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
..
app	Refactor: Improve the buffer close for vision_llm_chunk (#9845)	2025-09-02 10:31:37 +08:00
flow	Feat: init dataflow. (#9791)	2025-08-28 18:40:32 +08:00
llm	Use 'float' explicitly for OpenAI's embedding "encoding_format" (#9838)	2025-09-02 10:31:51 +08:00
nlp	Feat: init dataflow. (#9791)	2025-08-28 18:40:32 +08:00
prompts	Fix: meta data error. (#9670)	2025-08-25 09:41:52 +08:00
res	Refa: add result to callback for agent tool use. (#9137)	2025-08-01 21:49:39 +08:00
svr	Refactor: Improve the try logic for upload_to_minio (#9735)	2025-08-28 09:35:29 +08:00
utils	Feat: init dataflow. (#9791)	2025-08-28 18:40:32 +08:00
__init__.py	Update comments (#4569)	2025-01-21 20:52:28 +08:00
benchmark.py	Refactor embedding batch_size (#3825)	2024-12-03 16:22:39 +08:00
raptor.py	Refactor: based on async await to handle Redis when raptor (#9576)	2025-08-22 10:58:02 +08:00
settings.py	Feat: make document parsing and embedding batch sizes configurable via environment variables (#8266)	2025-06-16 13:40:47 +08:00