New Providers, Bug Fixes & Improvements #469
Replies: 4 comments 11 replies
-
|
Does this update add Gemini 2.5-flash support? |
Beta Was this translation helpful? Give feedback.
-
|
A breaking change, but only a patch number bump?! |
Beta Was this translation helpful? Give feedback.
-
|
Adding the configuration.yaml text here prevents home assistant from accessing other media. How do we ensure this is in addition to existing media (wallpapers, pictures etc) in the media folder rather than replacing them? EDIT: think I found a solution. If you have not manually specified media directories previously in configuration.yaml, you also need to add a second entry to include the default media folder: |
Beta Was this translation helpful? Give feedback.
-
|
I tried to switch my blueprint based automation to use What could the issue be? |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
1.5.1 Release Notes
This update adds native support for OpenRouter and Azure, fixes an issue with Google Gemini, adds support for GPT-5 models and adds Dutch and Polish translations.
Contributors
A huge thank you to our contributors @TheRealFalseReality, @NikNikovsky, @Minionguyjpro, @meceonzo—and of course everyone who helped test and provided feedback for the beta versions!
Timeline snapshots have moved from
/wwwto/media. add the following to yourconfiguration.yaml:💡 Make sure to create the
/mediaand the/llmvisioninside it before restarting!💡 Update LLM Vision Card to the latest version! Otherwise snapshots won't show correctly.
max_tokensis now displayed as aboxtype number selector rather than a slider. This change accommodates newer models that use thinking parameters counting towardmax_tokens. Unlike the limited slider, the box allows for inputting much larger numbers.💡If you notice empty responses, consider increasing
max_tokens.Integration
✨ Features
🔧 Improvements & Fixes
temperatureandtop_pfrom request when a gpt-5 model is used (GPT-5 not support temperature #437), (@valentinfrlch)/media. LLM Vision will attempt to migrate previously captured snapshots to the new folder.max_tokenslimit:max_tokensis now displayed as aboxtype number selector rather than a slider. This change allows for larger token limits, as thinking tokens count toward themax_tokenslimit. (@valentinfrlch)aiofilepackage to imports (aiofile package declaration missing in manifest.json #404), (@valentinfrlch)Blueprint
Update the blueprint by re-importing it from the Blueprint settings page in Home Assistant.
https://github.com/valentinfrlch/ha-llmvision/blob/main/blueprints/event_summary.yamlA huge thank you to @TheRealFalseReality for maintaining the blueprint!
✨ Features
🔧 Improvements & Fixes
/wwwto/media/llmvision/snapshots(LLMVision 1.5.1 Beta 3 and Blueprint 1.5.1 problem with snapshot-folder #457)This discussion was created from the release New Providers, Bug Fixes & Improvements.
Beta Was this translation helpful? Give feedback.
All reactions