diff options
| -rw-r--r-- | README.md | 17 | ||||
| -rw-r--r-- | docs/async_client.md | 92 | ||||
| -rw-r--r-- | docs/legacy.md (renamed from docs/legacy/legacy.md) | 0 | ||||
| -rw-r--r-- | docs/legacy/legacy_async_client.md | 380 | ||||
| -rw-r--r-- | etc/unittest/backend.py | 2 | ||||
| -rw-r--r-- | g4f/client/__init__.py | 71 |
6 files changed, 88 insertions, 474 deletions
@@ -72,12 +72,8 @@ Is your site on this repository and you want to take it down? Send an email to t - [Local Inference](docs/local.md) - [Configuration](#configuration) - [Full Documentation for Python API](#full-documentation-for-python-api) - - **New:** - - [Async Client API from G4F](docs/async_client.md) - - [Client API like the OpenAI Python library](docs/client.md) - - **Legacy** - - [Legacy API with python modules](docs/legacy/legacy.md) - - [Legacy AsyncClient API from G4F](docs/legacy/legacy_async_client.md) + - [Client API from G4F](docs/client.md) + - [AsyncClient API from G4F](docs/async_client.md) - [🚀 Providers and Models](docs/providers-and-models.md) - [🔗 Powered by gpt4free](#-powered-by-gpt4free) - [🤝 Contribute](#-contribute) @@ -123,7 +119,7 @@ To ensure the seamless operation of our application, please follow the instructi ### Installation Steps -1. **Download the Application**: Visit our [releases page](https://github.com/xtekky/gpt4free/releases/tag/0.3.1.7) and download the most recent version of the application, named `g4f.exe.zip`. +1. **Download the Application**: Visit our [releases page](https://github.com/xtekky/gpt4free/releases/tag/0.3.4.2) and download the most recent version of the application, named `g4f.exe.zip`. 2. **File Placement**: After downloading, locate the `.zip` file in your Downloads folder. Unpack it to a directory of your choice on your system, then execute the `g4f.exe` file to run the app. 3. **Open GUI**: The app starts a web server with the GUI. Open your favorite browser and navigate to `http://localhost:8080/chat/` to access the application interface. 4. **Firewall Configuration (Hotfix)**: Upon installation, it may be necessary to adjust your Windows Firewall settings to allow the application to operate correctly. To do this, access your Windows Firewall settings and allow the application. @@ -204,12 +200,11 @@ print(f"Generated image URL: {image_url}") #### **Full Documentation for Python API** - **New:** - - **Async Client API from G4F:** [/docs/async_client](docs/async_client.md) - - **Client API like the OpenAI Python library:** [/docs/client](docs/client.md) + - **Client API from G4F:** [/docs/client](docs/client.md) + - **AsyncClient API from G4F:** [/docs/async_client](docs/async_client.md) - **Legacy:** - - **Legacy API with python modules:** [/docs/legacy/legacy](docs/legacy/legacy.md) - - **Legacy AsyncClient API from G4F:** [/docs/async_client](docs/legacy/legacy_async_client.md) + - **Legacy API with python modules:** [/docs/legacy](docs/legacy.md) #### Web UI **To start the web interface, type the following codes in python:** diff --git a/docs/async_client.md b/docs/async_client.md index 7194c792..fe6f46ff 100644 --- a/docs/async_client.md +++ b/docs/async_client.md @@ -1,9 +1,10 @@ -# G4F - Async client API Guide -The G4F async client API is a powerful asynchronous interface for interacting with various AI models. This guide provides comprehensive information on how to use the API effectively, including setup, usage examples, best practices, and important considerations for optimal performance. + +# G4F - AsyncClient API Guide +The G4F AsyncClient API is a powerful asynchronous interface for interacting with various AI models. This guide provides comprehensive information on how to use the API effectively, including setup, usage examples, best practices, and important considerations for optimal performance. ## Compatibility Note -The G4F async client API is designed to be compatible with the OpenAI API, making it easy for developers familiar with OpenAI's interface to transition to G4F. +The G4F AsyncClient API is designed to be compatible with the OpenAI API, making it easy for developers familiar with OpenAI's interface to transition to G4F. ## Table of Contents - [Introduction](#introduction) @@ -26,7 +27,7 @@ The G4F async client API is designed to be compatible with the OpenAI API, makin ## Introduction -The G4F async client API is an asynchronous version of the standard G4F Client API. It offers the same functionality as the synchronous API but with