Find answers from the community

Updated 5 months ago

DLAI - Building Agentic RAG with Llamain...

At a glance

The community member is taking a course on building an agentic RAG (Retrieval Augmented Generation) with LlamaIndex and is looking for suggestions on which vector store to use for a multi-document agent. They are also interested in finding a cost-effective solution, as they are building an app for 200 users. The comments suggest that there are various options, including cloud-hosted (e.g., Pinecone) and self-hosted (e.g., Chroma, Qdrant, Weaviate) vector stores, and the community members are discussing whether to go for a cloud-hosted or self-hosted solution on AWS to minimize costs.

Useful resources
hey man,
https://learn.deeplearning.ai/courses/building-agentic-rag-with-llamaindex/lesson/1/introduction
I was going through the course how to implement it with a vector store. And which vector you suggest for multi-document agent. Also looking for something cheap
L
B
3 comments
I mean, its pretty much up to you. Some are cloud hosted (pinecone), some are local (chroma), others have options for both (qdrant, weaviate)
but any suggestion, building an app for 200 users. Keeping the cost as minimum as possible. Do you suggest to go for cloud hosted one or self hosting it on my aws?
Add a reply
Sign up and join the conversation on Discord