Parthasarathi Mukhopadhyay

Thanks Amanda. It is now much improved, and I tested it already the moment you posted this news in ***@***.*** I'll post in the ror forum in case any further...

Thanks for your response. 1. Is the vector store large enough that ChromaDB runs out of RAM? This could be the case if you have ingested many WARCs, or very...

@matteocargnelutti I find this section (VECTOR_SEARCH) in the .env file: ``` #------------------------------------------------------------------------------- # Vector Store / Search settings #------------------------------------------------------------------------------- VECTOR_SEARCH_COLLECTION_NAME="collection" VECTOR_SEARCH_SENTENCE_TRANSFORMER_MODEL="intfloat/e5-large-v2" # Can be any Sentence-Transformers compatible model available on...

@matteocargnelutti Thanks for the guidance. I reinstalled the new version (0.1.0) from scratch and it re-ingested my 6 warc files. All went very smooth. Additionally I deleted the cache generated...

@matteocargnelutti In my case the default settings is always producing a disabled "Ask' button. However if I change combinations in settings like change of model (llama2 or mistral), Search enabled/disabled....

Could this line be the reason (in ui.py) for disabled 'Ask' button in my case in versions 0.1.1 and 0.1.0 (until I change from llama to mistral or mistral to...

Great. I tested version 0.1.2, and it's performing well now - no disabled Ask button (although response time is still an issue for me). Now I understand your previous question:...

Thanks Ken :)