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
2024-03-04 11:08:59 +08:00
sigoden
75fe0b9205
feat: support mistral ( #324 )
2024-02-28 08:22:15 +08:00
sigoden
c538533014
feat: support claude ( #278 )
2024-02-27 08:38:19 +08:00
sigoden
179a5f5749
refactor: update vertexai/gemini/ernie clients ( #309 )
2024-02-16 18:32:33 +08:00
sigoden
5e4210980d
feat: support vertexai ( #308 )
2024-02-15 08:10:30 +08:00
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>
2024-01-30 19:43:55 +08:00
sigoden
a30c3cc4c1
feat: add openai.api_base config ( #302 )
2024-01-30 18:28:12 +08:00
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
2024-01-13 19:52:07 +08:00
sigoden
0e5c8567d4
refactor: ollam api_base configuration ( #285 )
2023-12-25 08:05:06 +08:00
sigoden
1c9ca1b002
feat: custom REPL prompt ( #283 )
2023-12-24 16:04:18 +08:00
sigoden
64c4edf7c8
feat: support ollama ( #276 )
2023-12-20 07:49:05 +08:00
sigoden
6fb13359f4
feat: abandon PaLM2 ( #274 )
2023-12-19 20:47:15 +08:00
sigoden
6286251d32
feat: support gemini ( #273 )
2023-12-19 20:37:53 +08:00
sigoden
6bb2ec05be
feat: add config.prelude to allow setting default role/session ( #224 )
2023-11-07 19:14:58 +08:00
sigoden
7627771e2d
feat: support Qianwen ( #211 )
2023-11-04 09:51:01 +08:00
sigoden
ec1f99fbf5
feat: support Ernie ( #210 )
2023-11-04 08:54:40 +08:00
sigoden
bba5028615
feat: support PaLM ( #209 )
2023-11-04 08:11:51 +08:00
sigoden
4380b4f20b
refactor: rename azure to azure_openai, improve register_client! ( #208 )
2023-11-04 06:28:40 +08:00
sigoden
b34e40e25f
refactor: rename azure-openai to azure ( #204 )
2023-11-03 09:56:15 +08:00
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
2023-11-01 10:28:54 +08:00
sigoden
64202758ec
chore: move split_line_* from repl/cmd.rs to utils/ ( #190 )
2023-10-31 18:34:38 +08:00
sigoden
bd3fc8e657
chore: refactor config description
2023-10-31 17:34:16 +08:00
sigoden
a137483b03
feat: improve client ( #189 )
2023-10-31 16:50:08 +08:00
sigoden
36380475d5
feat: support azure-openai ( #166 )
2023-10-31 06:36:52 +08:00
sigoden
eb023e5759
chore: rename config.yaml to config.example.yaml
2023-10-30 19:57:45 +08:00
