I think i found a bug in KnowledgeGraphRAGRetriever code, it will get the "graph_query_synthesis_prompt" into "KnowledgeGraphQueryEngine" from kwargs but also leave it in the kwargs, result in TypeError: llama_index.query_engine.knowledge_graph_query_engine.KnowledgeGraphQueryEngine() got multiple values for keyword argument 'graph_query_synthesis_prompt'

I am building an index with 300k documents, is it possible to see the progress of building? like tqdm metric?

I have a graph stored in neo4j graph database, is it possible to query the graph with llama index? I saw you could only build a new graph out of documents but not using existing graph

Is it possible to make a wrapper for model LLM and use my own API for embedding and prediction?

How to stream response but not printing it?
this


will print the output, I want to pass it to a chatbot

Hello, i've build an index, is there a way to query it but just return the top k relevant nodes without the generated response step?

I can't find a doc on how to implement streaming for custom LLM, the CompletionResponseGen section is not implemented in the doc

Ok found it - https://gpt-index.readthedocs.io/en/latest/core_modules/query_modules/retriever/root.html