Anirban Kar
6494f5ac2e
fix: updated logger and model caching minor bugfix #release ( #895 )
...
* fix: updated logger and model caching
* usage token stream issue fix
* minor changes
* updated starter template change to fix the app title
* starter template bigfix
* fixed hydretion errors and raw logs
* removed raw log
* made auto select template false by default
* more cleaner logs and updated logic to call dynamicModels only if not found in static models
* updated starter template instructions
* browser console log improved for firefox
* provider icons fix icons
2024-12-31 22:47:32 +05:30
Anirban Kar
fc4f89f806
feat: add Starter template menu in homepage ( #884 )
...
* added icons and component
* updated unocss to add dynamic icons
* removed temp logs
* updated readme
2024-12-24 22:37:28 +05:30
Anirban Kar
7295352a98
refactor: refactored LLM Providers: Adapting Modular Approach ( #832 )
...
* refactor: Refactoring Providers to have providers as modules
* updated package and lock file
* added grok model back
* updated registry system
2024-12-21 11:45:17 +05:30
Anirban Kar
a53b10ff39
Merge pull request #800 from gokulkgm/xai-update
...
feat: add xAI grok-2-1212 model
2024-12-19 21:22:52 +05:30
Anirban Kar
b892d708ec
removed logs and openAI fix
2024-12-18 21:55:17 +05:30
Anirban Kar
283eb22ae5
added indicator on settings menu
2024-12-18 20:04:43 +05:30
Anirban Kar
62ebfe51a6
fix: .env file baseUrl Issue
2024-12-18 16:34:18 +05:30
GK
8d0f0da04a
add: xAI grok-2-1212 model
2024-12-17 17:31:10 +00:00
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
