18 Commits (main)

Author	SHA1	Message	Date
sigoden	a732291f33	refactor: rename `pass_max_tokens` to `require_max_tokens` (#562)	1 week ago
sigoden	1ec6abfaee	feat: support RAG (#560) ... * feat: support RAG * support more embeddings models and implement concurrent embedding api * show the progress of addings paths * ignore embedding context when saving message * embedding model max_chunk_size => default_chunk_size * support pdf and pandoc formats (docx, epub, ipynb)	1 week ago
sigoden	571d1022f6	refactor: rename some client structs and methods (#555) ... * rename `Completeion*` to `ChatCompletions*` * rename `send_message*` to `chat_completions*` * rename `request_builder` to `chat_completions_builder` * rename `build_body` to `build_chat_completions_body` * rename `extract_completion` to `extract_chat_completions` * format * remove unused config fields	2 weeks ago
sigoden	54a837784c	refactor: rename `SendData` to `CompletionData` (#553)	2 weeks ago
sigoden	b4a40e3fed	feat: support function calling (#514) ... * feat: support function calling * fix on Windows OS * implement multi-steps function calling * fix on Windows OS * add error for client not support function calling * refactor message data structure and make claude client supporting function calling * support reuse previous call results * improve error handling for function calling * use prefix `may_` as indicator for `execute` type fucntions	4 weeks ago
sigoden	369cf9a36a	refactor: minor refinement	4 weeks ago
sigoden	79d0bba640	feat: allow binding model to the role (#505)	4 weeks ago
sigoden	84fab36a1f	refactor: split /data.json into /v1/models and /v1/roles (#494)	1 month ago
sigoden	7762cd6bed	refactor: model pass_max_tokens (#493)	1 month ago
sigoden	85ad276a29	feat: support playground/arena webui (#487)	1 month ago
sigoden	b6957ae3af	refactor: improve serve (#477)	1 month ago
sigoden	8a65337d59	feat: add `.set max_output_tokens` (#468)	1 month ago
sigoden	37a0cd08a9	refactor: rename some structs (#457)	1 month ago
sigoden	865be2bf75	feat: non-streaming returns completion stats (#456)	1 month ago
sigoden	b33e2da75e	refactor: improve serve responses (#455)	2 months ago
sigoden	6e73d25bfe	refactor: change default address for api serveing	2 months ago
sigoden	a17f349daa	feat: support customizing `top_p` parameter (#434)	2 months ago
sigoden	0a4c0413ef	feat: serve all LLMs as OpenAI-compatible API (#431)	2 months ago