summaryrefslogtreecommitdiffstats
path: root/src/client/qianwen.rs
AgeCommit message (Collapse)AuthorLines
2024-05-30refactor: rename `SendData` to `CompletionData` (#553)sigoden-8/+12
2024-05-23fix: json stream parser and refine client modules (#538)sigoden-9/+5
2024-05-23refactor: qiawen client add qwen-long (#537)sigoden-18/+26
2024-05-22feat: allow patching req body with client config (#534)sigoden-2/+5
2024-05-18feat: support function calling (#514)sigoden-12/+25
* 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
2024-05-08refactor: model pass_max_tokens (#493)sigoden-1/+1
2024-05-02chore: fix typos (#476)Tatsuya Kyushima-1/+1
2024-04-30feat: openai-compatible platforms share the same client (#469)sigoden-2/+2
2024-04-30refactor: improve code qualitysigoden-5/+4
2024-04-29refactor: check res status codesigoden-1/+1
2024-04-29refactor: sse handling (#465)sigoden-3/+3
2024-04-29refactor: abstract event stream handling (#458)sigoden-32/+15
2024-04-29refactor: rename some structs (#457)sigoden-9/+9
2024-04-29feat: non-streaming returns completion stats (#456)sigoden-40/+50
2024-04-28refactor: extract prelude models to models.yaml (#451)sigoden-13/+0
2024-04-26refactor: simplify impl client trait (#445)sigoden-28/+28
2024-04-25refactor: fix typo and some error message (#438)sigoden-1/+1
2024-04-25refactor: extract common catch_error (#437)sigoden-12/+4
2024-04-25refactor: rewrite list models of all clients (#436)sigoden-19/+19
2024-04-24feat: support customizing `top_p` parameter (#434)sigoden-29/+24
2024-04-24refactor: handling of response error (#433)sigoden-9/+10
2024-04-23feat: builtin models can be overwrited by models config (#429)sigoden-13/+5
2024-04-23feat: customize model's max_output_tokens (#428)sigoden-3/+7
2024-04-23refactor: more async code (#427)sigoden-5/+2
2024-04-11refactor: all clients use openai token counter (#402)sigoden-4/+1
2024-04-06refactor: update models (#388)sigoden-3/+3
2024-03-25refactor: reorder models (#372)sigoden-3/+3
The capable ones come first.
2024-03-22refactor: do not automatically convert temperature value (#368)sigoden-2/+7
2024-03-06refactor: rename model's `max_tokens` to `max_input_tokens` (#339)sigoden-6/+8
BREAKING CHANGE: rename model's `max_tokens` to `max_input_tokens`
2024-02-13feat: update openai/qianwen/gemini models (#306)sigoden-1/+2
2024-01-13feat: supports model capabilities (#297)sigoden-12/+11
1. automatically switch to the model that has the necessary capabilities. 2. throw an error if the client does not have a model with the necessary capabilities
2023-12-24feat: custom REPL prompt (#283)sigoden-2/+2
2023-12-20feat: qianwen vision models support embeded images (#277)sigoden-19/+128
2023-12-19feat: support qianwen:qwen-vl-plus (#275)sigoden-40/+110
2023-11-27feat: add ernie:ernie-bot-8k qianwen:qwen-max (#252)sigoden-13/+13
2023-11-09refactor: qianwen client use incremental_output (#240)sigoden-5/+5
2023-11-07feat: allow the use of an unlisted model (#219)sigoden-0/+2
2023-11-07refactor: remove Model.client_index, match client by name (#218)sigoden-2/+2
2023-11-07refactor: rename Model.llm_name to name (#216)sigoden-1/+1
2023-11-04feat: support Qianwen (#211)sigoden-0/+160
generated by cgit v1.2.3 (git 2.39.1) at 2026-10-03 16:25:29 +0000