Rik Hendrix

> I first tried with mongodb but.. 2 weeks ago it was broken .. > > so tried with milvus- neo4j - redis .. neo4j is broken.. > > so...

> > I was thinking of posting how I improved Neo4j to become 5x faster and a lot less CPU heavy. > > please do.. I posted it, so I...

I might have something to note about this implementation. I have done something similar to this for my own LightRAG. For my own lightrag before a chunk gets send to...

Yes, I would also like to see the addition of the "metadata" tags to entities like "timestamp" or other relevant data. This should be appendable when uploading a document. This...

> [@fingeng](https://github.com/fingeng) not yet, have posted on the discord channel too but no replies yet. Can you send the discord link? I want to be in it.

> PR [#1258](https://github.com/HKUDS/LightRAG/pull/1258) introduce a batch operation to prevent making to many parallel query to database. Is that address this problem? Well yes kind of. The issue you linked talks...

Hi @danielaskdd , Just to clarify: when you mentioned “your suggestion,” are you specifically referring to combining the calls into one larger database call? I ask because when I implement...

I'm also fairly new to Milvus, so I had a chat with o3-mini and this was what the conclusion is in short: - **MinIO’s Role:** - Acts as the persistent,...

What exactly are you running? Can you show the code you have in your "ingest_demo.py"?

> the code works fine when using default storage settings: LIGHTRAG_KV_STORAGE=JsonKVStorage LIGHTRAG_VECTOR_STORAGE=NanoVectorDBStorage LIGHTRAG_GRAPH_STORAGE=NetworkXStorage LIGHTRAG_DOC_STATUS_STORAGE=JsonDocStatusStorage I recommend: ```python async def main(): rag: LightRAG = await initialize_rag() rag.chunk_entity_relation_graph.embedding_func = rag.embedding_func check_path(WORKING_DIR) check_path(INPUT_DIR)...