| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-06-06 | refactor: config refinement (#570) | sigoden | -60/+69 | |
| 2024-06-05 | refactor: change error message of the model does not support vision (#568) | sigoden | -1/+1 | |
| 2024-06-05 | revert: feat: use systemInstruction for gemini-1.5-* models (#564) (#567) | sigoden | -10/+1 | |
| 2024-06-05 | feat: custom more path to file/dirs with environment variables (#565) | sigoden | -10/+24 | |
| 2024-06-05 | feat: use systemInstruction for gemini-1.5-* models (#564) | sigoden | -1/+10 | |
| 2024-06-05 | chore: format | sigoden | -29/+37 | |
| 2024-06-05 | chore: update readme | sigoden | -11/+16 | |
| 2024-06-05 | refactor: rename `pass_max_tokens` to `require_max_tokens` (#562) | sigoden | -46/+46 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -304/+2616 | |
| * 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) | ||||
| 2024-06-02 | refactor: switch to bitflags State (#557) | sigoden | -86/+72 | |
| 2024-06-01 | refactor: rename some client structs and methods (#555) | sigoden | -265/+298 | |
| * 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 | ||||
| 2024-06-01 | chore: update readme | sigoden | -1/+1 | |
| 2024-06-01 | chore: release v0.18.0 (#551) | sigoden | -141/+158 | |
| 2024-05-30 | refactor: rename `SendData` to `CompletionData` (#553) | sigoden | -99/+152 | |
| 2024-05-30 | refactor: adjust default `compress_threshold` to 4000 (#552) | sigoden | -2/+2 | |
| 2024-05-30 | chore: fix typos | sigoden | -4/+4 | |
| 2024-05-29 | refactor: use `json_stream` for ollama to improve reliability (#549) | ProjectMoon | -11/+11 | |
| * Use JSON stream for ollama to improve reliability. Fixes #548. * remove unused import * fix clippy error * format --------- Co-authored-by: sigoden <sigoden@gmail.com> | ||||
| 2024-05-29 | refactor: `temp` session ignore `save_session` (#547) | sigoden | -3/+16 | |
| 2024-05-26 | fix: bedrock issues (#544) | rolfwilms | -2/+3 | |
| * 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> | ||||
| 2024-05-23 | fix: json stream parser and refine client modules (#538) | sigoden | -233/+361 | |
| 2024-05-23 | refactor: qiawen client add qwen-long (#537) | sigoden | -29/+43 | |
| 2024-05-22 | refactor: rename `function_filter` to `function_matcher` (#535) | sigoden | -22/+22 | |
| 2024-05-22 | feat: allow patching req body with client config (#534) | sigoden | -115/+194 | |
| 2024-05-21 | refactor: adjust some placeholder/prompt text (#530) | sigoden | -13/+12 | |
| 2024-05-21 | refactor: change prompt for executing tool functions (#529) | sigoden | -50/+85 | |
| * refactor: change prompt for executing tool functions * add AICHAT_FUNCTION_AUTO_EXECUTE to auto confirm | ||||
| 2024-05-20 | refactor: no export LLM_FUNCTION_DATA, pass json as command arg (#528) | sigoden | -66/+13 | |
| 2024-05-20 | feat: webui operates independently from aichat (#527) | sigoden | -24/+49 | |
| 2024-05-20 | refactor: webui enhence input textarea and copy message (#526) | sigoden | -78/+65 | |
| 2024-05-20 | fix: webui message body do not autoscroll to bottom sometimes (#525) | sigoden | -34/+27 | |
| 2024-05-19 | refactor: export LLM_FUNCTION_DATA when calling functions (#524) | sigoden | -7/+5 | |
| 2024-05-19 | fix: webui issue with image (#523) | sigoden | -2/+7 | |
| 2024-05-19 | refactor: webui limit height of input textarea (#522) | sigoden | -30/+64 | |
| 2024-05-19 | feat: webui add toolbox(copy-bt/regenerate-btn) to message (#521) | sigoden | -13/+144 | |
| 2024-05-18 | fix: panic when check api error (#520) | sigoden | -4/+26 | |
| 2024-05-18 | refactor: shell detect/prompt (#519) | sigoden | -44/+44 | |
| 2024-05-18 | refactor: non-zero exit code when model call fails (#518) | sigoden | -1/+2 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -683/+1791 | |
| * 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 | ||||
| 2024-05-15 | chore: update bug_report issue-template | sigoden | -0/+3 | |
| 2024-05-15 | fix: unexpect enter repl if have pipe-in but no text args (#512) | sigoden | -1/+1 | |
| 2024-05-15 | refactor: add gemini-1.5-flash to models.yaml (#510) | sigoden | -5/+17 | |
| 2024-05-15 | fix: no builtin roles if no roles.yaml (#509) | sigoden | -10/+8 | |
| 2024-05-15 | chore: update issue-templates | sigoden | -12/+12 | |
| 2024-05-15 | refactor: improve tokenzie | sigoden | -1/+2 | |
| 2024-05-14 | feat: remove tiktoken (#506) | sigoden | -100893/+27 | |
| 2024-05-14 | refactor: minor refinement | sigoden | -2/+2 | |
| 2024-05-14 | feat: allow binding model to the role (#505) | sigoden | -25/+81 | |
| 2024-05-14 | refactor: config::Input (#503) | sigoden | -119/+110 | |
| 2024-05-14 | chore: release v0.17.0 (#497) | sigoden | -152/+207 | |
| 2024-05-14 | refactor: update models.yaml (#501) | sigoden | -8/+15 | |
| 2024-05-11 | refactor: list roles includeing builtin roles (#499) | sigoden | -76/+72 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |