summaryrefslogtreecommitdiffstats
path: root/src/serve.rs
AgeCommit message (Collapse)AuthorLines
2024-07-26refactor: several optimizations (#749)sigoden-2/+4
2024-06-22refactor: update readme and models.yamlsigoden-2/+2
2024-06-22refactor: some error messages (#627)sigoden-1/+1
2024-06-21feat: serve embeddings api (#624)sigoden-27/+93
2024-06-05refactor: rename `pass_max_tokens` to `require_max_tokens` (#562)sigoden-2/+2
2024-06-05feat: support RAG (#560)sigoden-9/+2
* 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)
2024-06-01refactor: rename some client structs and methods (#555)sigoden-8/+6
* 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
2024-05-30refactor: rename `SendData` to `CompletionData` (#553)sigoden-5/+7
2024-05-18feat: support function calling (#514)sigoden-23/+28
* 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
2024-05-14refactor: minor refinementsigoden-1/+1
2024-05-14feat: allow binding model to the role (#505)sigoden-1/+1
2024-05-08refactor: split /data.json into /v1/models and /v1/roles (#494)sigoden-7/+14
2024-05-08refactor: model pass_max_tokens (#493)sigoden-2/+2
2024-05-07feat: support playground/arena webui (#487)sigoden-11/+88
2024-05-02refactor: improve serve (#477)sigoden-2/+4
2024-04-30feat: add `.set max_output_tokens` (#468)sigoden-1/+1
2024-04-29refactor: rename some structs (#457)sigoden-12/+12
2024-04-29feat: non-streaming returns completion stats (#456)sigoden-8/+31
2024-04-28refactor: improve serve responses (#455)sigoden-14/+27
2024-04-24refactor: change default address for api serveingsigoden-2/+2
2024-04-24feat: support customizing `top_p` parameter (#434)sigoden-0/+3
2024-04-24feat: serve all LLMs as OpenAI-compatible API (#431)sigoden-0/+364