const userSystemEnabled = process.env.ENABLE_USER_SYSTEM || false
+
+// Logout
+router.get('/logout', (req, res) => {
+  // Do anything you want
+  console.warn('logout not implemented!')
+
+  // finish
+  res.redirect('/')
+});
+  
+// Login
+router.get('/', async (req, res) => {
+  // Do anything you want
+  console.warn('login not implemented! Automatic passed as sample user')
+
+  // save the user info into session
+  // username will be used in db
+  // display will be used in UI
+  req.session.user = {
+    username: 'sample_user',
+    display: 'Sample User',
+  }
+
+  req.session.save(function (error) {
+    if (error) {    
+        console.log(error);
+        res.send(`<h1>Login Failed. An error occurred. Please see the server logs for details.</h1>`);
+    } else res.redirect('/')
+  })
+});
+
+module.exports = router;

api/server/routes/convos.js

@@ -0,0 +1,67 @@
+const express = require('express');
+const router = express.Router();
+const { titleConvo } = require('../../app/');
+const { getConvo, saveConvo, getConvoTitle } = require('../../models');
+const { getConvosByPage, deleteConvos, updateConvo } = require('../../models/Conversation');
+const { getMessages } = require('../../models/Message');
+
+router.get('/', async (req, res) => {
+  const pageNumber = req.query.pageNumber || 1;
+  res.status(200).send(await getConvosByPage(req?.session?.user?.username, pageNumber));
+});
+
+router.post('/gen_title', async (req, res) => {
+  const { conversationId } = req.body.arg;
+
+  const convo = await getConvo(req?.session?.user?.username, conversationId)
+  const firstMessage = (await getMessages({ conversationId }))[0]
+  const secondMessage = (await getMessages({ conversationId }))[1]
+
+  const title = convo.jailbreakConversationId
+    ? await getConvoTitle(req?.session?.user?.username, conversationId)
+    : await titleConvo({
+        model: convo?.model,
+        message: firstMessage?.text,
+        response: JSON.stringify(secondMessage?.text || '')
+      });
+
+  await saveConvo(
+    req?.session?.user?.username,
+    {
+      conversationId,
+      title
+    }
+  )
+
+  res.status(200).send(title);
+});
+
+router.post('/clear', async (req, res) => {
+  let filter = {};
+  const { conversationId } = req.body.arg;
+  if (conversationId) {
+    filter = { conversationId };
+  }
+
+  try {
+    const dbResponse = await deleteConvos(req?.session?.user?.username, filter);
+    res.status(201).send(dbResponse);
+  } catch (error) {
+    console.error(error);
+    res.status(500).send(error);
+  }
+});
+
+router.post('/update', async (req, res) => {
+  const update = req.body.arg;
+
+  try {
+    const dbResponse = await updateConvo(req?.session?.user?.username, update);
+    res.status(201).send(dbResponse);
+  } catch (error) {
+    console.error(error);
+    res.status(500).send(error);
+  }
+});
+
+module.exports = router;

api/server/routes/customGpts.js

@@ -0,0 +1,67 @@
+const express = require('express');
+const router = express.Router();
+const {
+  getCustomGpts,
+  updateCustomGpt,
+  updateByLabel,
+  deleteCustomGpts
+} = require('../../models');
+
+router.get('/', async (req, res) => {
+  const models = (await getCustomGpts(req?.session?.user?.username)).map((model) => {
+    model = model.toObject();
+    model._id = model._id.toString();
+    return model;
+  });
+  res.status(200).send(models);
+});
+
+router.post('/delete', async (req, res) => {
+  const { arg } = req.body;
+
+  try {
+    await deleteCustomGpts(req?.session?.user?.username, arg);
+    const models = (await getCustomGpts(req?.session?.user?.username)).map((model) => {
+      model = model.toObject();
+      model._id = model._id.toString();
+      return model;
+    });
+    res.status(201).send(models);
+    // res.status(201).send(dbResponse);
+  } catch (error) {
+    console.error(error);
+    res.status(500).send(error);
+  }
+});
+
+// router.post('/create', async (req, res) => {
+//   const payload = req.body.arg;
+
+//   try {
+//     const dbResponse = await createCustomGpt(payload);
+//     res.status(201).send(dbResponse);
+//   } catch (error) {
+//     console.error(error);
+//     res.status(500).send(error);
+//   }
+// });
+
+router.post('/', async (req, res) => {
+  const update = req.body.arg;
+
+  let setter = updateCustomGpt;
+
+  if (update.prevLabel) {
+    setter = updateByLabel;
+  }
+
+  try {
+    const dbResponse = await setter(req?.session?.user?.username, update);
+    res.status(201).send(dbResponse);
+  } catch (error) {
+    console.error(error);
+    res.status(500).send(error);
+  }
+});
+
+module.exports = router;

api/server/routes/handlers.js

@@ -0,0 +1,62 @@
+const _ = require('lodash');
+const citationRegex = /\[\^\d+?\^]/g;
+const { getCitations, citeText, detectCode } = require('../../app/');
+
+const handleError = (res, message) => {
+  res.write(`event: error\ndata: ${JSON.stringify(message)}\n\n`);
+  res.end();
+};
+
+const sendMessage = (res, message) => {
+  if (message.length === 0) {
+    return;
+  }
+  res.write(`event: message\ndata: ${JSON.stringify(message)}\n\n`);
+};
+
+const createOnProgress = () => {
+  let i = 0;
+  let tokens = '';
+
+  const progressCallback = async (partial, { res, text, bing = false, ...rest }) => {
+    tokens += partial === text ? '' : partial;
+    tokens = tokens.replaceAll('[DONE]', '');
+
+    if (tokens.match(/^\n/)) {
+      tokens = tokens.replace(/^\n/, '');
+    }
+
+    if (bing) {
+      tokens = citeText(tokens, true);
+    }
+
+    sendMessage(res, { text: tokens, message: true, initial: i === 0, ...rest });
+    i++;
+  };
+
+  const onProgress = (model, opts) => {
+    const bingModels = new Set(['bingai', 'sydney']);
+    return _.partialRight(progressCallback, { ...opts, bing: bingModels.has(model) });
+  };
+
+  return onProgress;
+};
+
+const handleText = async (response, bing = false) => {
+  let { text } = response;
+  // text = await detectCode(text);
+  response.text = text;
+
+  if (bing) {
+    // const hasCitations = response.response.match(citationRegex)?.length > 0;
+    const links = getCitations(response);
+    if (response.text.match(citationRegex)?.length > 0) {
+      text = citeText(response);
+    }
+    text += links?.length > 0 ? `\n<small>${links}</small>` : '';
+  }
+
+  return text;
+};
+
+module.exports = { handleError, sendMessage, createOnProgress, handleText };

api/server/routes/index.js

@@ -0,0 +1,8 @@
+const ask = require('./ask');
+const messages = require('./messages');
+const convos = require('./convos');
+const customGpts = require('./customGpts');
+const prompts = require('./prompts');
+const { router: auth, authenticatedOr401, authenticatedOrRedirect } = require('./auth');
+
+module.exports = { ask, messages, convos, customGpts, prompts, auth, authenticatedOr401, authenticatedOrRedirect };

api/server/routes/messages.js

@@ -0,0 +1,10 @@
+const express = require('express');
+const router = express.Router();
+const { getMessages } = require('../../models/Message');
+
+router.get('/:conversationId', async (req, res) => {
+  const { conversationId } = req.params;
+  res.status(200).send(await getMessages({ conversationId }));
+});
+
+module.exports = router;

