Javier Martinez
Javier Martinez
@mlbrnm can you open a PR with that fix to prevent it? I prefer remove keep_alive to have a problem with channel, connection or whatever
It is a problem related to the async implementation of Ollama in llama-index... Can you try to move to sync version until we have a solution?
Could you provide more details about what you are trying to run? Please check our documentation, which includes installation instructions and how to run the application: [Setup and Configuration](https://docs.privategpt.dev/installation/getting-started/main-concepts#setups-and-configuration). Here's...
Llama index has been bumped... I will update Llama Index to fix all dependencies issues.
Can you try to resaving in another encoding and reuploading? Using UTF-8 should work without any issue
Can you try to save using other format xlsx vs xls? It should work without problem. Are there any non-ascii char in the document?
Can you give us more details about your environment? Probably, it will related to GPU and vRAM.
It should work equally using postman and requests. Can you increate request timeout? ``` client = PrivateGPTApi(base_url="http://localhost:8001", client=...) ``` And two mode things to take into account: 1. When you...
Can you share more details, e.g. environment, machine, SO, complete stack trace, etc?
What do you want to do with chunking? Right now, chunking is by sentence, so each document should generate N chunks that it should be interoperable. If no enough chunks...