Commit Graph

258 Commits (774d991144915368f9eee9740091448b92c17e62)

Author SHA1 Message Date
sigoden 774d991144
feat: support moonshot (#369) 6 months ago
sigoden 527da63d18
refactor: do not automatically convert temperature value (#368) 6 months ago
sigoden 4d52479545
fix: vertexai model names (#365) 7 months ago
sigoden 7279e43141
fix: color on non-truecolor terminal (#363)
* fix: color on non-truecolor terminal

* make ansicolor lower contrast
7 months ago
Chief Marlin 8681895944
fix: misspelled mistral model name (#359) 7 months ago
sigoden 50c03e4fdc
feat: update ernie models (#357) 7 months ago
sigoden f3210d622a
refactor: remove role field from session struct (#356) 7 months ago
sigoden 992d570041
refactor: cleanup the deprecated repl commands (#355) 7 months ago
sigoden 930d8c12ab
feat: new model claude:claude-3-haiku-20240307 (#353) 7 months ago
sigoden aed243c3aa
feat: allow use of temporary role in a session (#348) 7 months ago
sigoden 8f14498969
fix: erratic behaviour when using temp role in a session (#347) 7 months ago
sigoden 2404a619e4 chore: update deps 7 months ago
sigoden d5b10ea0c1 chore: fix typos 7 months ago
sigoden f82f577b6d
feat: add nushell integration (#344) 7 months ago
sigoden 46cb320aa5 chore: spell check 7 months ago
sigoden 20c78d6f15
feat: add new ernie models (#340) 7 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`
7 months ago
sigoden be4e5e569a
feat: support claude-3 (#336) 7 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
7 months ago
sigoden 9e15a3409e
feat: reduce gemini blocking of unsafe content with safetySettings (#334) 7 months ago
sigoden e443905dc1
feat: add `.clear messages` to clear session messages (#332) 7 months ago
sigoden 7e32787dba chore: improve code quanity on ReplCommand/State 7 months ago
sigoden 8421f23b45
feat: allow overriding execute/code role (#331) 7 months ago
sigoden b2f86f2899
refactor: auto_copy works when executing command (#328) 7 months ago
sigoden 3c16aff591
feat: add `-c/--code` to generate only code (#327) 7 months ago
sigoden bc3cbce2f4
refactor: enhanced shell support (#326) 7 months ago
sigoden bbb13d8227 chore: improve openai api error handling 7 months ago
sigoden 7633940e03 chore: update order of openai models 7 months ago
sigoden 75fe0b9205
feat: support mistral (#324) 7 months ago
sigoden c538533014
feat: support claude (#278) 7 months ago
sigoden c773e8d2e1
refactor: improve saving messages (#322) 7 months ago
sigoden a3fbf71c1c chore: improve execute commands prompt 7 months ago
sigoden 21d1be5bed
refactor: improve prompt error handling (#319) 7 months ago
sigoden 16b7ac071f chore: update deps and readme 7 months ago
sigoden 7638412128
feat: support `-e/--execute` to execute shell command (#318) 7 months ago
sigoden 6c0204e696
refactor: change header of messages saved to markdown (#317) 7 months ago
sigoden 373b34ef5c
feat: edit current prompt on $VISUAL/$EDITOR (#314) 7 months ago
sigoden 179a5f5749
refactor: update vertexai/gemini/ernie clients (#309) 8 months ago
sigoden 5e4210980d
feat: support vertexai (#308) 8 months ago
sigoden 3bf0c371e4
feat: update openai/qianwen/gemini models (#306) 8 months ago
Joseph Goulden 25b27c148a
fix: do not attempt to deserialize zero byte chunks in ollama stream (#303) 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>
8 months ago
sigoden a30c3cc4c1
feat: add openai.api_base config (#302) 8 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
Nicola Coretti 4e99df4c1b
fix: deprecation warning of .read command (#296) 9 months ago
sigoden 0e5c8567d4
refactor: ollam api_base configuration (#285) 9 months ago
sigoden 1c9ca1b002
feat: custom REPL prompt (#283) 9 months ago
sigoden 89fefb4d1a
refactor: remove path existence indicator from info (#282) 9 months ago
sigoden 6280f5ab4b
feat: qianwen vision models support embeded images (#277) 10 months ago
sigoden 64c4edf7c8
feat: support ollama (#276) 10 months ago