api/server/routes/prompts.js

@@ -0,0 +1,14 @@
+const express = require('express');
+const router = express.Router();
+const { savePrompt, getPrompts, deletePrompts } = require('../../models/Prompt');
+
+router.get('/', async (req, res) => {
+  let filter = {};
+  // const { search } = req.body.arg;
+  // if (!!search) {
+  //   filter = { conversationId };
+  // }
+  res.status(200).send(await getPrompts(filter));
+});
+
+module.exports = router;

api/utils/languages.js

@@ -0,0 +1,318 @@
+const languages = new Set([
+ 'adoc',
+ 'apacheconf',
+ 'arm',
+ 'as',
+ 'asc',
+ 'atom',
+ 'bat',
+ 'bf',
+ 'bind',
+ 'c++',
+ 'capnp',
+ 'cc',
+ 'clj',
+ 'cls',
+ 'cmake.in',
+ 'cmd',
+ 'coffee',
+ 'console',
+ 'cr',
+ 'craftcms',
+ 'crm',
+ 'cs',
+ 'cson',
+ 'cts',
+ 'cxx',
+ 'dfm',
+ 'docker',
+ 'dst',
+ 'erl',
+ 'f90',
+ 'f95',
+ 'fs',
+ 'gawk',
+ 'gemspec',
+ 'gms',
+ 'golang',
+ 'gololang',
+ 'gss',
+ 'gyp',
+ 'h',
+ 'h++',
+ 'hbs',
+ 'hh',
+ 'hpp',
+ 'hs',
+ 'html',
+ 'html.handlebars',
+ 'html.hbs',
+ 'https',
+ 'hx',
+ 'hxx',
+ 'hylang',
+ 'i7',
+ 'iced',
+ 'ino',
+ 'instances',
+ 'irb',
+ 'jinja',
+ 'js',
+ 'jsp',
+ 'jsx',
+ 'julia-repl',
+ 'kdb',
+ 'kt',
+ 'lassoscript',
+ 'ls',
+ 'ls',
+ 'mak',
+ 'make',
+ 'mawk',
+ 'md',
+ 'mipsasm',
+ 'mk',
+ 'mkd',
+ 'mkdown',
+ 'ml',
+ 'ml',
+ 'mm',
+ 'mma',
+ 'moon',
+ 'mts',
+ 'nawk',
+ 'nc',
+ 'nginxconf',
+ 'nimrod',
+ 'objc',
+ 'obj-c',
+ 'obj-c++',
+ 'objective-c++',
+ 'osascript',
+ 'pas',
+ 'pascal',
+ 'patch',
+ 'pcmk',
+ 'pf.conf',
+ 'pl',
+ 'plist',
+ 'pm',
+ 'podspec',
+ 'postgres',
+ 'postgresql',
+ 'pp',
+ 'ps',
+ 'ps1',
+ 'py',
+ 'pycon',
+ 'rb',
+ 're',
+ 'rs',
+ 'rss',
+ 'sas',
+ 'scad',
+ 'sci',
+ 'sh',
+ 'st',
+ 'stanfuncs',
+ 'step',
+ 'stp',
+ 'styl',
+ 'svg',
+ 'tao',
+ 'text',
+ 'thor',
+ 'tk',
+ 'toml',
+ 'ts',
+ 'tsx',
+ 'txt',
+ 'v',
+ 'vb',
+ 'vbs',
+ 'wl',
+ 'x++',
+ 'xhtml',
+ 'xjb',
+ 'xls',
+ 'xlsx',
+ 'xpath',
+ 'xq',
+ 'xsd',
+ 'xsl',
+ 'yaml',
+ 'zep',
+ 'zone',
+ 'zsh',
+ '1c',
+ 'abnf',
+ 'accesslog',
+ 'actionscript',
+ 'ada',
+ 'angelscript',
+ 'apache',
+ 'applescript',
+ 'arcade',
+ 'arduino',
+ 'armasm',
+ 'asciidoc',
+ 'aspectj',
+ 'autohotkey',
+ 'autoit',
+ 'avrasm',
+ 'awk',
+ 'axapta',
+ 'bash',
+ 'basic',
+ 'bnf',
+ 'brainfuck',
+ 'c',
+ 'cal',
+ 'capnproto',
+ 'clojure',
+ 'cmake',
+ 'coffeescript',
+ 'coq',
+ 'cos',
+ 'cpp',
+ 'crmsh',
+ 'crystal',
+ 'csharp',
+ 'csp',
+ 'css',
+ 'd',
+ 'dart',
+ 'diff',
+ 'django',
+ 'dns',
+ 'dockerfile',
+ 'dos',
+ 'dpr',
+ 'dsconfig',
+ 'dts',
+ 'dust',
+ 'ebnf',
+ 'elixir',
+ 'elm',
+ 'erlang',
+ 'excel',
+ 'fix',
+ 'fortran',
+ 'fsharp',
+ 'gams',
+ 'gauss',
+ 'gcode',
+ 'gherkin',
+ 'glsl',
+ 'go',
+ 'golo',
+ 'gradle',
+ 'graph',
+ 'graphql',
+ 'groovy',
+ 'haml',
+ 'handlebars',
+ 'haskell',
+ 'haxe',
+ 'http',
+ 'hy',
+ 'inform7',
+ 'ini',
+ 'irpf90',
+ 'java',
+ 'javascript',
+ 'json',
+ 'julia',
+ 'k',
+ 'kotlin',
+ 'lasso',
+ 'ldif',
+ 'leaf',
+ 'less',
+ 'lisp',
+ 'livecodeserver',
+ 'livescript',
+ 'lua',
+ 'makefile',
+ 'markdown',
+ 'mathematica',
+ 'matlab',
+ 'maxima',
+ 'mel',
+ 'mercury',
+ 'mips',
+ 'mizar',
+ 'mojolicious',
+ 'monkey',
+ 'moonscript',
+ 'n1ql',
+ 'nginx',
+ 'nim',
+ 'nix',
+ 'nsis',
+ 'objectivec',
+ 'ocaml',
+ 'openscad',
+ 'oxygene',
+ 'p21',
+ 'parser3',
+ 'perl',
+ 'pf',
+ 'pgsql',
+ 'php',
+ 'plaintext',
+ 'pony',
+ 'powershell',
+ 'processing',
+ 'profile',
+ 'prolog',
+ 'properties',
+ 'protobuf',
+ 'puppet',
+ 'python',
+ 'python-repl',
+ 'qml',
+ 'r',
+ 'reasonml',
+ 'rib',
+ 'rsl',
+ 'ruby',
+ 'ruleslanguage',
+ 'rust',
+ 'SAS',
+ 'scala' ,
+ 'scheme',
+ 'scilab',
+ 'scss',
+ 'shell',
+ 'smali',
+ 'smalltalk',
+ 'sml',
+ 'sql',
+ 'stan',
+ 'stata',
+ 'stylus',
+ 'subunit',
+ 'swift',
+ 'tap',
+ 'tcl',
+ 'tex',
+ 'thrift',
+ 'tp',
+ 'twig',
+ 'typescript',
+ 'vala',
+ 'vbnet',
+ 'vbscript',
+ 'verilog',
+ 'vhdl',
+ 'vim',
+ 'x86asm',
+ 'xl',
+ 'xml',
+ 'xquery',
+ 'yml',
+ 'zephir',
+]);
+
+module.exports = languages;

