Multiple metadata filters
As well as equality operations, Pinecone provides operators for other core comparison operations, as well as enabling multiple filters in a single query. In this exercise, you'll create multiple filters using Pinecone's other comparison operators and use them to re-query your index.
This exercise is part of the course
Vector Databases for Embeddings with Pinecone
Exercise instructions
- Initialize the Pinecone connection using your API key.
- Retrieve the MOST similar vector to the
vectorprovided, only searching through vectors where the the"genre"metadata is"thriller"and"year"is less than2018.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Initialize the Pinecone client using your API key
pc = Pinecone(api_key="____")
index = pc.Index('datacamp-index')
# Retrieve the MOST similar vector with genre and year filters
query_result = index.query(
vector=vector,
top_k=1,
filter=____
)
print(query_result)