Find answers from the community

Updated 10 months ago

Hi, I am trying to retrieve some

At a glance
The community member is trying to retrieve conversation data from QdrantDB, but is facing an issue where they receive a validation error when querying the data. The error message indicates that the text field in the payload is set to None, which is not allowed. A comment suggests that the vector store expects a text field to be present in the payload, and that in Qdrant, this field is currently hardcoded to be named text. There is no explicitly marked answer in the comments.
Hi, I am trying to retrieve some conversation data from QdrantDB, the points have already been pushed to Qdrant. And I just want to query some similar conversation in the following manner:


Plain Text
from qdrant_client import QdrantClient

client = QdrantClient(
    url="<qdrant_url>", 
    api_key=qdrant_key,
)



vector_store = QdrantVectorStore(client=client, collection_name="<collection_name>")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_vector_store(vector_store=vector_store, storage_context=storage_context, embed_model=embed_model)
retriever = VectorIndexRetriever(index=index, similarity_top_k=10)

llm = OpenAI(model="gpt-3.5-turbo") 

query_engine = RetrieverQueryEngine.from_args(retriever=retriever, llm=llm)
response = query_engine.query("Find conversation around Food preferences?")


But while asking any query (last line), I always face issue: 1 validation error for TextNode text none is not an allowed value (type=type_error.none.not_allowed)
L
1 comment
vector stores depend on having a field of text to put into a node object

looks like in qdrant thats currently hardcoded to a payload field called "text"
Add a reply
Sign up and join the conversation on Discord