ci_cd/check_file_length.py

@@ -1,28 +0,0 @@
-import sys
-
-
-def check_file_length(max_lines, filenames):
-    bad_files = []
-    for filename in filenames:
-        with open(filename, "r") as file:
-            lines = file.readlines()
-            if len(lines) > max_lines:
-                bad_files.append((filename, len(lines)))
-    return bad_files
-
-
-if __name__ == "__main__":
-    max_lines = int(sys.argv[1])
-    filenames = sys.argv[2:]
-
-    bad_files = check_file_length(max_lines, filenames)
-    if bad_files:
-        bad_files.sort(
-            key=lambda x: x[1], reverse=True
-        )  # Sort files by length in descending order
-        for filename, length in bad_files:
-            print(f"{filename}: {length} lines")
-
-        sys.exit(1)
-    else:
-        sys.exit(0)

ci_cd/check_files_match.py

@@ -1,32 +0,0 @@
-import sys
-import filecmp
-import shutil
-
-
-def main(argv=None):
-    print(
-        "Comparing model_prices_and_context_window and litellm/model_prices_and_context_window_backup.json files... checking if they match."
-    )
-
-    file1 = "model_prices_and_context_window.json"
-    file2 = "litellm/model_prices_and_context_window_backup.json"
-
-    cmp_result = filecmp.cmp(file1, file2, shallow=False)
-
-    if cmp_result:
-        print(f"Passed! Files {file1} and {file2} match.")
-        return 0
-    else:
-        print(
-            f"Failed! Files {file1} and {file2} do not match. Copying content from {file1} to {file2}."
-        )
-        copy_content(file1, file2)
-        return 1
-
-
-def copy_content(source, destination):
-    shutil.copy2(source, destination)
-
-
-if __name__ == "__main__":
-    sys.exit(main())

client/.babelrc

@@ -0,0 +1,23 @@
+{
+  /*
+      a preset is a set of plugins used to support particular language features.
+      The two presets Babel uses by default: es2015, react
+  */
+  "presets": [
+      "@babel/preset-env", //compiling ES2015+ syntax
+      "@babel/preset-react" //for react
+  ],
+  /*
+      Babel's code transformations are enabled by applying plugins (or presets) to your configuration file.
+  */
+  "plugins": [
+      "@babel/plugin-transform-runtime",
+      [
+        "babel-plugin-root-import",
+        {
+          "rootPathPrefix": "~/",
+          "rootPathSuffix": "./src"
+        }
+      ]
+  ]
+}

client/.dockerignore

@@ -0,0 +1,2 @@
+/node_modules
+.env

client/Dockerfile

@@ -0,0 +1,22 @@
+# Stage 1
+FROM node:19-alpine as builder
+WORKDIR /client
+# copy package.json into the container at /client
+COPY package*.json /client/
+# install dependencies
+RUN npm install
+# Copy the current directory contents into the container at /client
+COPY . /client/
+# Build webpack artifacts
+RUN npm run build
+
+# Stage 2
+FROM nginx:stable-alpine
+WORKDIR /usr/share/nginx/html
+RUN rm -rf ./*
+COPY --from=builder /client/public /usr/share/nginx/html
+# Add your nginx.conf
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+ENTRYPOINT ["nginx", "-g", "daemon off;"]
+
+# docker build -t react-client .

client/index.js

@@ -0,0 +1,19 @@
+import React from 'react';
+import { createRoot } from 'react-dom/client';
+import { Provider } from 'react-redux';
+import { store } from './src/store';
+import { ThemeProvider } from './src/hooks/ThemeContext';
+import App from './src/App';
+import './src/style.css';
+import './src/mobile.css'
+
+const container = document.getElementById('root');
+const root = createRoot(container);
+
+root.render(
+  <Provider store={store}>
+    <ThemeProvider>
+      <App />
+    </ThemeProvider>
+  </Provider>
+);

client/nginx.conf

@@ -0,0 +1,15 @@
+server {
+  listen 80;
+  server_name localhost;
+
+  location / {
+    # Serve your React app
+    root /usr/share/nginx/html;
+    index index.html;
+  }
+
+  location /api {
+    # Proxy requests to the API service
+    proxy_pass http://api:3080/api;
+  }
+}

client/package.json

@@ -0,0 +1,79 @@
+{
+  "name": "chatgpt-clone",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "build": "webpack",
+    "build-dev": "Webpack . --watch"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/danny-avila/chatgpt-clone.git"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "bugs": {
+    "url": "https://github.com/danny-avila/chatgpt-clone/issues"
+  },
+  "homepage": "https://github.com/danny-avila/chatgpt-clone#readme",
+  "dependencies": {
+    "@radix-ui/react-alert-dialog": "^1.0.2",
+    "@radix-ui/react-dialog": "^1.0.2",
+    "@radix-ui/react-dropdown-menu": "^2.0.2",
+    "@radix-ui/react-label": "^2.0.0",
+    "@radix-ui/react-tabs": "^1.0.2",
+    "@reduxjs/toolkit": "^1.9.2",
+    "axios": "^1.3.4",
+    "class-variance-authority": "^0.4.0",
+    "clsx": "^1.2.1",
+    "crypto-browserify": "^3.12.0",
+    "highlight.js": "^11.7.0",
+    "lucide-react": "^0.113.0",
+    "markdown-to-jsx": "^7.1.9",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0",
+    "react-redux": "^8.0.5",
+    "react-textarea-autosize": "^8.4.0",
+    "react-transition-group": "^4.4.5",
+    "swr": "^2.0.3",
+    "tailwind-merge": "^1.9.1",
+    "tailwindcss-animate": "^1.0.5",
+    "url": "^0.11.0"
+  },
+  "devDependencies": {
+    "@babel/cli": "^7.20.7",
+    "@babel/core": "^7.20.12",
+    "@babel/eslint-parser": "^7.19.1",
+    "@babel/plugin-transform-runtime": "^7.19.6",
+    "@babel/preset-env": "^7.20.2",
+    "@babel/preset-react": "^7.18.6",
+    "@babel/runtime": "^7.20.13",
+    "autoprefixer": "^10.4.13",
+    "babel-loader": "^9.1.2",
+    "babel-plugin-root-import": "^6.6.0",
+    "babel-preset-react": "^6.24.1",
+    "css-loader": "^6.7.3",
+    "eslint": "^8.33.0",
+    "eslint-config-airbnb-base": "^15.0.0",
+    "eslint-config-prettier": "^8.6.0",
+    "eslint-plugin-jest": "^27.2.1",
+    "eslint-plugin-react": "^7.32.2",
+    "eslint-plugin-react-hooks": "^4.6.0",
+    "path": "^0.12.7",
+    "postcss": "^8.4.21",
+    "postcss-loader": "^7.0.2",
+    "postcss-preset-env": "^8.0.1",
+    "prettier": "^2.8.3",
+    "prettier-plugin-tailwindcss": "^0.2.2",
+    "source-map-loader": "^1.1.3",
+    "style-loader": "^3.3.1",
+    "tailwindcss": "^3.2.6",
+    "ts-loader": "^9.4.2",
+    "typescript": "^4.9.5",
+    "webpack": "^5.75.0",
+    "webpack-cli": "^5.0.1",
+    "webpack-dev-server": "^4.11.1"
+  }
+}

