Commit Graph

568 Commits (b3bec3cfb0ab75a5dc30dbd55b91e687a3588410)
 

Author SHA1 Message Date
sigoden b05b730cb5
feat: add config `repl_prelude` and `bot_prelude` (#584) 3 weeks ago
sigoden fcdfeea548
refactor: rename `function_matcher` to `selected_functions` (#583) 3 weeks ago
sigoden 8615293747
feat: add config `dangerously_functions` (#582) 3 weeks ago
sigoden 822688a06a
refactor: adjust config methods order (#581) 3 weeks ago
sigoden bb867c4fcb
feat: support bot (#579)
* feat: support bots

* refactor with RoleLike

* improve exiting session

* make bot works with rag

* refactor repl assert state

* add bot banner

* repl complete bots according bots.txt

* fix on windows

* remove threadpool executing function callings

* adjust repl left_prompt

* move bot config to global config.yaml

* `.bot` throw err if funciton callings is not configured
3 weeks ago
sigoden 5635ca6a58
refactor: warning model or client don't support function calling (#572) 4 weeks ago
sigoden 93ef6da629
refactor: global IS_STDOUT_TERMINAL (#571) 4 weeks ago
sigoden c26594c3c8
refactor: config refinement (#570) 4 weeks ago
sigoden 171a46eee2
refactor: change error message of the model does not support vision (#568) 4 weeks ago
sigoden ce8d6d750d
revert: feat: use systemInstruction for gemini-1.5-* models (#564) (#567) 4 weeks ago
sigoden 4b27378443
feat: custom more path to file/dirs with environment variables (#565) 4 weeks ago
sigoden d4e043e5bf
feat: use systemInstruction for gemini-1.5-* models (#564) 4 weeks ago
sigoden b17719457b chore: format 4 weeks ago
sigoden eacc88f04a chore: update readme 4 weeks ago
sigoden a732291f33
refactor: rename `pass_max_tokens` to `require_max_tokens` (#562) 4 weeks ago
sigoden 1ec6abfaee
feat: support RAG (#560)
* 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)
4 weeks ago
sigoden 71f2e94579
refactor: switch to bitflags State (#557) 1 month ago
sigoden 571d1022f6
refactor: rename some client structs and methods (#555)
* 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
1 month ago
sigoden 259583f4f7 chore: update readme 1 month ago
sigoden 38797e3264
chore: release v0.18.0 (#551) 1 month ago
sigoden 54a837784c
refactor: rename `SendData` to `CompletionData` (#553) 1 month ago
sigoden fa4bf14e02
refactor: adjust default `compress_threshold` to 4000 (#552) 1 month ago
sigoden c0f4d2d712 chore: fix typos 1 month ago
ProjectMoon 00f3cb182f
refactor: use `json_stream` for ollama to improve reliability (#549)
* Use JSON stream for ollama to improve reliability. Fixes #548.

* remove unused import

* fix clippy error

* format

---------

Co-authored-by: sigoden <sigoden@gmail.com>
1 month ago
sigoden 4fa92b020a
refactor: `temp` session ignore `save_session` (#547) 1 month ago
rolfwilms 569317728c
fix: bedrock issues (#544)
* 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>
1 month ago
sigoden 5458150ed3
fix: json stream parser and refine client modules (#538) 1 month ago
sigoden 2ccbb0f06a
refactor: qiawen client add qwen-long (#537) 1 month ago
sigoden 50b13d2de9
refactor: rename `function_filter` to `function_matcher` (#535) 1 month ago
sigoden ba3bcfd67c
feat: allow patching req body with client config (#534) 1 month ago
sigoden 91a06543b2
refactor: adjust some placeholder/prompt text (#530) 1 month ago
sigoden 2174dc055f
refactor: change prompt for executing tool functions (#529)
* refactor: change prompt for executing tool functions

* add AICHAT_FUNCTION_AUTO_EXECUTE to auto confirm
1 month ago
sigoden d4de2d761b
refactor: no export LLM_FUNCTION_DATA, pass json as command arg (#528) 2 months ago
sigoden 1a2a261f9f
feat: webui operates independently from aichat (#527) 2 months ago
sigoden 7d7caf7479
refactor: webui enhence input textarea and copy message (#526) 2 months ago
sigoden 482822da53
fix: webui message body do not autoscroll to bottom sometimes (#525) 2 months ago
sigoden 9b7d93ee84
refactor: export LLM_FUNCTION_DATA when calling functions (#524) 2 months ago
sigoden 7f21854b9a
fix: webui issue with image (#523) 2 months ago
sigoden eaf36cdfb5
refactor: webui limit height of input textarea (#522) 2 months ago
sigoden 1b9aed6afb
feat: webui add toolbox(copy-bt/regenerate-btn) to message (#521) 2 months ago
sigoden 31977f9642
fix: panic when check api error (#520) 2 months ago
sigoden d16cca23ac
refactor: shell detect/prompt (#519) 2 months ago
sigoden 665693ccf2
refactor: non-zero exit code when model call fails (#518) 2 months ago
sigoden b4a40e3fed
feat: support function calling (#514)
* 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
2 months ago
sigoden 1348a62e5f chore: update bug_report issue-template 2 months ago
sigoden f9d45175d3
fix: unexpect enter repl if have pipe-in but no text args (#512) 2 months ago
sigoden 5378033b34
refactor: add gemini-1.5-flash to models.yaml (#510) 2 months ago
sigoden 12d8798e61
fix: no builtin roles if no roles.yaml (#509) 2 months ago
sigoden 64943f49d1 chore: update issue-templates 2 months ago
sigoden 5883a0685a refactor: improve tokenzie 2 months ago