Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. Actively in public development.
19.4k
stars
3.24k
forks
source link
🎯 fix: Google AI Client Stability; feat: `gemini-exp` models #4781
Closed
danny-avila closed 6 days ago
Summary
Removed the 7-second timeout constraint that was likely causing AbortError in the Google client
Increased delay timings from 12 to 15 seconds for generative models to prevent premature timeouts
Created a regex constant
EXCLUDED_GENAI_MODELS
to better identify and handle Gemini modelsUpdated model detection logic to use regex testing instead of string, to use
@google/generative-ai
explicitly for latest modelsRemoved beta API version specification for generative models to use the stable release
Simplified the GenAI client initialization by removing unnecessary configuration
Updated
@langchain/google-genai
package from 0.1.3 to 0.1.4 for latest model supportImproved debug logging to accurately reflect the model type being used
[x] Bug fix (non-breaking change which fixes an issue)
[x] My code adheres to this project's style guidelines
[x] I have performed a self-review of my own code
[x] My changes do not introduce new warnings
[x] Local unit tests pass with my changes