### Install and Run WebAI-to-API Server

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

This sequence of commands guides you through cloning the WebAI-to-API repository, installing its dependencies using Poetry, copying and configuring the example configuration file, and finally running the FastAPI server.

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

```bash
poetry install
```

```bash
cp config.conf.example config.conf
```

```bash
poetry run python src/run.py
```

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

### Stop Docker Server using Make

Source: https://github.com/amm1rr/webai-to-api/blob/master/Docker.md

This `make` command provides a simple way to gracefully stop all running Docker containers associated with the project. It ensures that services are shut down cleanly, preventing resource leaks or data corruption.

```bash
make stop
```

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

### Run Docker Server using Make

Source: https://github.com/amm1rr/webai-to-api/blob/master/Docker.md

The `make up` command initiates the Dockerized server. In development mode, it runs in the foreground with hot-reloading enabled. For production, it automatically runs in detached mode with multiple workers, optimizing for performance and stability.

```bash
make up
```

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

### Build Docker Images using Make

Source: https://github.com/amm1rr/webai-to-api/blob/master/Docker.md

These `make` commands streamline the process of building the project's Docker images. `make build` performs a standard build, while `make build-fresh` forces a clean build by ignoring the cache, useful for troubleshooting or ensuring the latest dependencies.

```bash
make build         # Regular build
make build-fresh   # Force clean build (no cache)
```

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

### Example API Response for Chat Completions

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

This JSON object illustrates the expected response from the `/v1/chat/completions` endpoint, providing the assistant's reply, model information, and usage statistics in an OpenAI-compatible format. It includes the generated message, finish reason, and token usage.

```json
{
  "id": "chatcmpl-12345",
  "object": "chat.completion",
  "created": 1693417200,
  "model": "gemini-2.0-flash",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hi there!"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}
```

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

### Configure Docker Environment Variables

Source: https://github.com/amm1rr/webai-to-api/blob/master/Docker.md

This snippet demonstrates how to set the `ENVIRONMENT` variable within a `.env` file. This variable is crucial for determining the operational mode of the Dockerized application, switching between 'development' (with auto-reload and debug logs) and 'production' (with multi-worker and detached execution).

```env
# Set the environment mode
ENVIRONMENT=development
```

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

### Example API Request Payload for Chat Completions

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

This JSON object represents a typical request body for the `/v1/chat/completions` endpoint, specifying the LLM model to use and the user's message in an OpenAI-compatible format. This payload is used to initiate a chat completion request.

```json
{
  "model": "gemini-2.0-flash",
  "messages": [{ "role": "user", "content": "Hello!" }]
}
```

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

### WebAI-to-API Sample Configuration File

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

Provides a sample `config.conf` file demonstrating how to configure the WebAI-to-API service. It includes settings for default AI services, specific model names, cookie values for authentication, and enabling/disabling AI providers.

```INI
[AI]
# Default AI service.
default_ai = gemini

# Default model for Gemini.
default_model_gemini = gemini-2.0-flash

# Gemini cookies (leave empty to use browser_cookies3 for automatic authentication).
gemini_cookie_1psid =
gemini_cookie_1psidts =

[EnabledAI]
# Enable or disable AI services.
gemini = true

[Browser]
# Default browser options: firefox, brave, chrome, edge, safari.
name = firefox
```

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

### WebAI-to-API Project Directory Structure

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

Outlines the modular project structure of WebAI-to-API, detailing the organization of application components, API endpoints, services, utilities, models, schemas, and configuration files for clarity and maintainability.

```plaintext
src/
├── app/
│   ├── __init__.py
│   ├── main.py                # FastAPI app creation, configuration, and lifespan management.
│   ├── config.py              # Global configuration loader/updater.
│   ├── logger.py              # Centralized logging configuration.
│   ├── endpoints/             # API endpoint routers.
│   │   ├── __init__.py
│   │   ├── gemini.py          # Endpoints for Gemini (e.g., /gemini, /gemini-chat).
│   │   └── chat.py            # Endpoints for translation and OpenAI-compatible requests.
│   ├── services/              # Business logic and service wrappers.
│   │   ├── __init__.py
│   │   ├── gemini_client.py   # Gemini client initialization, content generation, and cleanup.
│   │   └── session_manager.py # Session management for chat and translation.
│   └── utils/                 # Helper functions.
│       ├── __init__.py
│       └── browser.py         # Browser-based cookie retrieval.
├── models/                    # Models and wrappers (e.g., MyGeminiClient).
│   └── gemini.py
├── schemas/                   # Pydantic schemas for request/response validation.
│   └── request.py
├── config.conf                # Application configuration file.
└── run.py                     # Entry point to run the server.
```

