Commit Graph

30 Commits (3b3d39cef0211b607d51360d0739022f953ba1a7)

Author SHA1 Message Date
sigoden 3b3d39cef0
refactor: rag add rag_minimum_score config (#617) 2 weeks ago
sigoden 62b297e8bb
feat: add `.regenerate` repl command (#610) 2 weeks ago
sigoden ba884c9fc6
feat: add `.continue` repl command (#608) 2 weeks ago
sigoden 638bf32766
refactor: improve code quatity (#604) 2 weeks ago
sigoden 255b194bcc
feat: add `.starter` repl command (#594) 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 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 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 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 54a837784c
refactor: rename `SendData` to `CompletionData` (#553) 1 month ago
sigoden 50b13d2de9
refactor: rename `function_filter` to `function_matcher` (#535) 1 month 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
1 month ago
sigoden a75aef459d
feat: remove tiktoken (#506) 2 months ago
sigoden 79d0bba640
feat: allow binding model to the role (#505) 2 months ago
sigoden 5284a18248
refactor: config::Input (#503) 2 months ago
sigoden 1e8fc5d269
refactor: list roles includeing builtin roles (#499) 2 months ago
sigoden e7fa6c5a20 refactor: improve code quality 2 months ago
sigoden 38e594505b
feat: shell commands support revision (#413) 3 months ago
sigoden 664ac813aa
refactor: include filepaths if attaching multple text files (#389) 3 months ago
sigoden 992d570041
refactor: cleanup the deprecated repl commands (#355) 4 months ago
sigoden aed243c3aa
feat: allow use of temporary role in a session (#348) 4 months ago
sigoden c773e8d2e1
refactor: improve saving messages (#322) 4 months ago
sigoden 6c0204e696
refactor: change header of messages saved to markdown (#317) 4 months ago
sigoden fe35cfd941
feat: supports model capabilities (#297)
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
6 months ago
sigoden 6280f5ab4b
feat: qianwen vision models support embeded images (#277) 6 months ago
sigoden 27cae9582f
fix: cannot read image with uppercase ext (#270) 7 months ago
sigoden 35c75506e2
feat: support vision (#249)
* 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
7 months ago