Haiyue Wang 2e00d8d3d4 Use 'float' explicitly for OpenAI's embedding "encoding_format" (#9838) ... ### What problem does this PR solve? The default value for OpenAI '/v1/embeddings' parameter 'encoding_format' is 'base64'. Use 'float' explicitly to avoid base64 encoding & decoding, larger data size. https://github.com/openai/openai-python/blob/main/src/openai/resources/embeddings.py if not is_given(encoding_format): params["encoding_format"] = "base64" ### Type of change - [x] Performance Improvement		2025-09-02 10:31:51 +08:00
..
__init__.py	Fix: Ollama chat cannot access remote deployment (#9816)	2025-08-29 13:35:41 +08:00
chat_model.py	Refa: revise the implementation of LightRAG and enable response caching (#9828)	2025-08-29 17:58:36 +08:00
cv_model.py	Fix: Gemini parameters error (#9520)	2025-08-18 14:51:10 +08:00
embedding_model.py	Use 'float' explicitly for OpenAI's embedding "encoding_format" (#9838)	2025-09-02 10:31:51 +08:00
rerank_model.py	Refactor: for total_token_count method use if to check first. (#9707)	2025-08-26 10:47:20 +08:00
sequence2txt_model.py	Refa: OpenAI whisper-1 (#9552)	2025-08-19 16:41:18 +08:00
tts_model.py	Add **kwargs to model base class constructors (#9252)	2025-08-07 09:45:37 +08:00