gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
LightRAG/lightrag/llm
History
yangdx 88ab73f6ae HotFix: Restore streaming response in OpenAI LLM 
The stream and timeout parameters were moved from **kwargs to explicit
parameters in a previous commit, but were not being passed to the OpenAI
API, causing streaming responses to fail and fall back to non-streaming
mode.Fixes the issue where stream=True was being silently ignored, resulting
in unexpected non-streaming behavior.
2025-11-09 11:52:26 +08:00
..
__init__.py Separated llms from the main llm.py file and fixed some deprication bugs 2025-01-25 00:11:00 +01:00
anthropic.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
azure_openai.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
bedrock.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
binding_options.py Add Gemini embedding support 2025-11-08 03:34:30 +08:00
gemini.py feat: improve Gemini client error handling and retry logic 2025-11-08 22:10:09 +08:00
hf.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
jina.py refactor: simplify jina embedding dimension handling 2025-11-07 22:09:57 +08:00
llama_index_impl.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
lmdeploy.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
lollms.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00
nvidia_openai.py refactor: Remove deprecated max_token_size from embedding configuration 2025-07-29 10:49:35 +08:00
ollama.py Modernize type hints and remove Python 3.8 compatibility code 2025-10-02 23:15:42 +08:00
openai.py HotFix: Restore streaming response in OpenAI LLM 2025-11-09 11:52:26 +08:00
siliconcloud.py refactor: Remove deprecated max_token_size from embedding configuration 2025-07-29 10:49:35 +08:00
zhipu.py Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 2025-09-09 22:34:36 +08:00