Hi for Structured Retrieval using Auto retrival In the demo weaviate db is used.
nodes = retriever.retrieve( "Tell me about the childhood of a popular sports celebrity in the United" " States" )
INFO:llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever:Using query str: childhood of a popular sports celebrity Using query str: childhood of a popular sports celebrity INFO:llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever:Using filters: {'category': 'Sports', 'country': 'United States'} Using filters: {'category': 'Sports', 'country': 'United States'} INFO:llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever:Using top_k: 2 Using top_k: 2
the retrieval automatically filters sports and country from the meta data.
I tried to replicate the same using deeplake indexing
response = query_engine.query( "Tell me about a celebrity from the United States" )
INFO:httpx:HTTP Request: POST http://localhost:11434/api/chat "HTTP/1.1 200 OK" HTTP Request: POST http://localhost:11434/api/chat "HTTP/1.1 200 OK" INFO:llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever:Using query str: celebrity from United States Using query str: celebrity from United States INFO:llama_index.indices.vector_store.retrievers.auto_retriever.auto_retriever:Using filters: [] Using filters: []
the retriever is unable to identify the filters. is it because of change in db. Please suggest me other local indexer for structured retrieval.
