Adrian de los Santos

after doing a git pull, creating again the postgres database and processing a bunch of input files: -- error:value too long for type character varying(255) Failed to extract entities and...

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

BTW if you store everything in text files.. it works.. it even works faster than using a proper database behind..

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

Also reports high response times on postgres queries after this error.. the db works but takes a lot to answer (170 seconds - 200 seconds)

also reporting high cpu usage top snip.. 857162 systemd-r 20 0 343M 106M 95184 R 99.7 0.3 0:53.74 postgres: 16/main: rag rag 172.17.0.1(49784) authentication 857163 systemd-r 20 0 343M 87924...

so... just tyring the example with milvus i found: ValueError: Storage implementation 'RedisKVStorage' is not compatible with DOC_STATUS_STORAGE. Compatible implementations are: JsonDocStatusStorage, PGDocStatusStorage, PGDocStatusStorage, MongoDocStatusStorage so.. RedisKVStorage does not exists...

error:column "chunk_ids" of relation "lightrag_vdb_entity" does not exist Failed to extract entities and relationships reporting the same issue..

neo4j ? most likely u need to raise the default config of neo4j..

no answer when a question is made to the rag system. i can see the post to embeddings to "map" the query vectors DEBUG:HTTP Request: POST https://api.openai.com/v1/embeddings "200 OK" DEBUG:close.started...