client/postcss.config.js

@@ -0,0 +1,2 @@
+const tailwindcss = require('tailwindcss');
+module.exports = { plugins: ['postcss-preset-env', tailwindcss] };

client/public/index.html

@@ -0,0 +1,40 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <meta name="theme-color" content="#343541">
+    <title>ChatGPT Clone</title>
+    <link
+      rel="shortcut icon"
+      href="#"
+    />
+    <link
+      rel="icon"
+      type="image/png"
+      sizes="32x32"
+      href="/assets/favicon-32x32.png"
+    />
+    <link
+      rel="icon"
+      type="image/png"
+      sizes="16x16"
+      href="/assets/favicon-16x16.png"
+    />
+    <meta
+      name="viewport"
+      content="width=device-width, initial-scale=1"
+    />
+    <script
+      defer
+      src="main.js"
+    ></script>
+  </head>
+  <body>
+    <div id="root"></div>
+
+    <script
+      type="text/javascript"
+      src="main.js"
+    ></script>
+  </body>
+</html>

client/src/App.jsx

@@ -0,0 +1,71 @@
+import React, { useEffect, useState } from 'react';
+import Messages from './components/Messages';
+import Landing from './components/Main/Landing';
+import TextChat from './components/Main/TextChat';
+import Nav from './components/Nav';
+import MobileNav from './components/Nav/MobileNav';
+import useDocumentTitle from '~/hooks/useDocumentTitle';
+import { useSelector, useDispatch } from 'react-redux';
+import { setUser } from './store/userReducer';
+import axios from 'axios';
+
+const App = () => {
+  const dispatch = useDispatch();
+  
+  const { messages, messageTree } = useSelector((state) => state.messages);
+  const { user } = useSelector((state) => state.user);
+  const { title } = useSelector((state) => state.convo);
+  const { conversationId } = useSelector((state) => state.convo);
+  const [ navVisible, setNavVisible ]= useState(false)
+  useDocumentTitle(title);
+
+  useEffect(() => {
+    axios.get('/api/me', {
+      timeout: 1000,
+      withCredentials: true
+    }).then((res) => {
+      return res.data
+    }).then((user) => {
+      if (user)
+        dispatch(setUser(user))
+      else {
+        console.log('Not login!')
+        window.location.href = "/auth/login";
+      }
+    }).catch((error) => {
+      console.error(error)
+      console.log('Not login!')
+      window.location.href = "/auth/login";
+    })
+    // setUser
+  }, [])
+
+  if (user)
+    return (
+      <div className="flex h-screen">
+        <Nav navVisible={navVisible} setNavVisible={setNavVisible} />
+        <div className="flex h-full w-full flex-1 flex-col bg-gray-50 md:pl-[260px]">
+          <div className="transition-width relative flex h-full w-full flex-1 flex-col items-stretch overflow-hidden bg-white dark:bg-gray-800">
+            <MobileNav setNavVisible={setNavVisible} />
+            {messages.length === 0 ? (
+              <Landing title={title} />
+            ) : (
+              <Messages
+                messages={messages}
+                messageTree={messageTree}
+              />
+            )}
+            <TextChat messages={messages} />
+          </div>
+        </div>
+      </div>
+    );
+  else
+    return (
+      <div className="flex h-screen">
+        
+      </div>
+    )
+};
+
+export default App;

client/src/components/Conversations/Conversation.jsx

@@ -0,0 +1,184 @@
+import React, { useState, useRef } from 'react';
+import RenameButton from './RenameButton';
+import DeleteButton from './DeleteButton';
+import { useSelector, useDispatch } from 'react-redux';
+import { setConversation } from '~/store/convoSlice';
+import { setSubmission, setStopStream, setCustomGpt, setModel, setCustomModel } from '~/store/submitSlice';
+import { setMessages, setEmptyMessage } from '~/store/messageSlice';
+import { setText } from '~/store/textSlice';
+import manualSWR from '~/utils/fetchers';
+import ConvoIcon from '../svg/ConvoIcon';
+import { refreshConversation } from '../../store/convoSlice';
+
+export default function Conversation({
+  id,
+  model,
+  parentMessageId,
+  conversationId,
+  title,
+  chatGptLabel = null,
+  promptPrefix = null,
+  bingData,
+  retainView,
+}) {
+  const [renaming, setRenaming] = useState(false);
+  const [titleInput, setTitleInput] = useState(title);
+  const { modelMap } = useSelector((state) => state.models);
+  const { stopStream } = useSelector((state) => state.submit);
+  const inputRef = useRef(null);
+  const dispatch = useDispatch();
+  const { trigger } = manualSWR(`/api/messages/${id}`, 'get');
+  const rename = manualSWR(`/api/convos/update`, 'post');
+
+  const clickHandler = async () => {
+    if (conversationId === id) {
+      return;
+    }
+
+    if (!stopStream) {
+      dispatch(setStopStream(true));
+      dispatch(setSubmission({}));
+    }
+    dispatch(setEmptyMessage());
+
+    const convo = { title, error: false, conversationId: id, chatGptLabel, promptPrefix };
+
+    if (bingData) {
+      const {
+        parentMessageId,
+        conversationSignature,
+        jailbreakConversationId,
+        clientId,
+        invocationId
+      } = bingData;
+      dispatch(
+        setConversation({
+          ...convo,
+          parentMessageId,
+          jailbreakConversationId,
+          conversationSignature,
+          clientId,
+          invocationId,
+          latestMessage: null
+        })
+      );
+    } else {
+      dispatch(
+        setConversation({
+          ...convo,
+          parentMessageId,
+          jailbreakConversationId: null,
+          conversationSignature: null,
+          clientId: null,
+          invocationId: null,
+          latestMessage: null
+        })
+      );
+    }
+    const data = await trigger();
+
+    if (chatGptLabel) {
+      dispatch(setModel('chatgptCustom'));
+      dispatch(setCustomModel(chatGptLabel.toLowerCase()));
+    } else {
+      dispatch(setModel(model));
+      dispatch(setCustomModel(null));
+    }
+
+    // if (modelMap[chatGptLabel.toLowerCase()]) {
+    //   console.log('custom model', chatGptLabel);
+    //   dispatch(setCustomModel(chatGptLabel.toLowerCase()));
+    // } else {
+    //   dispatch(setCustomModel(null));
+    // }
+
+    dispatch(setMessages(data));
+    dispatch(setCustomGpt(convo));
+    dispatch(setText(''));
+    dispatch(setStopStream(false));
+  };
+
+  const renameHandler = (e) => {
+    e.preventDefault();
+    setTitleInput(title);
+    setRenaming(true);
+    setTimeout(() => {
+      inputRef.current.focus();
+    }, 25);
+  };
+
+  const cancelHandler = (e) => {
+    e.preventDefault();
+    setRenaming(false);
+  };
+
+  const onRename = (e) => {
+    e.preventDefault();
+    setRenaming(false);
+    if (titleInput === title) {
+      return;
+    }
+    rename.trigger({ conversationId, title: titleInput })
+      .then(() => {
+        dispatch(refreshConversation())
+      });
+  };
+
+  const handleKeyDown = (e) => {
+    if (e.key === 'Enter') {
+      onRename(e);
+    }
+  };
+
+  const aProps = {
+    className:
+      'animate-flash group relative flex cursor-pointer items-center gap-3 break-all rounded-md bg-gray-800 py-3 px-3 pr-14 hover:bg-gray-800'
+  };
+
+  if (conversationId !== id) {
+    aProps.className =
+      'group relative flex cursor-pointer items-center gap-3 break-all rounded-md py-3 px-3 hover:bg-[#2A2B32] hover:pr-4';
+  }
+
+  return (
+    <a
+      onClick={() => clickHandler()}
+      {...aProps}
+    >
+      <ConvoIcon />
+      <div className="relative max-h-5 flex-1 overflow-hidden text-ellipsis break-all">
+        {renaming === true ? (
+          <input
+            ref={inputRef}
+            type="text"
+            className="m-0 mr-0 w-full border border-blue-500 bg-transparent p-0 text-sm leading-tight outline-none"
+            value={titleInput}
+            onChange={(e) => setTitleInput(e.target.value)}
+            onBlur={onRename}
+            onKeyDown={handleKeyDown}
+          />
+        ) : (
+          title
+        )}
+      </div>
+      {conversationId === id ? (
+        <div className="visible absolute right-1 z-10 flex text-gray-300">
+          <RenameButton
+            conversationId={id}
+            renaming={renaming}
+            renameHandler={renameHandler}
+            onRename={onRename}
+          />
+          <DeleteButton
+            conversationId={id}
+            renaming={renaming}
+            cancelHandler={cancelHandler}
+            retainView={retainView}
+          />
+        </div>
+      ) : (
+        <div className="absolute inset-y-0 right-0 z-10 w-8 bg-gradient-to-l from-gray-900 group-hover:from-[#2A2B32]" />
+      )}
+    </a>
+  );
+}

