forked from xtekky/gpt4free
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add new models, enhance search & UI components, improve providers
feat(g4f/models.py): add sonar-reasoning and deepseek-v3 models - Add sonar-reasoning model for Perplexity AI provider - Add deepseek-v3 model with Blackbox and DeepInfra providers - Refactor ModelUtils to use dynamic model discovery - Update provider list for deepseek-chat model --- feat(g4f/tools/web_search.py): enhance search robustness and error handling - Add input validation for search queries with length checks - Implement retry logic with multiple backend fallbacks - Add better error handling and logging throughout search flow - Improve cache handling with UTF-8 encoding and error recovery - Add detailed debug logging for search operations - Enhance query processing by joining keyword lists into strings --- feat(g4f/gui/client/static/css/style.css): add collapsible component styles - Add class with border, radius, and margin styling - Implement with hover effects and flex layout - Create with padding and hidden state - Add styling for flex-based layout - Include chevron rotation animation for active state --- refactor(g4f/gui/client/static/js/chat.v1.js): Refactor provider settings UI - Added collapsible container for provider options - Moved provider API key inputs into a new collapsible section - Added event listeners for collapsible header toggles - Improved organization of provider settings UI elements --- refactor(g4f/Provider/Blackbox.py): improve think tag parsing and remove duplicate model alias - Remove duplicate deepseek-chat model alias entry - Enhance think tag parsing logic for cleaner code organization - Split think tag content handling into pre-think, think-content and post-think sections - Add strip() calls to remove unnecessary whitespace from parsed content - Update Reasoning yield to use status parameter instead of f-string formatting --- fix(g4f/Provider/DeepInfraChat.py): update model alias for DeepSeek V3 - Rename deepseek-chat alias to deepseek-v3 for clarity --- refactor(g4f/Provider/PerplexityLabs.py): remove unused model aliases - Remove model_aliases dictionary and its entries - Clean up model mapping configuration - Improve code organization by removing deprecated aliases
- Loading branch information
kqlio67
committed
Jan 30, 2025
1 parent
9c30c4b
commit 1bfe600
Showing
6 changed files
with
136 additions
and
183 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.