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

### WebAI-to-API Key Configuration Options

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

Describes key configuration options for the WebAI-to-API service, including the default AI service for chat completions, the browser used for cookie-based authentication, and flags to enable or disable specific AI services like Gemini.

```APIDOC
Section: [AI]
  Option: default_ai
  Description: Default service for /v1/chat/completions
  Example Value: `gemini`

Section: [Browser]
  Option: name
  Description: Browser for cookie-based authentication
  Example Value: `firefox`

Section: [EnabledAI]
  Option: gemini
  Description: Enable/disable Gemini service
  Example Value: `true`
```

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

### gpt4free Server Endpoints

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

These endpoints are powered by the `gpt4free` library and follow the OpenAI-compatible structure, offering broader access to various LLMs. For detailed usage and advanced customization, refer to the official gpt4free documentation.

```APIDOC
POST /v1
  - Description: General endpoint for gpt4free services, typically used for various LLM interactions.
  - Parameters: Refer to gpt4free documentation for specific request body details.
  - Returns: LLM response based on the request.

POST /v1/chat/completions
  - Description: OpenAI-compatible chat completions endpoint, leveraging the gpt4free library to access multiple LLMs.
  - Parameters: Request body conforming to OpenAI chat completion specification (e.g., {"model": "string", "messages": [{"role": "string", "content": "string"}]}).
  - Returns: Response conforming to OpenAI chat completion specification.
```

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

### WebAI-to-API Server Endpoints

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

This section details the API endpoints provided by the WebAI-to-API server, including their purpose and behavior regarding session management. These endpoints facilitate interaction with browser-based LLMs like Gemini.

```APIDOC
GET /gemini
  - Description: Initiates a new conversation with the LLM. Each request creates a fresh session, making it suitable for stateless interactions.
  - Parameters: None
  - Returns: LLM response for a new conversation.

POST /gemini-chat
  - Description: Continues a persistent conversation with the LLM without starting a new session. Ideal for use cases that require context retention between messages.
  - Parameters: Request body containing chat messages.
  - Returns: LLM response within the ongoing session.

POST /translate
  - Description: Designed for quick integration with the 'Translate It!' browser extension. Functionally identical to `/gemini-chat`, meaning it maintains session context across requests.
  - Parameters: Request body containing text to translate or chat messages.
  - Returns: Translated text or LLM response within the ongoing session.

POST /v1/chat/completions
  - Description: A minimalistic implementation of the OpenAI-compatible endpoint. Built for simplicity and ease of integration with clients that expect the OpenAI API format.
  - Parameters: Request body conforming to OpenAI chat completion specification (e.g., {"model": "string", "messages": [{"role": "string", "content": "string"}]}).
  - Returns: Response conforming to OpenAI chat completion specification.
```

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

### WebAI-to-API REST API Endpoints

Source: https://github.com/amm1rr/webai-to-api/blob/master/README.md

Documents the available REST API endpoints for the WebAI-to-API service, including routes for chat completions, image generation, audio processing, model management, and file operations. These endpoints provide an API layer over various AI providers.

```APIDOC
GET  /
  # Health check

GET  /v1
  # Version info

GET  /v1/models
  # List all available models

GET  /api/{provider}/models
  # List models from a specific provider

GET  /v1/models/{model_name}
  # Get details of a specific model

POST /v1/chat/completions
  # Chat with default configuration

POST /api/{provider}/chat/completions

POST /api/{provider}/{conversation_id}/chat/completions

POST /v1/responses
  # General response endpoint

POST /api/{provider}/responses

POST /api/{provider}/images/generations

POST /v1/images/generations

POST /v1/images/generate
  # Generate images using selected provider

POST /v1/media/generate
  # Media generation (audio/video/etc.)

GET  /v1/providers
  # List all providers

GET  /v1/providers/{provider}
  # Get specific provider info

POST /api/{path_provider}/audio/transcriptions

POST /v1/audio/transcriptions
  # Audio-to-text

POST /api/markitdown
  # Markdown rendering

POST /api/{path_provider}/audio/speech

POST /v1/audio/speech
  # Text-to-speech

POST /v1/upload_cookies
  # Upload session cookies (browser-based auth)

GET  /v1/files/{bucket_id}
  # Get uploaded file from bucket

POST /v1/files/{bucket_id}
  # Upload file to bucket

GET  /v1/synthesize/{provider}
  # Audio synthesis

POST /json/{filename}
  # Submit structured JSON data

GET  /media/{filename}
  # Retrieve media

GET  /images/{filename}
  # Retrieve images
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.