Archives
/
aichat
mirror of https://github.com/sigoden/aichat
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
693 Commits
1 Branch
23 Tags
4.1 MiB
main
v0.1.0
v0.10.0
v0.11.0
v0.12.0
v0.13.0
v0.14.0
v0.15.0
v0.16.0
v0.17.0
v0.18.0
v0.19.0
v0.2.0
v0.20.0
v0.21.0
v0.21.1
v0.22.0
v0.3.0
v0.4.0
v0.5.0
v0.6.0
v0.7.0
v0.8.0
v0.9.0
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'e39498e340'
${ noResults }
Commit Graph

128 Commits (e39498e340a192077ec64d14c72470cd99716a71)

Author SHA1 Message Date
sigoden bbdd866eb3
feat: abandon `auto_copy` (#607) 4 months ago
sigoden 746b087111
refactor: add/modify rag-related config (#599) 4 months ago
sigoden e9e48f2320
refactor: rename `selected_functions` to `functions_filter` (#587) 4 months ago
sigoden b05b730cb5
feat: add config `repl_prelude` and `bot_prelude` (#584) 4 months ago
sigoden 8615293747
feat: add config `dangerously_functions` (#582) 4 months 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
 4 months 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)
 5 months ago
sigoden 38797e3264
chore: release v0.18.0 (#551) 5 months ago
sigoden fa4bf14e02
refactor: adjust default `compress_threshold` to 4000 (#552) 5 months ago
sigoden ba3bcfd67c
feat: allow patching req body with client config (#534) 5 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
 5 months ago
sigoden 7762cd6bed
refactor: model pass_max_tokens (#493) 5 months ago
sigoden 956a960390
feat: support zhipuai client (#491) 5 months ago
sigoden 0071d84aa5
feat: support deepseek client (#490) 5 months ago
sigoden 9b283024b4
feat: extract vertexai-claude client (#485) 6 months ago
sigoden 82a9ef024d
refactor: aware of lowercase https_proxy/all_proxy (#484) 6 months ago
sigoden 5eae392dbd
refactore: add models for openai-compatible platforms (#471) 6 months ago
sigoden 83ca74bf8a chore: minor refinement 6 months ago
sigoden 8dba46becf
feat: openai-compatible platforms share the same client (#469) 6 months ago
sigoden 50eac8b594
feat: support replicate client (#466) 6 months ago
sigoden ffb0af8236
refactor: add some openai-compatiable platforms to config.example.yaml (#464) 6 months ago
sigoden 4d1c53384b
refactor: prompts for generating config file (#463) 6 months ago
sigoden 3a00fb283e refactor: user config models replace client builtin models 6 months ago
sigoden 34041a976c
feat: support cloudflare client (#459) 6 months ago
sigoden 72d1e5958d chore: add openai-compatible platforms to config.example.yaml 6 months ago
sigoden 212ff1674e refactor: minor improvements 
- config.example.yaml comments
- `--serve` description
- No model error
 6 months ago
sigoden 7bda1eace2
refactor: rename ollama config field api_key => api_auth (#453) 6 months ago
sigoden 338b0438dc
feat: run without config file by set `AICHAT_CLIENT_TYPE` (#452) 6 months ago
sigoden 1f2b626703
feat: support bedrock client (#450) 6 months ago
sigoden 615bab215b
feat: support vertexai claude (#439) 6 months ago
sigoden a21e1213cc
feat: support perplexity (#444) 6 months ago
sigoden 503ec98bd1
feat: support moonshot again (#442) 6 months ago
sigoden 29a4ffd514
feat: support groq (#441) 6 months ago
sigoden b62e8e1625 refactor: update ollama chat_endpoint in example config file 6 months ago
sigoden a17f349daa
feat: support customizing `top_p` parameter (#434) 6 months ago
sigoden d1aafa1115
feat: customize model's max_output_tokens (#428) 6 months ago
sigoden 8ab57ed74e
refactor: update description for cli options and config fields (#423) 6 months ago
sigoden 8b806db857
feat: ctrlc won't exit repl and remove `ctrlc_exit` config (#419) 6 months ago
sigoden 5d7c786b7f
feat: remove moonshot client (#418) 6 months ago
sigoden b9bde15c1f
feat: add config `buffer_editor` (#417) 6 months ago
sigoden 4a88a3da04
refactor: `ctrlc_exit` config default to false (#403) 6 months ago
sigoden 5915bc2f3a
feat: support cohere (#397) 6 months ago
sigoden 2738988fc4
feat: add `ctrlc_exit` option to control REPL exit by ctrl+c (#391) 6 months ago
sigoden bd9a6a8725
feat: `save_session` config item can be null (#380) 7 months ago
sigoden 8da9fa5f4c
feat: add sepereate `save_session` config item to session (#377) 7 months ago
Patrick Jackson 582f56e915
feat: add `save_session` config item and `--save-session` cli option (#370) 
* fix: sessions should save when exiting