improved performance due to its asynchronous nature. This guide will walk you through the key features and usage of the G4F async client API. +The G4F AsyncClient API is an asynchronous version of the standard G4F Client API. It offers the same functionality as the synchronous API but with improved performance due to its asynchronous nature. This guide will walk you through the key features and usage of the G4F AsyncClient API. ## Key Features @@ -39,13 +40,13 @@ The G4F async client API is an asynchronous version of the standard G4F Client A ## Getting Started -### Initializing the Client -**To use the G4F `Client`, create a new instance:** +### Initializing the AsyncClient +**To use the G4F `AsyncClient`, create a new instance:** ```python -from g4f.client import Client +from g4f.client import AsyncClient from g4f.Provider import OpenaiChat, Gemini -client = Client( +client = AsyncClient( provider=OpenaiChat, image_provider=Gemini, # Add other parameters as needed @@ -56,7 +57,7 @@ client = Client( ## Creating Chat Completions **Here’s an improved example of creating chat completions:** ```python -response = await async_client.chat.completions.create( +response = await client.chat.completions.create( model="gpt-4o-mini", messages=[ { @@ -77,9 +78,9 @@ You can adjust these parameters based on your specific needs. ### Configuration -**Configure the `Client` with additional settings:** +**Configure the `AsyncClient` with additional settings:** ```python -client = Client( +client = AsyncClient( api_key="your_api_key_here", proxies="http://user:pass@host", # Add other parameters as needed @@ -93,12 +94,12 @@ client = Client( **Generate text completions using the ChatCompletions endpoint:** ```python import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() + client = AsyncClient() - response = await client.chat.completions.async_create( + response = await client.chat.completions.create( model="gpt-4o-mini", messages=[ { @@ -119,12 +120,12 @@ asyncio.run(main()) **Process responses incrementally as they are generated:** ```python import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() - - stream = await client.chat.completions.async_create( + client = AsyncClient() + + stream = client.chat.completions.create( model="gpt-4", messages=[ { @@ -136,7 +137,7 @@ async def main(): ) async for chunk in stream: - if chunk.choices[0].delta.content: + if chunk.choices and chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="") asyncio.run(main()) @@ -150,14 +151,14 @@ asyncio.run(main()) import g4f import requests import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() + client = AsyncClient() image = requests.get("https://raw.githubusercontent.com/xtekky/gpt4free/refs/heads/main/docs/cat.jpeg", stream=True).raw - response = await client.chat.completions.async_create( + response = await client.chat.completions.create( model=g4f.models.default, provider=g4f.Provider.Bing, messages=[ @@ -180,12 +181,12 @@ asyncio.run(main()) **Generate images using a specified prompt:** ```python import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() + client = AsyncClient() - response = await client.images.async_generate( + response = await client.images.generate( prompt="a white siamese cat", model="flux" ) @@ -201,12 +202,12 @@ asyncio.run(main()) #### Base64 Response Format ```python import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() + client = AsyncClient() - response = await client.images.async_generate( + response = await client.images.generate( prompt="a white siamese cat", model="flux", response_format="b64_json" @@ -224,13 +225,13 @@ asyncio.run(main()) **Execute multiple tasks concurrently:** ```python import asyncio -from g4f.client import Client +from g4f.client import AsyncClient async def main(): - client = Client() + client = AsyncClient() - task1 = client.chat.completions.async_create( - model="gpt-4o-mini", + task1 = client.chat.completions.create( + model=None, messages=[ { "role": "user", @@ -239,18 +240,21 @@ async def main(): ] ) - task2 = client.images.async_generate( + task2 = client.images.generate( model="flux", prompt="a white siamese cat" ) - chat_response, image_response = await asyncio.gather(task1, task2) - - print("Chat Response:") - print(chat_response.choices[0].message.content) - - print("Image Response:") - print(image_response.data[0].url) + try: + chat_response, image_response = await asyncio.gather(task1, task2) + + print("Chat