Commit Graph

515 Commits

Author SHA1 Message Date
Cohee 576352817e Merge branch 'staging' into tool-calling 2024-10-03 22:36:02 +03:00
Cohee da9200c82e Skip adding tool messages as regular chats 2024-10-03 12:59:59 +00:00
Cohee 6706cce10d Groq: Add new models and multimodal captions 2024-10-03 08:41:45 +03:00
Cohee 0f8c1fa95d Save tool calls to visible chats. 2024-10-02 22:17:27 +03:00
Cohee e8b9720425 Budgeting fix 2024-10-02 01:56:27 +03:00
Cohee c94c06ed4d Implement function tool calling for OpenAI 2024-10-02 01:45:57 +03:00
Cohee 8006795897 New tool calling framework 2024-10-02 01:00:48 +03:00
Cohee 7ac7398568 Remove debug log. Fix comment 2024-10-01 00:37:33 +03:00
Carsten Kragelund 4966fb65f7 fix: add assistant_prefill to request if people are using non prefill based continues 2024-09-28 22:46:23 +00:00
Carsten Kragelund aae934a849 fix: move prefill continuation handling to populateChatHistory 2024-09-28 22:37:16 +00:00
Cohee 6608f5dd95 Fix the use of stop strings for Gemini 2024-09-24 22:18:28 +03:00
Cohee 8c39e20ed9 Merge branch 'staging' into deprecate-cc-or-instruct 2024-09-24 21:19:03 +03:00
M0cho 2ee3eb7004 Support gemini-1.5-series-002 and new 8B exp model 2024-09-25 02:58:56 +09:00
Cohee 94977e71ff Merge OpenAI init functions 2024-09-22 12:29:32 +03:00
Cohee d3408c496f Change a log type for empty prompt messages 2024-09-21 16:23:59 +03:00
Cohee 82b0733d88 Allow setting role, position and depth for marker prompts 2024-09-18 21:51:10 +03:00
Cohee 60df924bec MistralAI: Add Pixtral to models and captioning 2024-09-17 21:44:25 +03:00
Cohee ca4d3c5ffe
Refactor instruct names behavior controls (#2837)
* Refactor instruct names behavior controls
Closes #2819

* Remove current persona from force names

* Don't add current user name in groups

* Revert to old text

* Add titles to names behavior

* Proper default for names_behavior
2024-09-16 00:46:03 +03:00
Cohee 44cc81fa73 Save models before emitting status change 2024-09-15 18:14:40 +03:00
Cohee 30af741c3e Deprecated forced instruct on OpenRouter for Chat Completion 2024-09-15 10:54:12 +03:00
Cohee eeee206887 Fix logit_bias comment 2024-09-13 21:03:04 +03:00
Cohee db2b356942 Remove stop for o1 2024-09-13 20:47:41 +03:00
Cohee 45cfc532b1 Redirect max_tokens to max_completion_tokens 2024-09-13 19:56:48 +03:00
Cohee 6d79cc015a Add OpenAI o1 2024-09-13 19:44:12 +03:00
Cohee be145c0bff Add missing return type 2024-09-08 17:24:42 +03:00
Cohee 8bb964515a Fix Gemini multimodal with JPG images
Fixes #2763
2024-09-08 10:48:28 +03:00
Cohee 6f9846a290 #2763 Add error handler to image token cost calculation 2024-09-08 02:16:54 +03:00
Cohee ac0c33eb76 Use CSS.supports to determine auto-fit validity 2024-09-05 20:00:45 +03:00
Cohee b9543054d8 Chat Completion: Increase unlocked context size 2024-08-30 21:47:26 +03:00
Cohee f155b83792 Cohere: new cmd-r models 2024-08-30 20:00:42 +03:00
Cohee 7aaabbd2bb Personas: fix duplication in Chat Completions 2024-08-28 22:44:26 +03:00
Cohee 07a6e1aa53
Merge pull request #2708 from Yokayo/staging
Update ru-ru translation
2024-08-28 21:23:45 +03:00
Cohee c820d5f56a Reformat code 2024-08-28 21:20:21 +03:00
M0cho 268aeb0ae5 Support gemini-1.5-exp-0827 2024-08-28 08:24:04 +09:00
Cohee c45e212b31 Fix negative penalties 2024-08-27 09:19:05 +00:00
Cohee e8de36a0d0 Cohere: limit penalties 2024-08-27 12:03:40 +03:00
Cohee 662e29911c Fix default model when loading preset 2024-08-26 17:34:54 +03:00
Cohee 7d4b3e0800 Use J1.5 Large by default 2024-08-26 12:11:29 +03:00
Cohee 5fc16a2474 New AI21 Jamba + tokenizer 2024-08-26 12:07:36 +03:00
Yokayo 383d46fe4d Work on tl 2024-08-26 01:39:56 +07:00
Cohee 06e3d5f8de Rename MakerSuite => AI Studio 2024-08-21 21:00:17 +03:00
err d02677feec
enable vision for chatgpt-4o-latest 2024-08-17 17:07:29 +02:00
Cohee bc7ac12317 New ChatGPT model 2024-08-14 20:31:25 +03:00
Cohee 2ef9d374ec Chat Completion: Don't insert group nudge when impersonating
Closes #2588
2024-08-11 20:55:59 +03:00
Cohee 8df27254fd
Merge pull request #2640 from edk208/release
Adding Block Entropy API endpoints for chat, image, and video generation
2024-08-11 16:19:14 +03:00
Cohee fcfa15a5ad Add model to presets. Fix restoration on app load 2024-08-11 16:18:24 +03:00
Edward Kim 41247740b1 fixed model in max context 2024-08-10 22:00:26 -04:00
Edward Kim 88ada0f67d fixed ordering in image generation source, and max token length for llm models 2024-08-10 21:55:52 -04:00
splitclover dcfeb837a8 Add await to events 2024-08-10 00:44:01 +02:00
splitclover 754752c80a Added chat completion import/export events 2024-08-09 23:49:18 +02:00