Commit Graph

85 Commits

Author SHA1 Message Date
Anirban Kar
c3c9e43935
Merge branch 'main' into fix-variable-name 2024-12-16 19:53:01 +05:30
Dustin Loring
2819911b96 Update constants.ts
fixes the 'WARN Constants Failed to get LMStudio models:  fetch failed' error as the user most likely just has it active in provider
2024-12-15 15:25:31 -05:00
Anirban Kar
885e104f27 added auto detect branch name and version tag 2024-12-16 01:54:24 +05:30
Anirban Kar
86f37fcaca
Merge branch 'main' into perplexity-models 2024-12-15 15:15:01 +05:30
Dustin Loring
ece0213500
add: Groq Llama 3.2 90B Vision Preview
Add 90b llama-3.2 model for better performance
2024-12-14 11:06:59 -05:00
Dustin Loring
eb53146937
add: groq-llama3.3-70b
add: Groq Llama 3.3 70B
removed Groq Llama 3.1 70B (deprecated)
2024-12-14 09:59:38 -05:00
Meet Patel
8bcd82c9d4 feat: added perplexity model 2024-12-14 11:59:10 +05:30
Anirban Kar
456c89429a fix: removed context optimization temporarily, to be moved to optional from menu 2024-12-14 02:25:36 +05:30
Dustin Loring
32409047ff Update constants.ts
Removed Llama3.1 70B and replaced it with Llama3.3-70B
2024-12-13 14:48:02 -05:00
Dustin Loring
ba1b5543db fix: LM Studio sending messgae
LM Studio was not able to send a message now it is.
2024-12-13 11:03:55 -05:00
Stijnus
e39f16e436 Settings UI enhancement
Date & Time Display
Added a real-time clock component in the sidebar

Event Logs System
Implemented an EventLogsTab component for system monitoring
Provides a structured way to:
Track user interactions
Monitor system events
Display activity history
2024-12-13 01:11:35 +01:00
eduardruzga
46a90c246b Add gemini flash 2.0 2024-12-11 21:03:45 +02:00
eduardruzga
17e500344a merge 2024-12-11 20:02:07 +02:00
Anirban Kar
5d4b860c94 updated to adapth baseurl setup 2024-12-11 14:02:21 +05:30
Anirban Kar
7ba734571e some more logs cleanup 2024-12-10 23:09:59 +05:30
Anirban Kar
af09104c82 moved log to only print on change, and changed error logs to warnings 2024-12-10 23:02:54 +05:30
Eduard Ruzga
9758e6c2a0
Merge pull request #573 from kekePower/update-gemini-models
Update to Gemini exp-1206
2024-12-09 09:42:15 +02:00
Stig-Ørjan Smelror
15a955e995 Update to Gemini exp-1206 2024-12-06 20:34:14 +01:00
Ibrahim H.
a2da05e9cb
Add 90b llama-3.2 model for better performance
Add support for `llama-3.2-90b-vision-preview` model from Groq.
2024-12-06 17:08:19 +01:00
Anirban Kar
7efad13284 list fix 2024-12-06 16:58:04 +05:30
Anirban Kar
7192690c1c clean up 2024-12-03 02:19:30 +05:30
Anirban Kar
1589d2a8f5 feat(Dynamic Models): together AI Dynamic Models 2024-12-03 02:13:33 +05:30
Dustin Loring
4250fa9834 pre commit lint 2024-12-01 15:17:02 -05:00
Dustin Loring
92918d1c14
Merge pull request #7 from ibrain-one/feature/307-together-ai-integration
feat: add Together AI integration and provider implementation guide
2024-12-01 11:34:37 -05:00
Dustin Loring
e187e48f4b
Merge pull request #23 from dustinwloring1988/prompt-caching
Prompt caching
2024-12-01 08:53:20 -05:00
Dustin Loring
b0b617dac7 lint fix 2024-12-01 07:57:42 -05:00
Dustin Loring
78d5202360
Merge pull request #10 from SujalXplores/feat/prompt-caching
Feat/prompt caching
2024-12-01 07:31:40 -05:00
Dustin Loring
416f7f9097
Update constants.ts 2024-12-01 07:15:25 -05:00
Dustin Loring
61c2a8b325 fix 2024-11-29 13:12:47 -05:00
SujalXplores
394d1439c1 feat: prompt caching 2024-11-27 00:17:00 +05:30
Sujal Shah
12dcb8deb3 fix: add browser environment check for local API calls 2024-11-25 17:54:29 +05:30
Sujal Shah
f94165a421 fix: silent eslint issues 2024-11-25 14:00:18 +05:30
Martin Ouimet
76cc7a8139 feat: add Together AI integration and provider implementation guide
- Create detailed provider implementation guide with:
  - Architecture overview and implementation steps
  - Configuration patterns and best practices
  - Testing checklist and Docker integration guide
  - Example using Together AI implementation
- Add Together AI as new provider with:
  - Environment variables and Docker configuration
  - Support for Qwen, Llama, and Mixtral models
  - API key and base URL management
  - OpenAI-compatible API integration
2024-11-23 00:20:35 -05:00
Oliver Jägle
4589014bda
Merge remote-tracking branch 'upstream/main' into linting 2024-11-22 20:38:58 +01:00
Eduard Ruzga
753f0b3638
Merge pull request #380 from kekePower/update-huggingface-models
Added 3 new models to Huggingface
2024-11-22 21:16:16 +02:00
Stig-Ørjan Smelror
bff2922067 Added 3 new models to Huggingface 2024-11-22 19:17:01 +01:00
Oliver Jägle
f63474ec9a
Merge remote-tracking branch 'upstream/main' into linting 2024-11-22 17:36:35 +01:00
Oliver Jägle
7d8f811886
Fix linting issues 2024-11-22 09:49:45 +01:00
Stig-Ørjan Smelror
5997d31aa3 Update to Gemini exp-1121 2024-11-22 07:15:04 +01:00
Oliver Jägle
2327de3810
Lint-fix all files in app 2024-11-21 22:05:35 +01:00
Raiyan Hasan
eabfbb2220 max token is now dynamically handle for each model 2024-11-20 21:41:51 +05:30
Raiyan Hasan
d41a0ac2c2 Cohere support added 2024-11-20 15:08:42 +00:00
Eduard Ruzga
88700c2452
Merge pull request #338 from kekePower/kekePower/update-google-models
Update the Google Gemini models list
2024-11-20 09:41:03 +02:00
Stig-Ørjan Smelror
b945ec8d2c Fix the list of names to include the correct model 2024-11-19 20:24:52 +01:00
Stig-Ørjan Smelror
7a03b26473 Update the Google Gemini models list 2024-11-19 20:21:27 +01:00
ahsan3219
7bf9c5c1b6 Huggingface Models Integrated 2024-11-18 04:49:02 +05:00
eduardruzga
d21ddf0080 One more fix 2024-11-14 15:37:41 +02:00
eduardruzga
df91d0edc0 More type fixes 2024-11-14 14:29:47 +02:00
eduardruzga
b0754e546b TypeCheck fix 2024-11-14 09:52:37 +02:00
eduardruzga
feb19509f6 Added dynamic openrouter model list 2024-11-13 22:21:50 +02:00