NOTE: This is a research project. Please do not use it commercially and use it responsibly.

WebAI to API

This project implements a web API that offers a unified interface to ChatGPT, Google Bard, and Claude.

Key Features

• Unified API: Single integration to query ChatGPT, Bard, and Claude. No juggling multiple APIs.

• Conversational interface: Text completion, QA, discussions. Put advanced AI to work immediately.

• Self-hosted: Python/FastAPI enables flexibility to run anywhere. Not locked into proprietary platforms.

• Streaming support: Real-time responses from ChatGPT and Bard. Claude streaming coming soon.

• Lightweight and scalable: Built with FastAPI for high performance.

Status

✅ Google Bard Web to API integration available now.

✅ Claude-2 Web to API integration is also fully implemented and available.

✅ ChatGPT Web to API integration is fully complete and available now.

✅ ChatGPT to Claude, The new adapter connects the ChatGPT API to Claude. Developers can now build apps using the ChatGPT API to get Claude's AI responses.

🔜 ChatGPT to Bard, Get ready for next chapter

This repository is up-to-date.
Please don't forget to give a Star ⭐

Prerequisites

Python version >= 3.10

Before using the APIs, sign up for free accounts to get access credentials if you don't already have them:

• ChatGPT: https://openai.com/api/
• Google Bard: https://bard.google.com/
• Claude: https://claude.ai/

Then, add your token(s) to the Config.conf file. (see Configuration section).

Note: Claude and Bard offer Auto Login options - you can either log in through your browser and skip this step.

Installation

Step 1. Clone Repository

git clone https://github.com/Amm1rr/WebAI-to-API.git && cd WebAI-to-API

python -m venv .venv

source .venv/bin/activate  # Linux/macOS
.venv\Scripts\activate     # Windows


pip install -r requirements.txt

Step 2. Start Web Server

Navigate into the src directory, and run the web server:

cd src/

python main.py

Now the API documentation should be available at the following address:

http://127.0.0.1:8000/docs

Available Endpoints:

#---------- Google Bard

http://127.0.0.1:8000/bard


#---------- Claude

http://127.0.0.1:8000/claude


#---------- ChatGPT

http://127.0.0.1:8000/chatgpt


#---------- OpenAI ChatGPT JSON Response

http://127.0.0.1:8000/v1/chat/completions


#---------- Claude -> ChatGPT JSON Response

http://127.0.0.1:8000/claude/v1/chat/completions

Input / Output

# Input:
_____

    {
      "message": "Hi, Who are you?",
      "stream": true
    }


--------------------


# Output:
_____

    {
      I am a Chatbot assistant :)
    }


--------------------


# OpenAI Response Output:
_____

# Streaming
  {
    "id": "chatcmpl-123",
    "object": "chat.completion.chunk",
    "created": 1677652288,
    "model": "gpt-3.5-turbo",
    "choices": [{
      "index": 0,
      "delta": {
        "content": "Hello",
      },
      "finish_reason": "stop"
    }]
  }


# Not Streaming
  {
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "gpt-3.5-turbo",
    "choices": [{
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?",
      },
      "finish_reason": "stop"
    }]
  }

Example

Once you have launched the web server using src\python main.py:

Note: The first argument to run the example determines whether to return streaming or not.

cd examples/


python example_claude.py false
python example_claude.py true

python example_bard.py false
python example_bard.py true

python example_chatgpt1.py false
python example_chatgpt1.py true

python example_chatgpt2.py false
python example_chatgpt2.py true

or try Claude with cURL

run this cURL command in a terminal window:

curl -X 'POST' \
  'http://localhost:8000/claude' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "message": "who are you?",
  "stream": false
}'

Note: The session_id is configured in the Config.conf file. If you send this variable empty, it will use the Config.conf

Usage

How to Find Your Tokens

Note: Claude and Bard offer two authentication options - you can either log in through your browser and skip this step, or you can follow the instructions below to configure the authentication.

Important: "The auto login by browser issue is caused by using multiple accounts or browser profiles. It will take some time to fully resolve. A future update will address it. For now, if you have problems logging in with your browsers, try logging in with just one browser or manually copy sessions and cookies as a workaround, as described in the instructions below."

First you need to add your tokens to the Config.conf file (see Configuration section).

Configuration

How to Find Your Tokens

• Google Bard
• Claude
• ChatGPT

Note: Claude and Bard present Auto Login options - logging in through your browser or configuring Claude and Bard using the provided config file.

Config File Path:

• WebAI-to-API\src\Config.conf

# Case-Sensative

[Claude]
COOKIE=[YOURS]

[Bard]
SESSION_ID=[YOURS]
SESSION_IDTS=[YOURS]
SESSION_IDCC=[YOURS]

[ChatGPT]
ACCESS_TOKEN=[YOURS]

Sources

Google Bard API | revChatGPT

Licensing

This project is licensed under the MIT License. Feel free to use it however you like.