Hi, I am using auto-retrieval and my data is stored in pinecone. When querying, some times I am receiving an error "ValueError: Filter operator text_match not supported pinecone". I think pinecone doesn't support this operator. But I am not sure how to counter this issue. Can someone help?

Hey, can someone share how an index is updated with new nodes/embeddings? I am not able to find the docs for this.

Hi, I am new to llama index and trying to build a basic document retrieval system. I am using Azure OpenAI embeddings. I have two problems and I am not sure how to resolve:

1. I have a long documents with multiple paragraphs. I want to to treat each paragraph as a seperate document. How to do this?

1. I have many text files. I can create documents object for each. But how do I generate embeddings? Everytime with more one 1 document, I get error as “Too many inputs…..” Seems like some limitation of Azure embeddings. How to resolve this?

Thanks in advance!!

Hey guys, In RAG context, is there a way where I can retrieve a set of nodes based on a query, and then use only those nodes for further queries? Thanks!

Hi, maybe a naive question, but how to retrieve via ID from pinecone vector store package?

Hi, I am using IngestionPipeline to ingest to pinecone db. I have just specified a vector store and not docstore. For the deduplication to be handled (during upsert), is it necessary to add docstore? If so, then the docstore is supposed to be a db or just any cloud location works?
Thanks in advance!

Hey, a basic question here -- When storing to any index, is it recommended to store nodes or documents? Does it make any difference? (Consider documents are tiny and won't create multiple nodes)

Hey, when we use autoretrieval method and it does the filtering based on the metadata provided, how does it work when metadata is a list? eg. metadata is a list of categories -- cat: ["entertainmant", "sports"]
How does the matching happen and is there a specific way to ddefine this in the metadatainfo?
For that matter, apart from str, if metadata is in any other data format (list, dict, list of tuples etc.) , how does the matching happen?