Enable Filters in MongoDB Vector Search Retriever #3333
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
This pull request introduces changes that enable the use of filters in the MongoDB vector search retriever, similar to how it’s done in Pinecone.
Description:
• These changes will allow the implementation of filters in the MongoDB Vector Search Retriever, aligning with the capabilities provided by Pinecone.
• When creating an Atlas Vector Search to index the embedding field, it’s important to also add the filters you want to use, as demonstrated in the MongoDB documentation: MongoDB Atlas Vector Search - Create Index.
Points to consider:
• Ensure that when configuring the Atlas Vector Search for your application, you define both the embedding field and any necessary filters during index creation, as described in the documentation.
screenshots: