yetone
3ec847e3cb
fix(ci): lua lint ( #1035 )
2025-01-05 17:11:15 +08:00
Larry Lv
ec5d1abf34
fix(openai): support all o series models ( #1031 )
...
Before this change, since `max_completion_tokens` was not set for `o` series models, the completion request will time out sometimes. This makes sure it converts the `max_tokens` parameter to `max_completion_tokens` for `o` series models.
I tested this change with `gpt-4o-mini`, `o1-mini` and `o3-mini`, and they all still work as expected.
2025-01-05 13:23:33 +08:00
yetone
01e05a538b
fix: more reasonable error reporting ( #965 )
2024-12-18 23:16:41 +08:00
Aaron Batilo
e60ccd2db4
feat: enable streaming for o1 models ( #896 )
...
As of a few days ago, o1 models support streaming responses. Please see:
https://community.openai.com/t/openai-o1-streaming-now-available-api-access-for-tiers-1-5/1025430
2024-11-24 17:28:27 +08:00
yetone
9891b03656
fix(openai): user and assistant roles should be alternating ( #859 )
2024-11-17 03:49:02 +08:00
yetone
ff85b9c1e2
refactor: remove redundant local field to facilitate provider configuration ( #858 )
2024-11-17 02:55:40 +08:00
yetone
4acdcb6e8b
fix: provider inherited_from ( #857 )
2024-11-17 01:09:33 +08:00
yetone
dfc51b3247
feat: add url_join ( #856 )
2024-11-17 00:39:03 +08:00
insects
ecaf850859
fix(compat): filter out non value and not user message ( #818 )
...
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-07 05:38:56 -05:00
insects
ec9b00db8b
fix(openai): add backward compat for get_user_message ( #813 )
...
Co-authored-by: ming.chen <ming.chen@shopee.com>
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
2024-11-07 02:16:19 -05:00
yetone
1e8abbf798
feat: memory 🧠 ( #793 )
2024-11-04 16:20:28 +08:00
Aaron Batilo
f92c3a60f3
fix: support legacy finish_reason ( #706 )
...
Many OpenAI compatible alternative servers are still returning a
`finish_reason` of `eos_token` instead of `stop`. This commit adds
support for that to support more of these servers/options.
2024-10-11 21:46:34 +08:00
Sapir Shemer
d74c9d0417
feat: supports openai o1-preview
...
* feat: make O1 models on openai work by handle non-streams & correct
parameters
* chore: set temperature automatically when using o1 models
2024-09-27 21:08:10 +08:00
Aaron Pham
2b89f0d529
perf(anthropic): prompt-caching ( #517 )
...
bring back prompt caching support on Anthropic
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-09-04 03:19:33 -04:00
Aaron Pham
e57a3f27df
chore(provider): use default value set in metaclass ( #503 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-09-03 21:56:52 -04:00
Aaron Pham
0d8098e4eb
fix(style): add parentheses ( #471 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-09-03 05:12:07 -04:00
Aaron Pham
e8c71d931e
chore: run stylua [generated] ( #460 )
...
* chore: add stylua
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* chore: running stylua
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
---------
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-09-03 04:19:54 -04:00
Aaron Pham
4ad913435c
feat(templates): avanterules filetype support ( closes #254 ) ( #466 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-09-03 04:09:13 -04:00
Aaron Pham
0557deeab7
feat: tokenizers ( #429 )
...
* feat: tokenizers
This reverts commit d5a4db8321d232a1b9c0d86fc38e8dd516d15776.
* fix(inputs): #422
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
---------
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-31 13:39:50 -04:00
yetone
d5a4db8321
Revert tokenizers ( #423 )
...
* Revert "fix: add missing "with" in README"
This reverts commit bf1e7f1f17c8b82687b15c41e5a8104ea03f70cf.
* Revert "feat: tokenizers (#407 )"
This reverts commit d2095ba267abbfe169582708a4449e609aa9709b.
2024-08-31 22:45:31 +08:00
Aaron Pham
d2095ba267
feat: tokenizers ( #407 )
...
* feat: autobuild tiktoken lib and schenanigans
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* chore: revert readme changes
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* fix(build): windows
Signed-off-by: Hanchin Hsieh <me@yuchanns.xyz>
* chore(plugin): early load commands and base setup
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* fix(build): make sync
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* feat: rust go vroom vroom
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* feat: scuffed afaf implementation binding go brrrr
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* chore: remove dups
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* fix(tokens): calculate whether we should do prompt_caching (fixes #416 )
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* chore: ignore lockfiles
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* Update README.md
* Update crates/avante-tokenizers/README.md
* chore: remove unused
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* chore: remove auto build
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
---------
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Hanchin Hsieh <me@yuchanns.xyz>
Co-authored-by: yuchanns <me@yuchanns.xyz>
2024-08-31 07:19:59 -04:00
Aaron Pham
5ff5dcf72b
chore(openai): add back support functions for ease-of-use ( #402 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-30 13:49:08 -04:00
Aaron Pham
b196627e86
chore(provider): use latest cohere models ( #400 )
...
Update prompts to correct grammar
concat with table.concat to avoid overhead
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-30 13:39:36 -04:00
yetone
104484f17c
fix: use the original prompts ( #397 )
2024-08-30 22:21:50 +08:00
yetone
fc1bcda822
fix: copilot message format ( #395 )
2024-08-30 19:25:04 +08:00
yetone
2997d4669a
refactor: refactor planning prompts to resolve line number issues and indentation issues ( #382 )
2024-08-30 18:53:49 +08:00
Aaron Pham
8a683b053b
fix(style): reformat ( #344 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-28 19:56:11 -04:00
Daniel Rodriguez
bb5411cd9a
fix(openai): first chunk emit errors ( #337 )
2024-08-28 18:36:50 -04:00
Aaron Pham
c635f73748
feat: pasting image within buffer ( #331 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-28 14:43:14 -04:00
Aaron Pham
755c15c0bd
chore(clipboard): separate logic to save as base64 and files ( #329 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-28 11:52:12 -04:00
Aaron Pham
d7be4a59c2
fix(openai): enable image support on OpenAI platform only ( fixes #282 ) ( #284 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-27 11:35:25 -04:00
Aaron Pham
971e61b2c8
feat(openai): support pasting image from clipboard ( #280 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-27 07:06:20 -04:00
Aaron Pham
a7d3defa3d
feat(llm): add support for parsing secret vault ( #200 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-24 17:52:38 -04:00
Coffee
1142c3c274
fix(openai): add support for Cloudflare's AI-Gateway ( #192 )
2024-08-24 12:32:16 -04:00
Aaron Pham
6475407d0d
fix(llm): persistent key check for override class ( #158 )
...
* fix(llm): make sure to allow passing custom module
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* fix: correct custom class
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
* fix: correct attribute
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
---------
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-22 23:52:49 -04:00
Aaron Pham
8d52229f16
refactor(llm): cleanup providers for future ops ( closes #134 ) ( #147 )
...
support allow_insecure and proxy ops
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-08-22 01:48:40 -04:00