client/src/components/Conversations/DeleteButton.jsx

@@ -0,0 +1,35 @@
+import React from 'react';
+import TrashIcon from '../svg/TrashIcon';
+import CrossIcon from '../svg/CrossIcon';
+import manualSWR from '~/utils/fetchers';
+import { useDispatch } from 'react-redux';
+import { setNewConvo, removeConvo } from '~/store/convoSlice';
+import { setMessages } from '~/store/messageSlice';
+import { setSubmission } from '~/store/submitSlice';
+
+export default function DeleteButton({ conversationId, renaming, cancelHandler, retainView }) {
+  const dispatch = useDispatch();
+  const { trigger } = manualSWR(
+    `/api/convos/clear`,
+    'post',
+    () => {
+      dispatch(setMessages([]));
+      dispatch(removeConvo(conversationId));
+      dispatch(setNewConvo());
+      dispatch(setSubmission({}));
+      retainView();
+    }
+  );
+
+  const clickHandler = () => trigger({ conversationId });
+  const handler = renaming ? cancelHandler : clickHandler;
+
+  return (
+    <button
+      className="p-1 hover:text-white"
+      onClick={handler}
+    >
+      { renaming ? <CrossIcon/> : <TrashIcon />}
+    </button>
+  );
+}

client/src/components/Conversations/RenameButton.jsx

@@ -0,0 +1,16 @@
+import React from 'react';
+import RenameIcon from '../svg/RenameIcon';
+import CheckMark from '../svg/CheckMark';
+
+export default function RenameButton({ renaming, renameHandler, onRename, twcss }) {
+  const handler = renaming ? onRename : renameHandler;
+  const classProp = { className: "p-1 hover:text-white" };
+  if (twcss) {
+    classProp.className = twcss;
+  }
+  return (
+    <button {...classProp} onClick={handler}>
+      {renaming ? <CheckMark /> : <RenameIcon />}
+    </button>
+  );
+}

client/src/components/Conversations/index.jsx

@@ -0,0 +1,61 @@
+import React from 'react';
+import Conversation from './Conversation';
+
+export default function Conversations({ conversations, conversationId, pageNumber, pages, nextPage, previousPage, moveToTop }) {
+  const clickHandler = (func) => async (e) => {
+    e.preventDefault();
+    await func();
+  };
+
+  return (
+    <>
+      {conversations &&
+        conversations.length > 0 &&
+        conversations.map((convo) => {
+          const bingData = convo.conversationSignature
+            ? {
+                jailbreakConversationId: convo.jailbreakConversationId,
+                conversationSignature: convo.conversationSignature,
+                parentMessageId: convo.parentMessageId || null,
+                clientId: convo.clientId,
+                invocationId: convo.invocationId
+              }
+            : null;
+
+          return (
+            <Conversation
+              key={convo.conversationId}
+              id={convo.conversationId}
+              model={convo.model}
+              parentMessageId={convo.parentMessageId}
+              title={convo.title}
+              conversationId={conversationId}
+              chatGptLabel={convo.chatGptLabel}
+              promptPrefix={convo.promptPrefix}
+              bingData={bingData}
+              retainView={moveToTop}
+            />
+          );
+        })}
+        <div className="m-auto mt-4 mb-2 flex justify-center items-center gap-2">
+          <button
+            onClick={clickHandler(previousPage)}
+            className={"flex btn btn-small transition bg-transition dark:text-white disabled:text-gray-300 dark:disabled:text-gray-400 m-auto gap-2 hover:bg-gray-800" + (pageNumber<=1?" hidden-visibility":"")}
+            disabled={pageNumber<=1}
+          >
+            &lt;&lt;
+          </button>
+          <span className="flex-none text-gray-400">
+            {pageNumber} / {pages}
+          </span>
+          <button
+            onClick={clickHandler(nextPage)}
+            className={"flex btn btn-small transition bg-transition dark:text-white disabled:text-gray-300 dark:disabled:text-gray-400 m-auto gap-2 hover:bg-gray-800" + (pageNumber>=pages?" hidden-visibility":"")}
+            disabled={pageNumber>=pages}
+          >
+            &gt;&gt;
+          </button>
+        </div>
+    </>
+  );
+}

client/src/components/Main/Footer.jsx

@@ -0,0 +1,18 @@
+import React from 'react';
+
+export default function Footer() {
+  return (
+    <div className="hidden md:block px-3 pt-2 pb-1 text-center text-xs text-black/50 dark:text-white/50 md:px-4 md:pt-3 md:pb-4">
+      <a
+        href="https://github.com/danny-avila/chatgpt-clone"
+        target="_blank"
+        rel="noreferrer"
+        className="underline"
+      >
+        ChatGPT Clone
+      </a>
+      . Serves and searches all conversations reliably. All AI convos under one house. Pay per
+      call and not per month (cents compared to dollars).
+    </div>
+  );
+}