* feat: improve save sessions

* feat: do not allow saving the temp session name

* feat: allow creating a session without interactive use

* feat: add `save_session` config and `--save-session` option

---------

Co-authored-by: sigoden <sigoden@gmail.com>
 7 months ago
sigoden 7f05dc1a4a
feat: support customizing gemini safeSettings (#375) 7 months ago
sigoden 0ebc7955da
refactor: improve creating config for openai-compatible client (#374) 7 months ago
sigoden eec041c111
feat: rename client localai to openai-compatible (#373) 
BREAKING CHANGE: rename client localai to openai-compatible
 7 months ago
sigoden 774d991144
feat: support moonshot (#369) 7 months ago
sigoden 527da63d18
refactor: do not automatically convert temperature value (#368) 7 months ago
sigoden d5b10ea0c1 chore: fix typos 8 months ago
sigoden 8e5d4e55b1
refactor: rename model's `max_tokens` to `max_input_tokens` (#339) 
BREAKING CHANGE: rename model's `max_tokens` to `max_input_tokens`
 8 months ago
sigoden 3f693ea060
feat: compress session automaticlly (#333) 
* feat: compress session automaticlly

* non-block

* update field description

* set compress_threshold

* update session::clear_messages

* able to override session compress_threshold

* enable compress_threshold by default

* make session compress_threshold optional
 8 months ago
sigoden 75fe0b9205
feat: support mistral (#324) 8 months ago
sigoden c538533014
feat: support claude (#278) 8 months ago
sigoden 179a5f5749
refactor: update vertexai/gemini/ernie clients (#309) 8 months ago
sigoden 5e4210980d
feat: support vertexai (#308) 8 months ago
Kelvie Wong 176ff6f83e
feat: add `extra_fields` to models of localai/ollama clients (#298) 
* Add an "extra_fields" config to localai models

Because there are so many local AIs out there with a bunch of custom
parameters you can set, this allows users to send in extra parameters to
a local LLM runner, such as, e.g. `instruction_template: Alpaca`, so
that Mixtral can take a system prompt.

* support ollama

---------

Co-authored-by: sigoden <sigoden@gmail.com>
 9 months ago
sigoden a30c3cc4c1
feat: add openai.api_base config (#302) 9 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
 9 months ago
sigoden 0e5c8567d4
refactor: ollam api_base configuration (#285) 10 months ago
sigoden 1c9ca1b002
feat: custom REPL prompt (#283) 10 months ago
sigoden 64c4edf7c8
feat: support ollama (#276) 10 months ago
sigoden 6fb13359f4
feat: abandon PaLM2 (#274) 10 months ago
sigoden 6286251d32
feat: support gemini (#273) 10 months ago
sigoden 6bb2ec05be
feat: add `config.prelude` to allow setting default role/session (#224) 12 months ago
sigoden 7627771e2d
feat: support Qianwen (#211) 12 months ago
sigoden ec1f99fbf5
feat: support Ernie (#210) 12 months ago
sigoden bba5028615
feat: support PaLM (#209) 12 months ago
sigoden 4380b4f20b
refactor: rename azure to azure_openai, improve register_client! (#208) 12 months ago
sigoden b34e40e25f
refactor: rename azure-openai to azure (#204) 12 months ago
sigoden 7f2210dbca
refactor: clients/* and config.rs (#193) 
- add register_clients macro to make it easier to add a new client
- no create_client_config, just add const PROMPTS
- move ModelInfo from clients/ to config/
- model's max_tokens are optional
- improve code quanity on config/mod.rs
- add/use macro config_get_fn
 12 months ago
sigoden 64202758ec
chore: move split_line_* from repl/cmd.rs to utils/ (#190) 12 months ago
sigoden bd3fc8e657 chore: refactor config description 12 months ago
sigoden a137483b03
feat: improve client (#189) 12 months ago
sigoden 36380475d5
feat: support azure-openai (#166) 12 months ago
sigoden eb023e5759 chore: rename config.yaml to config.example.yaml 12 months ago