LlamaIndex
Log in

Find answers from the community

Home
Members
Chris
C
Chris
Offline, last seen 3 months ago
Joined September 25, 2024
CChris
·

Error setting up auto index retriever with QdrantVectorStore

Hey guys, wondering if any of ya'll have fixed this error. I keep getting the following when trying to set up and use an auto index retriever: b'{"status":{"error":"Wrong input: Vector params for are not specified in config"},"time":0.000074995}'

I've tried both adding the dense_config to QdrantVectorStore() as well as adding embed_model to VectorStoreIndex() but neither have worked to resolve the issue. I also tried what was suggested above (https://discord.com/channels/1059199217496772688/1059200010622873741/1233183387884191774 - upgrading the python library) but that didn't work either. Here's the code for reference:

Plain Text
_SS_VECTOR_STORE = QdrantVectorStore(client=_QDRANT_CLIENT, collection_name="STAGE", dense_config=models.VectorParams(size=384, distance=models.Distance.COSINE))
_SS_STORAGE_CONTEXT = StorageContext.from_defaults(vector_store=_SS_VECTOR_STORE)
_SS_RECURSIVE_INDEX = VectorStoreIndex.from_vector_store(vector_store=_SS_VECTOR_STORE, storage_context=_SS_STORAGE_CONTEXT, embed_model=FastEmbedEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2"))

_RETRIEVER = VectorIndexAutoRetriever(
    _SS_RECURSIVE_INDEX, vector_store_info=_VECTOR_STORE_INFO, similarity_top_k=20
)
11 comments
L
C
CChris
·

Hey guys, I was hoping to upgrade our

Hey guys, I was hoping to upgrade our chat engine by using VectorIndexAutoRetriever (so we can filter results in Qdrant with the retriever prior to generating responses). However, I realized it's no longer as simple as index.as_chat_engine() since we now have a retriever instead of an index. Anyone know best practices for combining the two? Or would I have to create my own chat pipeline?
14 comments
J
C
L
CChris
·

Hey guys! I feel like this is a really

Hey guys! I feel like this is a really simple question but I haven't been able to find it in the docs. Does anyone know how I can filter by a specific document from my vector store (qdrant)? For context, our users want to chat with specific documents on our platform instead of searching through all of them for an answer. So we wanted to narrow down the scope of these by just filtering the results of retrival by the document's ID or filename - which we already store in qdrant. Anyone know a good way of doing this? Thank you!!
2 comments
C
L