client/src/components/Main/Landing.jsx

@@ -0,0 +1,112 @@
+import React, { useState } from 'react';
+import { useDispatch } from 'react-redux';
+import { setText } from '~/store/textSlice';
+import useDocumentTitle from '~/hooks/useDocumentTitle';
+import Templates from '../Prompts/Templates';
+import SunIcon from '../svg/SunIcon';
+import LightningIcon from '../svg/LightningIcon';
+import CautionIcon from '../svg/CautionIcon';
+import ChatIcon from '../svg/ChatIcon';
+
+export default function Landing({ title }) {
+  const [showingTemplates, setShowingTemplates] = useState(false);
+  const dispatch = useDispatch();
+  useDocumentTitle(title);
+
+  const clickHandler = (e) => {
+    e.preventDefault();
+    const { innerText } = e.target;
+    const quote = innerText.split('"')[1].trim();
+    dispatch(setText(quote));
+  };
+
+  const showTemplates = (e) => {
+    e.preventDefault();
+    setShowingTemplates(!showingTemplates);
+  };
+
+  return (
+    <div className="flex pt-10 md:pt-0 h-full flex-col items-center overflow-y-auto text-sm dark:bg-gray-800">
+      <div className="w-full px-6 text-gray-800 dark:text-gray-100 md:flex md:max-w-2xl md:flex-col lg:max-w-3xl">
+        <h1 className="mt-6 ml-auto mr-auto mb-10 flex items-center justify-center gap-2 text-center text-4xl font-semibold md:mt-[20vh] sm:mb-16">
+          ChatGPT Clone
+        </h1>
+        <div className="items-start gap-3.5 text-center md:flex">
+          <div className="mb-8 flex flex-1 flex-col gap-3.5 md:mb-auto">
+            <h2 className="m-auto flex items-center gap-3 text-lg font-normal md:flex-col md:gap-2">
+              <SunIcon />
+              Examples
+            </h2>
+            <ul className="m-auto flex w-full flex-col gap-3.5 sm:max-w-md">
+              <button
+                onClick={clickHandler}
+                className="w-full rounded-md bg-gray-50 p-3 hover:bg-gray-200 dark:bg-white/5 dark:hover:bg-gray-900"
+              >
+                &quot;Explain quantum computing in simple terms&quot; →
+              </button>
+              <button
+                onClick={clickHandler}
+                className="w-full rounded-md bg-gray-50 p-3 hover:bg-gray-200 dark:bg-white/5 dark:hover:bg-gray-900"
+              >
+                &quot;Got any creative ideas for a 10 year old&apos;s birthday?&quot; →
+              </button>
+              <button
+                onClick={clickHandler}
+                className="w-full rounded-md bg-gray-50 p-3 hover:bg-gray-200 dark:bg-white/5 dark:hover:bg-gray-900"
+              >
+                &quot;How do I make an HTTP request in Javascript?&quot; →
+              </button>
+            </ul>
+          </div>
+          <div className="mb-8 flex flex-1 flex-col gap-3.5 md:mb-auto">
+            <h2 className="m-auto flex items-center gap-3 text-lg font-normal md:flex-col md:gap-2">
+              <LightningIcon />
+              Capabilities
+            </h2>
+            <ul className="m-auto flex w-full flex-col gap-3.5 sm:max-w-md">
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                Remembers what user said earlier in the conversation
+              </li>
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                Allows user to provide follow-up corrections
+              </li>
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                Trained to decline inappropriate requests
+              </li>
+            </ul>
+          </div>
+          <div className="mb-8 flex flex-1 flex-col gap-3.5 md:mb-auto">
+            <h2 className="m-auto flex items-center gap-3 text-lg font-normal md:flex-col md:gap-2">
+              <CautionIcon />
+              Limitations
+            </h2>
+            <ul className="m-auto flex w-full flex-col gap-3.5 sm:max-w-md">
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                May occasionally generate incorrect information
+              </li>
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                May occasionally produce harmful instructions or biased content
+              </li>
+              <li className="w-full rounded-md bg-gray-50 p-3 dark:bg-white/5">
+                Limited knowledge of world and events after 2021
+              </li>
+            </ul>
+          </div>
+        </div>
+        {/* {!showingTemplates && (
+          <div className="mt-8 mb-4 flex flex-col items-center gap-3.5 md:mt-16">
+            <button
+              onClick={showTemplates}
+              className="btn btn-neutral justify-center gap-2 border-0 md:border"
+            >
+              <ChatIcon />
+              Show Prompt Templates
+            </button>
+          </div>
+        )}
+        {!!showingTemplates && <Templates showTemplates={showTemplates}/>} */}
+        <div className="group h-32 w-full flex-shrink-0 dark:border-gray-900/50 dark:bg-gray-800 md:h-48" />
+      </div>
+    </div>
+  );
+}

client/src/components/Main/Regenerate.jsx

@@ -0,0 +1,35 @@
+import React from 'react';
+import RegenerateIcon from '../svg/RegenerateIcon';
+
+export default function Regenerate({ submitMessage, tryAgain, errorMessage }) {
+  const clickHandler = (e) => {
+    e.preventDefault();
+    submitMessage();
+  };
+
+  return (
+    <>
+      <span className="mb-2 block flex justify-center text-xs text-black dark:text-white/50 md:mb-2">
+        There was an error generating a response
+      </span>
+      <span className="m-auto flex justify-center">
+        {!errorMessage.includes('short') && (
+          <button
+            onClick={clickHandler}
+            className="btn btn-primary m-auto flex justify-center gap-2"
+          >
+            <RegenerateIcon />
+            Regenerate response
+          </button>
+        )}
+        <button
+          onClick={tryAgain}
+          className="btn btn-neutral flex justify-center gap-2 border-0 md:border"
+        >
+          <RegenerateIcon />
+          Try another message
+        </button>
+      </span>
+    </>
+  );
+}

client/src/components/Main/SubmitButton.jsx

@@ -0,0 +1,61 @@
+import React from 'react';
+import { useSelector } from 'react-redux';
+
+export default function SubmitButton({ submitMessage, disabled }) {
+  const { isSubmitting } = useSelector((state) => state.submit);
+  const { error, latestMessage } = useSelector((state) => state.convo);
+
+  const clickHandler = (e) => {
+    e.preventDefault();
+    submitMessage();
+  };
+
+  if (isSubmitting) {
+    return (
+      <button
+        className="absolute bottom-0 right-1 h-[100%] w-[30px] rounded-md p-1 text-gray-500 hover:bg-gray-100 disabled:hover:bg-transparent dark:hover:bg-gray-900 dark:hover:text-gray-400 dark:disabled:hover:bg-transparent md:right-2"
+        disabled
+      >
+        <div className="text-2xl">
+          <span>·</span>
+          <span className="blink">·</span>
+          <span className="blink2">·</span>
+        </div>
+      </button>
+    );
+  }
+  return (
+    <button
+      onClick={clickHandler}
+      disabled={disabled}
+      className="group absolute bottom-0 right-0 flex h-[100%] w-[50px] items-center justify-center bg-transparent p-1 text-gray-500"
+    >
+      <div className="m-1 mr-0 rounded-md p-2 pt-[10px] pb-[10px] group-hover:bg-gray-100 group-disabled:hover:bg-transparent dark:group-hover:bg-gray-900 dark:group-hover:text-gray-400 dark:group-disabled:hover:bg-transparent">
+        <svg
+          stroke="currentColor"
+          fill="none"
+          strokeWidth="2"
+          viewBox="0 0 24 24"
+          strokeLinecap="round"
+          strokeLinejoin="round"
+          className="mr-1 h-4 w-4 "
+          height="1em"
+          width="1em"
+          xmlns="http://www.w3.org/2000/svg"
+        >
+          <line
+            x1="22"
+            y1="2"
+            x2="11"
+            y2="13"
+          />
+          <polygon points="22 2 15 22 11 13 2 9 22 2" />
+        </svg>
+      </div>
+    </button>
+  );
+}
+
+{
+  /* <div class="text-2xl"><span class="">·</span><span class="">·</span><span class="invisible">·</span></div> */
+}

