Verba
Verba copied to clipboard
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
## Description I suggest versioning up libraries. ## Is this a bug or a feature? - [ ] Bug - [x] Feature ## Steps to Reproduce ## Additional context -...
## Description I uploaded a 26 MB .txt file using OllamaEmbedder. Now, when I try to select the file in the "Documents" section, my browser freezes, preventing me from deleting...
## Description Using a pure-local config with Ollama and Unstructured in Docker I can import CSV data and interact with it (win!): OLLAMA_URL="http://192.168.2.204:9350" OLLAMA_MODEL="llama3" OLLAMA_EMBED_MODEL="mxbai-embed-large" UNSTRUCTURED_API_URL="http://192.168.2.216:9360/general/v0/general" UNSTRUCTURED_API_KEY="pseudokey" Problem: When importing...
As shown in the title, if you allow me to translate it into Chinese, please let me know the location of the original language storage or send me all the...
## Description Error in chat and importing documents: HTTPConnectionPool(host='host.docker.internal' I've seen similar issues to mine but not exactly the same setup so thought I'd post mine here. ## Is this...
urllib3.exceptions.NameResolutionError: : Failed to resolve 'openaipublic.blob.core.windows.net' ([Errno -3] Temporary failure in name resolution) The above exception was the direct cause of the following exception: Traceback (most recent call last): File...
## Description Window retriever uses weaviate autocut(1). It delivers too few results for my use case, and probably others. It would be good if this was please customisable between like...
## Description The current way of ingesting files is static and must be done manually in the UI. In my opinion, it would be awesome to be able to "watch"...
## Description I've imported multiple documents with the same filename - README.md. The window retriever seems to be randomly mixing up chunks from each of them into one document retrieval...
Hi. I want to use Ollama fully for answers and vectorization, but have run into a vectorization problem. I created an .env where I specified: OLLAMA_URL=http://ollama.ai.local OLLAMA_MODEL=llama3:8b-instruct-q8_0 OLLAMA_EMBED_MODEL=nomic-embed-text:latest When I...