Response:") + print(chat_response.choices[0].message.content) + + print("\nImage Response:") + print(image_response.data[0].url) + except Exception as e: + print(f"An error occurred: {e}") asyncio.run(main()) ``` @@ -286,7 +290,7 @@ client = AsyncClient(provider=g4f.Provider.OpenaiChat) # or -response = await client.chat.completions.async_create( +response = await client.chat.completions.create( model="gpt-4", provider=g4f.Provider.Bing, messages=[ @@ -306,7 +310,7 @@ Implementing proper error handling and following best practices is crucial when 1. **Use try-except blocks to catch and handle exceptions:** ```python try: - response = await client.chat.completions.async_create( + response = await client.chat.completions.create( model="gpt-4o-mini", messages=[ { @@ -368,7 +372,7 @@ logger = logging.getLogger(__name__) async def make_api_call(): try: - response = await client.chat.completions.async_create(...) + response = await client.chat.completions.create(...) logger.info(f"API call successful. Tokens used: {response.usage.total_tokens}") except Exception as e: logger.error(f"API call failed: {e}") @@ -387,7 +391,7 @@ def get_cached_response(query): ``` ## Conclusion -The G4F async client API provides a powerful and flexible way to interact with various AI models asynchronously. By leveraging its features and following best practices, you can build efficient and responsive applications that harness the power of AI for text generation, image analysis, and image creation. +The G4F AsyncClient API provides a powerful and flexible way to interact with various AI models asynchronously. By leveraging its features and following best practices, you can build efficient and responsive applications that harness the power of AI for text generation, image analysis, and image creation. Remember to handle errors gracefully, implement rate limiting, and monitor your API usage to ensure optimal performance and reliability in your applications. diff --git a/docs/legacy/legacy.md b/docs/legacy.md index d5cd5a36..d5cd5a36 100644 --- a/docs/legacy/legacy.md +++ b/docs/legacy.md diff --git a/docs/legacy/legacy_async_client.md b/docs/legacy/legacy_async_client.md deleted file mode 100644 index 5ddc2671..00000000 --- a/docs/legacy/legacy_async_client.md +++ /dev/null @@ -1,380 +0,0 @@ -# G4F - Legacy AsyncClient API Guide - -**IMPORTANT: This guide refers to the old implementation of AsyncClient. The new version of G4F now supports both synchronous and asynchronous operations through a unified interface. Please refer to the [new AsyncClient documentation](https://github.com/xtekky/gpt4free/blob/main/docs/async_client.md) for the latest information.** - -This guide provides comprehensive information on how to use the G4F AsyncClient API, including setup, usage examples, best practices, and important considerations for optimal performance. - -## Compatibility Note -The G4F AsyncClient API is designed to be compatible with the OpenAI API, making it easy for developers familiar with OpenAI's interface to transition to G4F. However, please note that this is the old version, and you should migrate to the new implementation for better support and features. - -## Table of Contents - - [Introduction](#introduction) - - [Key Features](#key-features) - - [Getting Started](#getting-started) - - [Initializing the Client](#initializing-the-client) - - [Creating Chat Completions](#creating-chat-completions) - - [Configuration](#configuration) - - [Usage Examples](#usage-examples) - - [Text Completions](#text-completions) - - [Streaming Completions](#streaming-completions) - - [Using a Vision Model](#using-a-vision-model) - - [Image Generation](#image-generation) - - [Concurrent Tasks](#concurrent-tasks-with-asynciogather) - - [Available Models and Providers](#available-models-and-providers) - - [Error Handling and Best Practices](#error-handling-and-best-practices) - - [Rate Limiting and API Usage](#rate-limiting-and-api-usage) - - [Conclusion](#conclusion) - -## Introduction -This is the old version: The G4F AsyncClient API is an asynchronous version of the standard G4F Client API. It offers the same functionality as the synchronous API but with improved performance due to its asynchronous nature. This guide will walk you through the key features and usage of the G4F AsyncClient API. - -## Key Features - - **Custom Providers**: Use custom providers for enhanced flexibility. - - **ChatCompletion Interface**: Interact with chat models through the ChatCompletion class. - - **Streaming Responses**: Get responses iteratively as they are received. - - **Non-Streaming Responses**: Generate complete responses in a single call. - - **Image Generation and Vision Models**: Support for image-related tasks. - -## Getting Started -**To ignore DeprecationWarnings related to the AsyncClient, you can use the following code:*** -```python -import warnings - -# Ignore DeprecationWarning for AsyncClient -warnings.filterwarnings("ignore", category=DeprecationWarning, module="g4f.client") -``` - -### Initializing the Client -**To use the G4F `Client`, create a new instance:** -```python -from g4f.client import AsyncClient -from g4f.Provider import OpenaiChat, Gemini - -client = AsyncClient( - provider=OpenaiChat, - image_provider=Gemini, - # Add other parameters as needed -) -``` - -## Creating Chat Completions -**Here's an improved example of creating chat completions:** -```python -response = await async_client.chat.completions.create( - model="gpt-3.5-turbo", - messages=[ - { - "role": "user", - "content": "Say this is a test" - } - ] - # Add other parameters as needed -) -``` - -**This example:** - - Asks a specific question `Say this is a test` - - Configures various parameters like temperature and max_tokens for more control over the output - - Disables streaming for a complete response - -You can adjust these parameters based on your specific needs. - -### Configuration -**Configure the `AsyncClient` with additional settings:** -```python -client = Client( - api_key="your_api_key_here", - proxies="http://user:pass@host", - # Add other parameters as needed -) -``` - -## Usage Examples -### Text Completions -**Generate text completions using the ChatCompletions endpoint:** -```python -import asyncio -import warnings -from g4f.client import AsyncClient - -# Ігноруємо DeprecationWarning -warnings.filterwarnings("ignore", category=DeprecationWarning) - -async def main(): - client = AsyncClient() - - response = await client.chat.completions.async_create( - model="gpt-3.5-turbo", - messages=[ - { - "role": "user", - "content": "Say this is a test" - } - ] - ) - - print(response.choices[0].message.content) - -asyncio.run(main()) -``` - -### Streaming Completions -**Process responses incrementally as they are generated:** -```python -import asyncio -from g4f.client import AsyncClient - -async def main(): - client = AsyncClient() - - stream = await client.chat.completions.async_create( - model="gpt-4", - messages=[ - { - "role": "user", - "content": "Say this is a test" - } - ], - stream=True, - ) - - async for chunk in stream: - if chunk.choices[0].delta.content: - print(chunk.choices[0].delta.content, end="") - -asyncio.run(main()) -``` - -### Using a Vision Model -**Analyze an image and generate a description:** -```python -import g4f -import requests -import asyncio -from g4f.client import AsyncClient - -async def main(): - client = AsyncClient() - - image = requests.get("https://raw.githubusercontent.com/xtekky/gpt4free/refs/heads/main/docs/cat.jpeg", stream=True).raw - - response = await client.chat.completions.async_create( - model=g4f.models.default, - provider=g4f.Provider.Bing, - messages=[ - { - "role": "user", - "content": "What's in this image?" - } - ], - image=image - ) - - print(response.choices[0].message.content) - -asyncio.run(main()) -``` - -### Image Generation -**Generate images using a specified prompt:** -```python -import asyncio -from g4f.client import AsyncClient - -async def main(): - client = AsyncClient() - - response = await client.images.async_generate( - prompt="a white siamese cat", - model="flux" - ) - - image_url = response.data[0].url - print(f"Generated image URL: {image_url}") - -asyncio.run(main()) -``` - -#### Base64 Response Format -```python -import asyncio -from g4f.client import AsyncClient - -async def main(): - client = AsyncClient() - - response = await client.images.async_generate( - prompt="a white siamese cat", - model="flux", - response_format="b64_json" - ) - - base64_text = response.data[0].b64_json - print(base64_text) - -asyncio.run(main()) -``` - -### Concurrent Tasks with asyncio.gather -**Execute multiple tasks concurrently:** -```python -import asyncio -import warnings -from g4f.client import AsyncClient - -# Ignore DeprecationWarning for AsyncClient -warnings.filterwarnings("ignore", category=DeprecationWarning, module="g4f.client") - -async def main(): - client = AsyncClient() - - task1 = client.chat.completions.async_create( - model="gpt-3.5-turbo", - messages=[ - { - "role": "user", - "content": "Say this is a test" - } - ] - ) - - task2 = client.images.async_generate( - model="flux", - prompt="a white siamese cat" - ) - - chat_response, image_response = await asyncio.gather(task1, task2) - - print("Chat Response:") - print(chat_response.choices[0].message.content) - - print("Image Response:") - print(image_response.data[0].url) - -asyncio.run(main()) -``` - -## Available Models and Providers -This is the old version: The G4F AsyncClient supports a wide range of AI models and providers, allowing you to choose the best option for your specific use case. -**Here's a brief overview of the available models and providers:** - -### Models - - GPT-3.5-Turbo - - GPT-4 - - DALL-E 3 - - Gemini - - Claude (Anthropic) - - And more... - -### Providers - - OpenAI - - Google (for Gemini) - - Anthropic - - Bing - - Custom providers - -**To use a specific model or provider, specify it when creating the client or in the API call:** -```python -client = AsyncClient(provider=g4f.Provider.OpenaiChat) - -# or - -response = await client.chat.completions.async_create( - model="gpt-4", - provider=g4f.Provider.Bing, - messages=[ - { - "role": "user", - "content": "Hello, world!" - } - ] -) -``` - -## Error Handling and Best Practices -Implementing proper error handling and following best practices is crucial when working with the G4F AsyncClient API. This ensures your application remains robust and can gracefully handle various scenarios. **Here are some key practices to follow:** - -1. **Use try-except blocks to catch and handle exceptions:** -```python -try: - response = await client.chat.completions.async_create( - model="gpt-3.5-turbo", - messages=[ - { - "role": "user", - "content": "Hello, world!" - } - ] - ) -except Exception as e: - print(f"An error occurred: {e}") -``` - -2. **Check the response status and handle different scenarios:** -```python -if response.choices: - print(response.choices[0].message.content) -else: - print("No response generated") -``` - -3. **Implement retries for transient errors:** -```python -import asyncio -from tenacity import retry, stop_after_attempt, wait_exponential - -@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10)) -async def make_api_call(): - # Your API call here - pass -``` - -## Rate Limiting and API Usage -This is the old version: When working with the G4F AsyncClient API, it's important to implement rate limiting and monitor your API usage. This helps ensure fair usage, prevents overloading the service, and optimizes your application's performance. **Here are some key strategies to consider:** - -1. **Implement rate limiting in your application:** -```python -import asyncio -from aiolimiter import AsyncLimiter - -rate_limit = AsyncLimiter(max_rate=10, time_period=1) # 10 requests per second - -async def make_api_call(): - async with rate_limit: - # Your API call here - pass -``` - -2. **Monitor your API usage and implement logging:** -```python -import logging - -logging.basicConfig(level=logging.INFO) -logger = logging.getLogger(__name__) - -async def make_api_call(): - try: - response = await client.chat.completions.async_create(...) - logger.info(f"API call successful. Tokens used: {response.usage.total_tokens}") - except Exception as e: - logger.error(f"API call failed: {e}") -``` - -3. **Use caching to reduce API calls for repeated queries:** -```python -from functools import lru_cache - -@lru_cache(maxsize=100) -def get_cached_response(query): - # Your API call here - pass -``` - -## Conclusion -This is the old version: The G4F AsyncClient API provides a powerful and flexible way to interact with various AI models asynchronously. By leveraging its features and following best practices, you can build efficient and responsive applications that harness the power of AI for text generation, image analysis, and image creation. - -Remember to handle errors gracefully, implement rate limiting, and monitor your API usage to ensure optimal performance and reliability in your applications. - ---- - -[Return to Home](/) diff --git a/etc/unittest/backend.py b/etc/unittest/backend.py index a2999c5c..e781de8a 100644 --- a/etc/unittest/backend.py +++ b/etc/unittest/backend.py @@ -46,4 +46,4 @@ class TestBackendApi(unittest.TestCase): self.skipTest(e) except MissingRequirementsError: self.skipTest("search is not installed") - self.assertEqual(5, len(result))
\ No newline at end of file + self.assertEqual(4, len(result)) diff --git a/g4f/client/__init__.py b/g4f/client/__init__.py index 6f679e4a..1f3cdab1 100644 --- a/g4f/client/__init__.py +++ b/g4f/client/__init__.py @@ -261,7 +261,7 @@ class Images: if isinstance(provider_handler, IterListProvider): if provider_handler.providers: - provider_handler = provider.providers[0] + provider_handler = provider_handler.providers[0] else: raise ValueError(f"IterListProvider for model {model} has no providers") @@ -287,44 +287,39 @@ class Images: raise NoImageResponseError(f"Unexpected response type: {type(response)}") async def _process_image_response(self, response: ImageResponse, response_format: str, proxy: str = None, model: str = None, provider: str = None) -> ImagesResponse: - async def process_image_item(session: aiohttp.ClientSession, image_data: str): - if image_data.startswith('http://') or image_data.startswith('https://'): - if response_format == "url": - return Image(url=image_data, revised_prompt=response.alt) - elif response_format == "b64_json": - # Fetch the image data and convert it to base64 - image_content = await self._fetch_image(session, image_data) - file_name = self._save_image(image_data_bytes) - b64_json = base64.b64encode(image_content).decode('utf-8') - return Image(b64_json=b64_json, url=file_name, revised_prompt=response.alt) - else: - # Assume image_data is base64 data or binary - if response_format == "url": - if image_data.startswith('data:image'): - # Remove the data URL scheme and get the base64 data - base64_data = image_data.split(',', 1)[-1] - else: - base64_data = image_data - # Decode the base64 data - image_data_bytes = base64.b64decode(base64_data) - # Convert bytes to an image + async def process_image_item(session: aiohttp.ClientSession, image_data: str): + image_data_bytes = None + if image_data.startswith("http://") or image_data.startswith("https://"): + if response_format == "url": + return Image(url=image_data, revised_prompt=response.alt) + elif response_format == "b64_json": + # Fetch the image data and convert it to base64 + image_data_bytes = await self._fetch_image(session, image_data) + b64_json = base64.b64encode(image_data_bytes).decode("utf-8") + return Image(b64_json=b64_json, url=image_data, revised_prompt=response.alt) + else: + # Assume image_data is base64 data or binary + if response_format == "url": + if image_data.startswith("data:image"): + # Remove the data URL scheme and get the base64 data + base64_data = image_data.split(",", 1)[-1] + else: + base64_data = image_data + # Decode the base64 data + image_data_bytes = base64.b64decode(base64_data) + if image_data_bytes: file_name = self._save_image(image_data_bytes) return Image(url=file_name, revised_prompt=response.alt) - elif response_format == "b64_json": - if isinstance(image_data, bytes): - file_name = self._save_image(image_data_bytes) - b64_json = base64.b64encode(image_data).decode('utf-8') - else: - b64_json = image_data # If already base64-encoded string - return Image(b64_json=b64_json, url=file_name, revised_prompt=response.alt) - - last_provider = get_last_provider(True) - async with aiohttp.ClientSession(cookies=response.get("cookies"), connector=get_connector(proxy=proxy)) as session: - return ImagesResponse( - await asyncio.gather(*[process_image_item(session, image_data) for image_data in response.get_list()]), - model=last_provider.get("model") if model is None else model, - provider=last_provider.get("name") if provider is None else provider - ) + else: + raise ValueError("Unable to process image data") + + last_provider = get_last_provider(True) + async with aiohttp.ClientSession(cookies=response.get("cookies"), connector=get_connector(proxy=proxy)) as session: + return ImagesResponse( + await asyncio.gather(*[process_image_item(session, image_data) for image_data in response.get_list()]), + model=last_provider.get("model") if model is None else model, + provider=last_provider.get("name") if provider is None else provider + ) async def _fetch_image(self, session: aiohttp.ClientSession, url: str) -> bytes: # Asynchronously fetch image data from the URL @@ -464,4 +459,4 @@ class AsyncImages(Images): async def create_variation(self, image: Union[str, bytes], model: str = None, provider: ProviderType = None, response_format: str = "url", **kwargs) -> ImagesResponse: return await self.async_create_variation( image, model, provider, response_format, **kwargs - )
\ No newline at end of file + ) |