client/src/components/Main/TextChat.jsx

@@ -0,0 +1,411 @@
+import React, { useEffect, useRef, useState } from 'react';
+import { SSE } from '~/utils/sse';
+import SubmitButton from './SubmitButton';
+import Regenerate from './Regenerate';
+import ModelMenu from '../Models/ModelMenu';
+import Footer from './Footer';
+import TextareaAutosize from 'react-textarea-autosize';
+import createPayload from '~/utils/createPayload';
+import resetConvo from '~/utils/resetConvo';
+import RegenerateIcon from '../svg/RegenerateIcon';
+import StopGeneratingIcon from '../svg/StopGeneratingIcon';
+import { useSelector, useDispatch } from 'react-redux';
+import {
+  setConversation,
+  setNewConvo,
+  setError,
+  refreshConversation
+} from '~/store/convoSlice';
+import { setMessages } from '~/store/messageSlice';
+import { setSubmitState, setSubmission } from '~/store/submitSlice';
+import { setText } from '~/store/textSlice';
+import { useMessageHandler } from '../../utils/handleSubmit';
+
+export default function TextChat({ messages }) {
+  const [errorMessage, setErrorMessage] = useState('');
+  const inputRef = useRef(null);
+  const isComposing = useRef(false);
+  const dispatch = useDispatch();
+  const { user } = useSelector((state) => state.user);
+  const convo = useSelector((state) => state.convo);
+  const { initial } = useSelector((state) => state.models);
+  const { isSubmitting, stopStream, submission, disabled, model, chatGptLabel, promptPrefix } =
+    useSelector((state) => state.submit);
+  const { text } = useSelector((state) => state.text);
+  const { error, latestMessage } = convo;
+  const { ask, regenerate, stopGenerating } = useMessageHandler();
+
+  const isNotAppendable = latestMessage?.cancelled || latestMessage?.error;
+
+  // auto focus to input, when enter a conversation.
+  useEffect(() => {
+    inputRef.current?.focus();
+  }, [convo?.conversationId]);
+
+  const messageHandler = (data, currentState, currentMsg) => {
+    const { messages, _currentMsg, message, sender, isRegenerate } = currentState;
+
+    if (isRegenerate)
+      dispatch(
+        setMessages([
+          ...messages,
+          {
+            sender,
+            text: data,
+            parentMessageId: message?.overrideParentMessageId,
+            messageId: message?.overrideParentMessageId + '_',
+            submitting: true
+          }
+        ])
+      );
+    else
+      dispatch(
+        setMessages([
+          ...messages,
+          currentMsg,
+          {
+            sender,
+            text: data,
+            parentMessageId: currentMsg?.messageId,
+            messageId: currentMsg?.messageId + '_',
+            submitting: true
+          }
+        ])
+      );
+  };
+
+  const cancelHandler = (data, currentState, currentMsg) => {
+    const { messages, _currentMsg, message, sender, isRegenerate } = currentState;
+
+    if (isRegenerate)
+      dispatch(
+        setMessages([
+          ...messages,
+          {
+            sender,
+            text: data,
+            parentMessageId: message?.overrideParentMessageId,
+            messageId: message?.overrideParentMessageId + '_',
+            cancelled: true
+          }
+        ])
+      );
+    else
+      dispatch(
+        setMessages([
+          ...messages,
+          currentMsg,
+          {
+            sender,
+            text: data,
+            parentMessageId: currentMsg?.messageId,
+            messageId: currentMsg?.messageId + '_',
+            cancelled: true
+          }
+        ])
+      );
+  };
+
+  const createdHandler = (data, currentState, currentMsg) => {
+    const { conversationId } = currentMsg;
+    dispatch(
+      setConversation({
+        conversationId,
+        latestMessage: null
+      })
+    );
+  };
+
+  const convoHandler = (data, currentState, currentMsg) => {
+    const { requestMessage, responseMessage } = data;
+    const { conversationId } = requestMessage;
+    const { messages, _currentMsg, message, isCustomModel, sender, isRegenerate } =
+      currentState;
+    const { model, chatGptLabel, promptPrefix } = message;
+    if (isRegenerate) dispatch(setMessages([...messages, responseMessage]));
+    else dispatch(setMessages([...messages, requestMessage, responseMessage]));
+    dispatch(setSubmitState(false));
+
+    const isBing = model === 'bingai' || model === 'sydney';
+
+    // refresh title
+    if (requestMessage.parentMessageId == '00000000-0000-0000-0000-000000000000') {
+      setTimeout(() => {
+        dispatch(refreshConversation());
+      }, 2000);
+
+      // in case it takes too long.
+      setTimeout(() => {
+        dispatch(refreshConversation());
+      }, 5000);
+    }
+
+    if (!isBing && convo.conversationId === null && convo.parentMessageId === null) {
+      const { title } = data;
+      const { conversationId, messageId } = responseMessage;
+      dispatch(
+        setConversation({
+          title,
+          conversationId,
+          parentMessageId: messageId,
+          jailbreakConversationId: null,
+          conversationSignature: null,
+          clientId: null,
+          invocationId: null,
+          chatGptLabel: model === isCustomModel ? chatGptLabel : null,
+          promptPrefix: model === isCustomModel ? promptPrefix : null,
+          latestMessage: null
+        })
+      );
+    } else if (model === 'bingai') {
+      console.log('Bing data:', data);
+      const { title } = data;
+      const { conversationSignature, clientId, conversationId, invocationId } =
+        responseMessage;
+      dispatch(
+        setConversation({
+          title,
+          parentMessageId: null,
+          conversationSignature,
+          clientId,
+          conversationId,
+          invocationId,
+          latestMessage: null
+        })
+      );
+    } else if (model === 'sydney') {
+      const { title } = data;
+      const {
+        jailbreakConversationId,
+        parentMessageId,
+        conversationSignature,
+        clientId,
+        conversationId,
+        invocationId
+      } = responseMessage;
+      dispatch(
+        setConversation({
+          title,
+          jailbreakConversationId,
+          parentMessageId,
+          conversationSignature,
+          clientId,
+          conversationId,
+          invocationId,
+          latestMessage: null
+        })
+      );
+    }
+  };
+
+  const errorHandler = (data, currentState, currentMsg) => {
+    const { initialResponse, messages, _currentMsg, message } = currentState;
+    console.log('Error:', data);
+    const errorResponse = {
+      ...data,
+      error: true,
+      parentMessageId: currentMsg?.messageId
+    };
+    setErrorMessage(data?.text);
+    dispatch(setSubmitState(false));
+    dispatch(setMessages([...messages, currentMsg, errorResponse]));
+    dispatch(setText(message?.text));
+    dispatch(setError(true));
+    return;
+  };
+  const submitMessage = () => {
+    ask({ text });
+  };
+
+  useEffect(() => {
+    inputRef.current?.focus();
+    if (Object.keys(submission).length === 0) {
+      return;
+    }
+
+    const currentState = submission;
+
+    let currentMsg = { ...currentState.message };
+    let latestResponseText = '';
+
+    const { server, payload } = createPayload(submission);
+    const onMessage = (e) => {
+      if (stopStream) {
+        return;
+      }
+
+      const data = JSON.parse(e.data);
+
+      if (data.final) {
+        convoHandler(data, currentState, currentMsg);
+        console.log('final', data);
+      }
+      if (data.created) {
+        currentMsg = data.message;
+        createdHandler(data, currentState, currentMsg);
+      } else {
+        let text = data.text || data.response;
+        if (data.initial) {
+          console.log(data);
+        }
+        if (data.message) {
+          latestResponseText = text;
+          messageHandler(text, currentState, currentMsg);
+        }
+        // console.log('dataStream', data);
+      }
+    };
+
+    const events = new SSE(server, {
+      payload: JSON.stringify(payload),
+      headers: { 'Content-Type': 'application/json' }
+    });
+
+    events.onopen = function () {
+      console.log('connection is opened');
+    };
+
+    events.onmessage = onMessage;
+
+    events.oncancel = (e) => {
+      cancelHandler(latestResponseText, currentState, currentMsg);
+    };
+
+    events.onerror = function (e) {
+      console.log('error in opening conn.');
+      events.close();
+
+      const data = JSON.parse(e.data);
+
+      errorHandler(data, currentState, currentMsg);
+    };
+
+    events.stream();
+
+    return () => {
+      events.removeEventListener('message', onMessage);
+      const isCancelled = events.readyState <= 1;
+      events.close();
+      if (isCancelled) {
+        const e = new Event('cancel');
+        events.dispatchEvent(e);
+      }
+    };
+  }, [submission]);
+
+  const handleRegenerate = () => {
+    if (latestMessage && !latestMessage?.isCreatedByUser) regenerate(latestMessage);
+  };
+
+  const handleStopGenerating = () => {
+    stopGenerating();
+  };
+
+  const handleKeyDown = (e) => {
+    if (e.key === 'Enter' && !e.shiftKey) {
+      e.preventDefault();
+    }
+
+    if (e.key === 'Enter' && !e.shiftKey) {
+      if (!isComposing.current) submitMessage();
+    }
+  };
+
+  const handleKeyUp = (e) => {
+    if (e.key === 'Enter' && e.shiftKey) {
+      return console.log('Enter + Shift');
+    }
+
+    if (isSubmitting) {
+      return;
+    }
+  };
+
+  const handleCompositionStart = (e) => {
+    isComposing.current = true;
+  };
+
+  const handleCompositionEnd = (e) => {
+    isComposing.current = false;
+  };
+
+  const changeHandler = (e) => {
+    const { value } = e.target;
+
+    // if (isSubmitting && (value === '' || value === '\n')) {
+    //   return;
+    // }
+    dispatch(setText(value));
+  };
+
+  const tryAgain = (e) => {
+    e.preventDefault();
+    dispatch(setError(false));
+  };
+
+  return (
+    <div className="input-panel md:bg-vert-light-gradient dark:md:bg-vert-dark-gradient fixed bottom-0 left-0 w-full border-t bg-white py-2 dark:border-white/20 dark:bg-gray-800 md:absolute md:border-t-0 md:border-transparent md:bg-transparent md:dark:border-transparent md:dark:bg-transparent">
+      <form className="stretch mx-2 flex flex-row gap-3 last:mb-2 md:pt-2 md:last:mb-6 lg:mx-auto lg:max-w-3xl lg:pt-6">
+        <div className="relative flex h-full flex-1 md:flex-col">
+          <span className="order-last ml-1 flex justify-center gap-0 md:order-none md:m-auto md:mb-2 md:w-full md:gap-2">
+            {isSubmitting ? (
+              <button
+                onClick={handleStopGenerating}
+                className="input-panel-button btn btn-neutral flex justify-center gap-2 border-0 md:border"
+                type="button"
+              >
+                <StopGeneratingIcon />
+                <span className="hidden md:block">Stop generating</span>
+              </button>
+            ) : latestMessage && !latestMessage?.isCreatedByUser ? (
+              <button
+                onClick={handleRegenerate}
+                className="input-panel-button btn btn-neutral flex justify-center gap-2 border-0 md:border"
+                type="button"
+              >
+                <RegenerateIcon />
+                <span className="hidden md:block">Regenerate response</span>
+              </button>
+            ) : null}
+          </span>
+          <div
+            className={`relative flex flex-grow flex-col rounded-md border border-black/10 ${
+              disabled ? 'bg-gray-100' : 'bg-white'
+            } py-2 shadow-[0_0_10px_rgba(0,0,0,0.10)] dark:border-gray-900/50 ${
+              disabled ? 'dark:bg-gray-900' : 'dark:bg-gray-700'
+            } dark:text-white dark:shadow-[0_0_15px_rgba(0,0,0,0.10)] md:py-3 md:pl-4`}
+          >
+            <ModelMenu />
+            <TextareaAutosize
+              tabIndex="0"
+              autoFocus
+              ref={inputRef}
+              // style={{maxHeight: '200px', height: '24px', overflowY: 'hidden'}}
+              rows="1"
+              value={disabled || isNotAppendable ? '' : text}
+              onKeyUp={handleKeyUp}
+              onKeyDown={handleKeyDown}
+              onChange={changeHandler}
+              onCompositionStart={handleCompositionStart}
+              onCompositionEnd={handleCompositionEnd}
+              placeholder={
+                disabled
+                  ? 'Choose another model or customize GPT again'
+                  : isNotAppendable
+                  ? 'Edit your message or Regenerate.'
+                  : ''
+              }
+              disabled={disabled || isNotAppendable}
+              className="m-0 h-auto max-h-52 resize-none overflow-auto border-0 bg-transparent p-0 pl-12 pr-8 leading-6 placeholder:text-sm focus:outline-none focus:ring-0 focus-visible:ring-0 dark:bg-transparent md:pl-8"
+            />
+            <SubmitButton
+              submitMessage={submitMessage}
+              disabled={disabled || isNotAppendable}
+            />
+          </div>
+        </div>
+      </form>
+      <Footer />
+    </div>
+  );
+}

