| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-07-27 | feat: support patching request url, headers and body (#756) | sigoden | -24/+17 | |
| 2024-07-27 | feat: change model patch structure (#754) | sigoden | -1/+1 | |
| 2024-06-22 | refactor: improve clients (#632) | sigoden | -10/+10 | |
| 2024-06-21 | feat: support rerank (#620) | sigoden | -1/+1 | |
| 2024-06-19 | refactor: rag add rag_minimum_score config (#617) | sigoden | -2/+1 | |
| 2024-06-11 | refactor: improve openai client (#586) | sigoden | -1/+0 | |
| 2024-06-05 | chore: format | sigoden | -5/+3 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -9/+58 | |
| * 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) | ||||
| 2024-06-01 | refactor: rename some client structs and methods (#555) | sigoden | -15/+15 | |
| * 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 | ||||
| 2024-05-30 | refactor: rename `SendData` to `CompletionData` (#553) | sigoden | -6/+10 | |
| 2024-05-23 | fix: json stream parser and refine client modules (#538) | sigoden | -2/+2 | |
| 2024-05-22 | feat: allow patching req body with client config (#534) | sigoden | -3/+6 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -10/+127 | |
| * 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 | ||||
| 2024-05-08 | refactor: model pass_max_tokens (#493) | sigoden | -1/+1 | |
| 2024-04-30 | feat: openai-compatible platforms share the same client (#469) | sigoden | -2/+2 | |
| 2024-04-30 | refactor: improve code quality | sigoden | -3/+1 | |
| 2024-04-29 | refactor: check res status code | sigoden | -1/+1 | |
| 2024-04-29 | refactor: sse handling (#465) | sigoden | -4/+4 | |
| 2024-04-29 | refactor: abstract event stream handling (#458) | sigoden | -46/+13 | |
| 2024-04-29 | refactor: rename some structs (#457) | sigoden | -7/+7 | |
| 2024-04-29 | feat: non-streaming returns completion stats (#456) | sigoden | -7/+16 | |
| 2024-04-28 | refactor: extract prelude models to models.yaml (#451) | sigoden | -14/+0 | |
| 2024-04-26 | refactor: simplify impl client trait (#445) | sigoden | -3/+6 | |
| 2024-04-25 | refactor: fix typo and some error message (#438) | sigoden | -1/+4 | |
| 2024-04-25 | refactor: extract common catch_error (#437) | sigoden | -13/+3 | |
| 2024-04-25 | refactor: rewrite list models of all clients (#436) | sigoden | -22/+20 | |
| 2024-04-24 | feat: support customizing `top_p` parameter (#434) | sigoden | -4/+8 | |
| 2024-04-24 | refactor: handling of response error (#433) | sigoden | -12/+20 | |
| 2024-04-23 | feat: builtin models can be overwrited by models config (#429) | sigoden | -13/+4 | |
| 2024-04-23 | feat: customize model's max_output_tokens (#428) | sigoden | -6/+7 | |
| 2024-04-23 | refactor: more async code (#427) | sigoden | -2/+2 | |
| 2024-04-19 | refactor: improve error message for some clients | sigoden | -4/+10 | |
| 2024-04-11 | refactor: improve error mesasge for invalid eventsource content-type (#405) | sigoden | -0/+4 | |
| 2024-04-11 | refactor: all clients use openai token counter (#402) | sigoden | -4/+1 | |
| 2024-04-10 | refactor: update openai models list (#400) | sigoden | -1/+5 | |
| 2024-04-10 | refactor: update openai models list (#396) | sigoden | -7/+5 | |
| 2024-04-06 | refactor: update models (#388) | sigoden | -4/+4 | |
| 2024-03-25 | refactor: reorder models (#372) | sigoden | -3/+3 | |
| The capable ones come first. | ||||
| 2024-03-22 | refactor: do not automatically convert temperature value (#368) | sigoden | -1/+1 | |
| 2024-03-06 | refactor: rename model's `max_tokens` to `max_input_tokens` (#339) | sigoden | -5/+5 | |
| BREAKING CHANGE: rename model's `max_tokens` to `max_input_tokens` | ||||
| 2024-03-01 | chore: improve openai api error handling | sigoden | -2/+5 | |
| 2024-03-01 | chore: update order of openai models | sigoden | -3/+3 | |
| 2024-02-13 | feat: update openai/qianwen/gemini models (#306) | sigoden | -2/+2 | |
| 2024-01-30 | feat: add openai.api_base config (#302) | sigoden | -6/+3 | |
| 2024-01-13 | feat: supports model capabilities (#297) | sigoden | -17/+12 | |
| 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 | ||||
| 2023-12-16 | chore: change order of openai models | sigoden | -2/+2 | |
| 2023-11-27 | feat: support vision (#249) | sigoden | -2/+9 | |
| * feat: support vision * clippy * implement vision * resolve data url to local file * add model openai:gpt-4-vision-preview * use newline to concate embeded text files * set max_tokens for gpt-4-vision-preview | ||||
| 2023-11-08 | feat: add openai:gpt-4-1106-preview (#233) | sigoden | -2/+4 | |
| 2023-11-07 | feat: allow the use of an unlisted model (#219) | sigoden | -0/+2 | |
| 2023-11-07 | refactor: remove Model.client_index, match client by name (#218) | sigoden | -2/+2 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |