| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-06-05 | revert: feat: use systemInstruction for gemini-1.5-* models (#564) (#567) | sigoden | -10/+1 | |
| 2024-06-05 | feat: use systemInstruction for gemini-1.5-* models (#564) | sigoden | -1/+10 | |
| 2024-06-05 | chore: format | sigoden | -4/+12 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -8/+71 | |
| * 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 | -24/+25 | |
| * 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 | -7/+11 | |
| 2024-05-23 | fix: json stream parser and refine client modules (#538) | sigoden | -4/+1 | |
| 2024-05-22 | feat: allow patching req body with client config (#534) | sigoden | -8/+5 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -53/+119 | |
| * 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 | |
| 2024-05-06 | refactor: unified access token management (#486) | sigoden | -13/+14 | |
| 2024-05-06 | feat: extract vertexai-claude client (#485) | sigoden | -107/+32 | |
| 2024-04-30 | feat: openai-compatible platforms share the same client (#469) | sigoden | -2/+3 | |
| 2024-04-30 | refactor: improve code quality | sigoden | -3/+1 | |
| 2024-04-29 | refactor: check res status code | sigoden | -2/+2 | |
| 2024-04-29 | refactor: prompts for generating config file (#463) | sigoden | -1/+1 | |
| 2024-04-29 | refactor: rename some structs (#457) | sigoden | -9/+9 | |
| 2024-04-29 | feat: non-streaming returns completion stats (#456) | sigoden | -6/+19 | |
| 2024-04-28 | feat: support vertexai claude (#439) | sigoden | -17/+93 | |
| 2024-04-28 | refactor: extract prelude models to models.yaml (#451) | sigoden | -9/+0 | |
| 2024-04-26 | refactor: simplify impl client trait (#445) | sigoden | -22/+22 | |
| 2024-04-25 | refactor: fix typo and some error message (#438) | sigoden | -1/+1 | |
| 2024-04-25 | refactor: extract common catch_error (#437) | sigoden | -34/+12 | |
| 2024-04-25 | refactor: rewrite list models of all clients (#436) | sigoden | -16/+15 | |
| 2024-04-24 | feat: support customizing `top_p` parameter (#434) | sigoden | -1/+6 | |
| 2024-04-24 | refactor: handling of response error (#433) | sigoden | -19/+22 | |
| 2024-04-23 | feat: builtin models can be overwrited by models config (#429) | sigoden | -14/+5 | |
| 2024-04-23 | feat: customize model's max_output_tokens (#428) | sigoden | -7/+9 | |
| 2024-04-23 | refactor: more async code (#427) | sigoden | -2/+2 | |
| 2024-04-11 | refactor: all clients use openai token counter (#402) | sigoden | -4/+1 | |
| 2024-04-10 | refactor: extract json stream handling (#398) | sigoden | -50/+8 | |
| 2024-04-10 | refactor: update gemini/vertexai models list (#395) | sigoden | -4/+2 | |
| 2024-04-04 | chore: fix typo | sigoden | -1/+1 | |
| 2024-04-04 | refactor: gemini/vertexai blocked by safety (#386) | sigoden | -10/+18 | |
| 2024-03-25 | feat: support customizing gemini safeSettings (#375) | sigoden | -16/+26 | |
| 2024-03-25 | refactor: reorder models (#372) | sigoden | -5/+5 | |
| The capable ones come first. | ||||
| 2024-03-19 | fix: vertexai model names (#365) | sigoden | -2/+2 | |
| 2024-03-07 | chore: update deps | sigoden | -1/+1 | |
| 2024-03-06 | refactor: rename model's `max_tokens` to `max_input_tokens` (#339) | sigoden | -4/+5 | |
| BREAKING CHANGE: rename model's `max_tokens` to `max_input_tokens` | ||||
| 2024-03-04 | feat: reduce gemini blocking of unsafe content with safetySettings (#334) | sigoden | -0/+6 | |
| 2024-02-16 | refactor: update vertexai/gemini/ernie clients (#309) | sigoden | -15/+259 | |
| 2024-02-15 | feat: support vertexai (#308) | sigoden | -0/+92 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |