Qdrant Not Returning Filtered Documents as Expected #5633
Comments
|
Hi @Mohana-Murugan. Could you print Also, could you try if using explicit types for the payload filter as documented here makes any difference? I mean something like this: query_filter=models.Filter(
must=[
models.FieldCondition(
key="user_id",
match=models.MatchValue(
value="K5617",
),
),
models.FieldCondition(
key="company_id",
match=models.MatchValue(
value="101",
),
),
models.FieldCondition(
key="agent_id",
match=models.MatchValue(
value="5307",
),
),
]
), |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
My exact issues are as follows
It works fine:
When IDs do not match:
It provides the following wrong answer
I am using the same embedding model, 'BAAI/bge-small-en-v1.5,' for storing and retrieving. However, I cannot identify the reason why I am getting these results.
When I pass this to the LLM, the model provides answers based on its pre-trained documents instead of retrieving information from Qdrant using a filter.
Without any filter, Qdrant works fine for us, and there is no doubt about that.
Originally posted by @Mohana-Murugan in #5863 (reply in thread)
The text was updated successfully, but these errors were encountered: