g4f v0.4.6.0

Release Notes

We're excited to announce the release of g4f 0.4.6.0! This update brings several new features, improvements, and bug fixes aimed at enhancing both functionality and user experience. Below is a summary of the key changes:

---

New Features

• Vision Models for HuggingFace Provider
  Expanded the HuggingFace provider to support vision models, opening up advanced image processing capabilities alongside traditional text models.
  [github.com]

• Premium Model Support in Blackbox Provider
  Introduced premium model support with enhanced validation in the Blackbox provider. This improvement ensures a smoother experience with robust premium authentication workflows.
  [github.com]

• Enhanced Unicode Image Handling
  Improved image processing in the copy_images module by adding better support for Unicode. This change enhances compatibility when dealing with files containing special characters.
  [github.com]

• Improved Mobile Interface
  Upgraded the client interface with enhanced mobile responsiveness and refined sidebar interactions, ensuring a more seamless user experience on mobile devices.
  [github.com]

---

Improvements and Bug Fixes

• Demo Mode Stability
  Resolved issues that were impacting demo mode functionality, resulting in a more stable and reliable demonstration environment.
  [github.com]

• API Endpoint Corrections
  Fixed provider-specific API endpoint errors to guarantee smoother data exchange and better overall connectivity with various services.
  [github.com]

• CablyAI Provider Refactor
  Reorganized the CablyAI provider by moving it into a dedicated needs_auth directory. This refactor clarifies its authentication requirements and simplifies future maintenance.
  [github.com]

• PollinationsAI Alias Cleanup
  Removed duplicate model aliases in the PollinationsAI provider to prevent conflicts and ensure accurate model selection during runtime.
  [github.com]

• Pipeline Tag Optimization for HuggingFace API
  Implemented caching for the pipeline tag and corrected its checking mechanism. These changes optimize performance by reducing redundant API calls and ensuring tag accuracy.
  [github.com]

• CLI and Initialization Enhancements
  Updated the command-line interface and initialization routines, streamlining user interactions and improving overall stability.
  [github.com]

---

Miscellaneous

• General Codebase Improvements
  Additional minor fixes and refactors have been merged into the codebase, enhancing code quality and laying the groundwork for future updates.
  [github.com]

---

We thank all the contributors for their hard work and valuable feedback. Enjoy the new features and improvements in g4f 0.4.6.0!
For more details, please check the full commit comparison.

New Contributors

• @mikebilly made their first contribution in #2706

g4f v0.4.5.5

Release Notes

New Features

• Introduced zerogpu_uuid: A new feature added to the demo, allowing for better identification and tracking in GPU-less environments.
• FluxDev Integration: The G4F provider now supports FluxDev, enhancing the variety of models available for users.

Improvements

• Enhanced Copy Images API: Improvements made to the Copy Images API for better performance and user experience.
• Updated Webmanifest: The webmanifest has been revised to include the latest features and optimizations.

Bug Fixes

• Resolved "Show New Window" Button Issue: Fixed a bug that prevented the "Show New Window" button from functioning correctly.
• Exception Handling in Generate Function: Added checks to handle exceptions in the generate function, improving overall stability.

Commits Overview

• Feb 5, 2025:

  • Added zerogpu_uuid to demo.
  • Implemented exception checks in the generate function.

• Feb 6, 2025:

  • Integrated FluxDev into the G4F provider.
  • Updated webmanifest and added missing imports.

• Feb 7, 2025:

  • Fixed the "Show New Window" button functionality.
  • Merged pull request #2688 and added new models while enhancing provider functionality.

What's Changed

• Add zerogpu_uuid to demo by @hlohaus in #2688
• Adding New Models and Enhancing Provider Functionality by @kqlio67 in #2689

For a complete comparison of changes, please refer to the commit history here [github.com].

g4f v0.4.5.4

Key Changes

• Updated Documentation
  The README has been refreshed with updated instructions and details to better guide users through setup and usage.
  Source: [github.com]

• New G4F Provider Added
  A new G4F provider has been integrated, expanding the available service options for users. This enhancement aims to improve overall compatibility and access to different AI models.
  Source: [github.com]

• Removal of Login URL from Error Messages
  To avoid user confusion and streamline error handling, the login URL has been removed from error messages.
  Source: [github.com]

• Model List Update and CablyAI Fixes
  The list of supported models has been updated. Additionally, issues with the model list display in the CablyAI integration have been fixed, ensuring more accurate model selection and improved reliability.
  Source: [github.com]

---

For More Information

For a detailed comparison of changes between version 0.4.5.3 and the current main branch, please check out the full diff:
[github.com]

These release notes compile the essential updates and improvements made in this version. We thank all contributors and community members for their valuable input and ongoing support.

Happy coding!

g4f v0.4.5.3

What's Changed

• Space by @hlohaus in #2684
• refactor: use dependency injection for RequestConfig by @sobelmangentz in #2683

New Contributors

• @sobelmangentz made their first contribution in #2683

Full Changelog: 0.4.5.2...0.4.5.3

g4f v0.4.5.2

What's Changed

• Fix api_key in HuggingFace provider by @hlohaus in #2681

Full Changelog: 0.4.5.1...0.4.5.2

g4f v0.4.5.1

Release Notes

This release includes several bug fixes, provider updates, and model additions to improve the stability and functionality of gpt4free.

Bug Fixes

• __str__ Type Error: Resolved an issue where the __str__ method returned a non-string type (specifically, a list) when using reasoning models like deepseek-r1 and sonar-reasoning. This fix ensures that all responses are correctly converted to strings, preventing TypeError exceptions. [github.com] [github.com]
• UI Model Selection: Improved the custom model selection in the UI, making it more user-friendly. [github.com] [github.com]

Provider Updates

• Docker Setup: Updated the Docker instructions in the README to clarify directory setup and x64-only support. [github.com]
• New Providers:
  • Added BlackboxAPI as a new provider. [github.com] [github.com]
  • Updated CablyAI provider, including API key support. [github.com] [github.com]
  • Updated Liaobots model support and alias entries. [github.com] [github.com]
  • Updated DeepInfraChat provider with new models. [github.com]
• Disabled Providers:
  • DarkAI provider has been moved to a not_working directory. [github.com]
  • GPROChat provider has been disabled. [github.com]
• Provider Improvements:
  • Enhanced handling for reasoning models and the <think> tags, for BlackboxAPI and CablyAI providers. [github.com] [github.com]

Model Additions/Updates

• Added support for several new models, including:
  • deepseek-v3 [github.com]
  • deepseek-r1 [github.com]
  • o3-mini-low [github.com]
  • mixtral-small-28b [github.com]
  • llama-3.3-70b
  • phi-4
  • dbrx-instruct [github.com]
  • cably-80b [github.com]
  • glm-4 [github.com]
• Updated the number of providers for gpt-4, gpt-4o, gpt-4o-mini to reflect current status. [github.com]
• Added nemotron-70b, dbrx-instruct, p1,cably-80b, glm-4 mini_max and evil models. [github.com]

Code Improvements

• Import Refactoring: Moved ImageResponse from g4f.image to g4f.providers.response to improve code organization. [github.com]
• Module Restructuring: Split the g4f/image.py file into g4f/image/__init__.py and g4f/image/copy_images.py for better modularity. [github.com]
• UI Enhancements: Improved the logic for managing conversation states and handling input for image generations in the client UI. [github.com]

Documentation

• Updated providers-and-models.md to include new providers, models, and their capabilities. [github.com]
• Added detailed information about provider statuses and model capabilities in the documentation. [github.com]

Other

• Fixed an issue with include in mocks.py. [github.com]
• The user_data_dir variable was corrected in get_nodriver. [github.com]

This release aims to provide a more stable and feature-rich experience with gpt4free. Please report any issues encountered on the project's GitHub page.

What's Changed

• 2.1 feb by @hlohaus in #2680
• Fix error str returned non-string (type list) when using reasonin model by @Juxoola in #2676
• Updated some providers, added new providers and added new models by @kqlio67 in #2679

New Contributors

• @Juxoola made their first contribution in #2676

Full Changelog: 0.4.5.0...0.4.5.1

g4f v0.4.5.0

Release Notes

Enhanced capabilities and new features for AI-powered interactions

✨ Key Enhancements

• Expanded Model Support

  • Added o3-mini and o3-mini-high models to OpenaiChat provider
  • Implemented model reasoning capabilities in OpenaiChat
  • Enabled custom model input support in GUI interface

• Platform Improvements

  • Optimized model filtering in HuggingFace providers using pipeline_tag checks
  • Revamped PerplexityLabs integration with updated API handling

🖼️ New Image Features

• PollinationsAI Integration
  • Added real-time image preview functionality
  • Implemented magic syntax for AI-generated images:
    ![your_description_here](/generate/filename.jpg)

📚 Additional Updates

• Improved error handling across multiple providers
• Enhanced documentation for developer contributions
• Streamlined API request/response logging

👥 Community Contributions

Special thanks to our contributors:

• @hlohaus for OpenAI model list expansion (#2674)
• @Parthsadaria for PerplexityLabs optimizations (#2671)

📋 Full Changelog:
0.4.4.4...0.4.5.0

g4f v0.4.4.4

What's Changed

• Fix response type of reasoning in UI by @hlohaus in #2664

Full Changelog: 0.4.4.2...0.4.4.4

g4f v0.4.4.3

What's Changed

• Fix response type of reasoning in UI by @hlohaus in #2663

Full Changelog: 0.4.4.1...0.4.4.3

g4f v0.4.4.2

What's Changed

• Fix response type of reasoning in UI by @hlohaus in #2663

Full Changelog: 0.4.4.1...0.4.4.2