Commit Graph

300 Commits

Author SHA1 Message Date
sigoden
6286251d32
feat: support gemini (#273) 2023-12-19 20:37:53 +08:00
sigoden
3adfeb1ae7 chore: change order of openai models 2023-12-16 03:15:43 +00:00
sigoden
65ab8c1d6f chore: update issue template 2023-12-13 22:52:40 +00:00
sigoden
27cae9582f
fix: cannot read image with uppercase ext (#270) 2023-12-14 06:15:01 +08:00
sigoden
10e3b6d234
chore: update change session error message (#267) 2023-12-13 08:11:10 +08:00
sigoden
e4d301f3d7
fix: pipe failed on macos (#264) 2023-12-08 07:42:47 +08:00
sigoden
e7272398dd
feat: change REPL indicators (#263) 2023-12-08 07:03:42 +08:00
sigoden
075631d794 chore: release v0.11.0 2023-11-29 11:00:00 +08:00
sigoden
30e2fd62dc chore: update deps 2023-11-29 10:38:16 +08:00
sigoden
eb8a150539 chore: improve readme 2023-11-28 11:59:02 +08:00
sigoden
ee5fbe629c
feat: allow shift-tab to select prev in completion menu (#254) 2023-11-27 19:08:33 +08:00
sigoden
0afef991f9 chore: update cli description and readme 2023-11-27 18:02:52 +08:00
sigoden
c58912ba64
refactor: sort of some complete type (#253) 2023-11-27 17:22:16 +08:00
sigoden
18f16c6511
feat: add ernie:ernie-bot-8k qianwen:qwen-max (#252) 2023-11-27 16:06:35 +08:00
sigoden
2508d56598
feat: state-aware completer (#251) 2023-11-27 15:39:55 +08:00
sigoden
25e545474f
chore: upgrade deps (#250) 2023-11-27 14:20:02 +08:00
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
2023-11-27 14:04:50 +08:00
sigoden
5bfe95d311
refactor: trim trailing spaces from the role prompt (#246) 2023-11-14 11:58:56 +08:00
sigoden
8f1d8dec5f
refactor: palm client system message (#245) 2023-11-14 10:34:42 +08:00
sigoden
e118e864d5
refactor: ernie client system message (#244) 2023-11-14 10:03:01 +08:00
sigoden
9b0fbe3506
fix: the last reply tokens was not highlighted (#243) 2023-11-14 08:53:21 +08:00
sigoden
542dcfe6f6
feat: extend .read to support files and messages (#242) 2023-11-13 19:53:24 +08:00
sigoden
757c192829
refactor: qianwen client use incremental_output (#240) 2023-11-09 08:55:52 +08:00
sigoden
01cf8acb81
refactor: improve code quanity (#238) 2023-11-08 22:20:46 +08:00
sigoden
b40659613d
feat: add a spinner to indicate waiting for response (#236) 2023-11-08 20:36:30 +08:00
sigoden
eb30d90391
refactor: improve render (#235)
* refactor: redesign render

- if stdout is not terminal, just write reply text to stdout
- rename repl_render_stream to markdown_stream
- deprecate cmd_render_stream
- use raw_stream to just print streaming reply text

* optimize rendering error

* optimize render_stream
2023-11-08 18:26:38 +08:00
sigoden
a8a504e0f0 chore: release v0.10.0 2023-11-08 11:46:30 +08:00
sigoden
c99dd5a2ff
feat: add openai:gpt-4-1106-preview (#233) 2023-11-08 11:39:27 +08:00
sigoden
15efa17963
refactor: use ::: as multipline input indicator, deprecate """ (#232) 2023-11-08 11:19:45 +08:00
sigoden
819f50d9b1
fix: unexpected additional newline in REPL (#231) 2023-11-08 08:24:27 +08:00
sigoden
e8461b8462
refactor: output info includes auto_copy and light_theme (#230) 2023-11-08 07:08:48 +08:00
sigoden
c99bd015aa
feat: temporarily use a role to send a message (#227) 2023-11-07 23:07:42 +08:00
sigoden
c256b6bae5
refactor: improve repl completer (#226) 2023-11-07 22:18:59 +08:00
sigoden
b07a112f89
feat: deprecate .edit, use """ instead (#225) 2023-11-07 21:45:36 +08:00
sigoden
6bb2ec05be
feat: add config.prelude to allow setting default role/session (#224) 2023-11-07 19:14:58 +08:00
sigoden
534733b77c
fix: unable to build on android using termux (#222) 2023-11-07 16:36:40 +08:00
sigoden
d40f104f66
feat: allow the use of an unlisted model (#219) 2023-11-07 11:54:56 +08:00
sigoden
9a8b302432
refactor: remove Model.client_index, match client by name (#218) 2023-11-07 10:56:28 +08:00
sigoden
87aec71e08
refactor: use &GlobalConfig to avoid clone (#217) 2023-11-07 10:21:17 +08:00
sigoden
81624f7267
refactor: rename Model.llm_name to name (#216) 2023-11-07 09:55:06 +08:00
sigoden
399ed3337f
refactor: improve error message for PaLM client (#213) 2023-11-06 19:37:45 +08:00
sigoden
5dabe723ed chore: release v0.9.0 2023-11-06 15:41:00 +08:00
sigoden
9bb259ee96
chore: add issue tempalte model_request.md (#212)
* chore: add issue tempalte model_request.md

* update label
2023-11-04 10:09:40 +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
887bf0a744
fix: fix rendering markdown in REPL (#207) 2023-11-03 18:36:17 +08:00
sigoden
811e605fbf
fix: don't ignore '\n\n' reply at begin (#206) 2023-11-03 13:41:03 +08:00
sigoden
c20cd20d53
fix: wrap and tokenize algorithm (#205)
* fix: wrap and tokenize algorithm

* update tests

* remove unnecessary tokenize from tiktoken
2023-11-03 12:30:40 +08:00