arty-hlr
arty-hlr
Hi, Using `mlx_audio.server`, I noticed while trying out different voices that they weren't unloaded as the new one was being loaded:  This can lead to heavy RAM usage as...
Hi, I saw the following error in the logs: ``` ⨯ unhandledRejection: Error: 400 The model `llama-3.3-70b-specdec` has been decommissioned and is no longer supported. Please refer to https://console.groq.com/docs/deprecations for...
**Describe the bug** When clicking on a PDF source after attaching it and asking a question about it, which seems to work, the citations seem to be correct, but they...
Running `lms chat --verbose` should return usage info at least like in the GUI, like the stats shown when hovering over **?**:  Example from `ollama run MODEL --verbose`: 
### Installation Method Local Installation ### The Problem When using `/api/v1/general/split-pages` with a range in the `pageNumbers` parameter, the files in the resulting zip files do not respect the given...
### What did you do when it broke? I added the ollama and lmstudio (openai compatible) providers in the config: and added the models under language models: ### How did...
### Feature Description Instead of having to add each model independently, could it maybe be possible to have a drop down list with available models per provider? A search on...
**Describe the bug** Perplexica is not able to connect to LM Studio with this configuration: Trying `https://lmstudio.macstudio.lan/v1` gives the same result: The logs don't say much more unfortunately: ``` Failed...
Hi, While trying to use speaches on macOS, I was met with the following issues. Thanks for your help in advance! ## Python I am trying to install this on...
Hi, Great work on the API and UI! I just had a few questions: ## Voices in the UI I don't see an option to choose the voice in the...