Verba
Verba copied to clipboard
weaviate
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
I am not sure if this has been implemented already but I don't see I way to change this. If the RAG does not find relevant answers in the external...
## Description I have pulled the latest version and I am trying to deploy it locally using docker and I cannot get it work. It just keeps crashing and shutting...
⚠ Query failed: Invalid URL '/api/embeddings': No scheme supplied. Perhaps you meant https:///api/embeddings? INFO: 127.0.0.1:50092 - "POST /api/query HTTP/1.1" 500 Internal Server Error
First of all: I really enjoyed playing around with this. I got it all working and it's a lot of fun! I wanted to show some people in my office...
I went through the code and seems it will always try to use WCS. There is no way to provide a URL to self-hosted Weaviate in Verba.  Failed to...
## Description ## Installation - [ ] pip install goldenverba - [x] pip install from source - [ ] Docker installation If you installed via pip, please specify the version:...
## Description ## Installation - [ ] pip install goldenverba - [ ] pip install from source installed via pip, please specify the version: (24.2) ## Weaviate Deployment - [...
Hello, On the Import Config page, when I select the Chunker option as Code, I choose either the Python or PHP option. Then, I select a file with the .py...
## Description Add Llamaparse API to Verba ## Additional context https://docs.llamaindex.ai/en/stable/llama_cloud/llama_parse/
## Description I installed goldenverba following the instructions (pip install) I created the .env file: OLLAMA_URL=http://localhost:11434 OLLAMA_MODEL=llama3 when I start verba everyhting is wokring. The issue only is, I always...