client/src/components/Messages/Embed.jsx

@@ -0,0 +1,35 @@
+import React, { useState } from 'react';
+import Clipboard from '../svg/Clipboard';
+import CheckMark from '../svg/CheckMark';
+
+export default function Embed({ children, language = '', code, matched }) {
+  const [buttonText, setButtonText] = useState('Copy code');
+  const isClicked = buttonText === 'Copy code';
+
+  const clickHandler = () => {
+    navigator.clipboard.writeText(code.trim());
+    setButtonText('Copied!');
+    setTimeout(() => {
+      setButtonText('Copy code');
+    }, 3000);
+  };
+
+  return (
+    <pre>
+      <div className="mb-4 rounded-md bg-black">
+        <div className="relative flex items-center rounded-tl-md rounded-tr-md bg-gray-800 px-4 py-2 font-sans text-xs text-gray-200">
+          <span className="">{language === 'javascript' && !matched ? '' : language}</span>
+          <button
+            className="ml-auto flex gap-2"
+            onClick={clickHandler}
+            disabled={!isClicked}
+          >
+            {isClicked ? <Clipboard /> : <CheckMark />}
+            {buttonText}
+          </button>
+        </div>
+        <div className="overflow-y-auto p-4">{children}</div>
+      </div>
+    </pre>
+  );
+}

client/src/components/Messages/Highlight.jsx

@@ -0,0 +1,18 @@
+import React, { useState, useEffect } from 'react';
+import hljs from 'highlight.js';
+import languages from '~/utils/languages';
+
+export default function Highlight({language, code}) {
+  const [highlightedCode, setHighlightedCode] = useState(code);
+  const lang = languages.has(language) ? language : 'shell';
+
+  useEffect(() => {
+    setHighlightedCode(hljs.highlight(code, { language: lang }).value);
+  }, [code, lang]);
+
+  return (
+    <pre>
+      <code className={`language-${lang}`} dangerouslySetInnerHTML={{__html: highlightedCode}}/>
+    </pre>
+  );
+}