| 7431ac06 | 26-Apr-2026 |
Eduardo Mozart de Oliveira <2974895+eduardomozart@users.noreply.github.com> |
Refactor models.json to remove deprecated models
Removed several outdated models and updated descriptions and prices for existing models. |
| 6d9a7680 | 26-Apr-2026 |
Eduardo Mozart de Oliveira <2974895+eduardomozart@users.noreply.github.com> |
Add inputTokenPrice and new embeddings to models.json |
| 9d5f0516 | 26-Apr-2026 |
Eduardo Mozart de Oliveira <2974895+eduardomozart@users.noreply.github.com> |
Add new Gemini models with updated parameters |
| b9715443 | 09-Apr-2026 |
Andreas Gohr <gohr@cosmocode.de> |
updated models info |
| c6ae286a | 21-Jan-2026 |
Eduardo Mozart de Oliveira <2974895+eduardomozart@users.noreply.github.com> |
Update Gemini model configurations
Updated model configurations to include new Gemini versions and removed outdated ones. |
| 332eea25 | 11-Jun-2025 |
Andreas Gohr <gohr@cosmocode.de> |
fixes based on tests, improve tests |
| 2e22aefb | 15-Apr-2025 |
Andreas Gohr <andi@splitbrain.org> |
introduce a "Generic" model
This is basically an OpenAI implementation, which then can be reused by most other providers since they usually implement a somewhat compatible API. The API URL can be se
introduce a "Generic" model
This is basically an OpenAI implementation, which then can be reused by most other providers since they usually implement a somewhat compatible API. The API URL can be set manually so it should be easy to add new unsupported providers.
show more ...
|
| c7364d3d | 01-Apr-2025 |
Andreas Gohr <andi@splitbrain.org> |
rewrite roles for Gemini
Gemini expects the role model instead of assistant. Older models allowed both, the newer ones not. |
| 5835c70b | 27-Mar-2025 |
Andreas Gohr <andi@splitbrain.org> |
updated model data |
| 42b2c6e8 | 12-Mar-2025 |
Andreas Gohr <andi@splitbrain.org> |
add remote component to ask questions to the bot
The endpoint allows to override model and language settings on demand. |
| da493c96 | 06-Feb-2025 |
Andreas Gohr <andi@splitbrain.org> |
some model updates
still not 100% uptodate |
| 4dd0657e | 06-Feb-2025 |
Andreas Gohr <andi@splitbrain.org> |
allow to set arbitrary models
We now initialize a model configuration even if we have no info in model.json using some default values for the token limits.
Models can implement the loadUnkonwModelI
allow to set arbitrary models
We now initialize a model configuration even if we have no info in model.json using some default values for the token limits.
Models can implement the loadUnkonwModelInfo() method to fetch the info from an API if such a thing exist. Implemented for gemini and ollama currently.
show more ...
|
| 10789c17 | 14-Nov-2024 |
Andreas Gohr <andi@splitbrain.org> |
support the Google Gemini API |