Feature/Extract Metadata Retriever #3579
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Outstanding. |
|
Is my understanding correct that this is basically a more dynamic way to set a metadata filter rather than specifying one on the vector store node? Will it be added in addition to any specified on the vector store node? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This retriever is designed to automatically extract keywords from query. The extracted JSON output is used as metadata filter for vector store.
For example, when we ask a question: "What is the profit for Apple", LLM will give an output of
{source: "apple"}, and this will be passed to vectore store's metadata filter