| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-07-28 | feat: abandon rag_dedicated client and improve (#757) | sigoden | -2/+1 | |
| 2024-07-27 | feat: support patching request url, headers and body (#756) | sigoden | -26/+58 | |
| 2024-07-27 | feat: bedrock client switch to converse api and support cohere models (#747) | sigoden | -159/+283 | |
| 2024-07-27 | feat: change model patch structure (#754) | sigoden | -1/+1 | |
| 2024-06-05 | chore: format | sigoden | -1/+1 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -6/+4 | |
| * 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 | -34/+40 | |
| * 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 | -11/+15 | |
| 2024-05-26 | fix: bedrock issues (#544) | rolfwilms | -0/+1 | |
| * Removed extraneous key [stream] for AWS Bedrock Claude models. * Reduceddefault AWS Bedrock llama-3 max_output_tokens to 2048 to align with API requirements. --------- Co-authored-by: Rolf Wilms <rwilms@csc.com> | ||||
| 2024-05-22 | feat: allow patching req body with client config (#534) | sigoden | -5/+5 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -15/+20 | |
| * 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 | -3/+3 | |
| 2024-05-02 | chore: fix typos (#476) | Tatsuya Kyushima | -2/+2 | |
| 2024-05-01 | refactore: add models for openai-compatible platforms (#471) | sigoden | -8/+4 | |
| 2024-04-30 | feat: openai-compatible platforms share the same client (#469) | sigoden | -3/+3 | |
| 2024-04-30 | refactor: improve code quality | sigoden | -37/+9 | |
| 2024-04-29 | refactor: check res status code | sigoden | -2/+2 | |
| 2024-04-29 | refactor: rename some structs (#457) | sigoden | -11/+11 | |
| 2024-04-29 | feat: non-streaming returns completion stats (#456) | sigoden | -14/+37 | |
| 2024-04-28 | chore: fix typo | sigoden | -2/+2 | |
| 2024-04-28 | feat: support bedrock client (#450) | sigoden | -0/+443 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |