What does the create-llama CLI tool create and how to integrate it into an existing app?
What does the create-llama CLI tool create and how to integrate it into an existing app?
At a glance
The community member is looking to use the create-llama CLI tool to integrate with their existing FastAPI backend, vector database, and graph database (Neo4j). They want to use LLM and the Llama Index to extract nodes and properties from their graph database. The community members are unsure how to integrate the create-llama tool with their existing setup, and are looking for guidance or tutorials on the best approach. The comments suggest that the create-llama tool may not be the right fit, as its backend is tightly coupled to the frontend it generates. The community members are advised to build the Llama Index integration directly into their FastAPI backend, and some suggestions are provided on how to make this scalable using a job queue and workers, or to do the processing directly in the FastAPI server. The community members are interested in a more detailed tutorial or demonstration on implementing the Llama Index in their backend.
hi gurus! I'm looking to try out the create-llama CLI tool but I'm not sure what it creates or how to integrate what it generates into an existing app. I already have a FastAPI backend and vector db and graph db setup and now I want to build the llama index layer to manage chunking and inserting/retrieval etc. I'm using Neo4j for graph db and have all the nodes and relationships specified and I want to use LLM and llama index to extract the nodes and properties. Can someone point to a tutorial or blog post that might present the process I should adopt? Thanks kindly
thank you for shedding light. What approach do you recommend? I have everything built to extract documents and hand them off to llama index. Right now, I'm only interested in the chunking/embedding/upserting as I'm finalizing my ETL workflow. Once I get the ingestion solid I'll turn to the frontend. I want to use a custom embedding model.
Yeah, I think so. Can you point me to a more involved demonstration or tutorial for implementing llama index that breaks it down into backend services? or at least two services, one for vectors and one for graph? This is a report app, so the traffic/scaling is not an issue. the ETL will run once a day and the reports are generated once a day or once a week
