Support vector index filtering #2
Open
+78
−5
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
willtai
reviewed
Jan 2, 2025
Comment on lines
+76
to
+77
| # The pattern to find Cypher code enclosed in triple backticks | ||
| pattern = r"###(.*?)###" |
There was a problem hiding this comment.
Why does the text get enclosed in ###?
Also, I think the comment can be corrected here.
willtai
reviewed
Jan 2, 2025
| @@ -62,6 +64,23 @@ def extract_cypher(text: str) -> str: | |||
| return matches[0] if matches else text | |||
|
|
|||
|
|
|||
| def extract_filter(text: str) -> str: | |||
There was a problem hiding this comment.
Could you please add a unit test for this under libs/neo4j/tests/unit_tests/chains/test_graph_qa.py?
willtai
reviewed
Jan 2, 2025
| @@ -88,6 +107,7 @@ def filter_func(x: str) -> bool: | |||
| for r in structured_schema.get("relationships", []) | |||
| if all(filter_func(r[t]) for t in ["start", "end", "type"]) | |||
| ], | |||
| "vector_indexes": structured_schema.get("vector_indexes", []), | |||
There was a problem hiding this comment.
Could you also add some test to ensure this field is included in libs/neo4j/tests/unit_tests/chains/test_graph_qa.py ?
willtai
reviewed
Jan 2, 2025
Comment on lines
+149
to
+150
| "The vector indexes are the following:", | ||
| ",".join(formatted_vector_indexes), |
There was a problem hiding this comment.
Similarly, please write some tests to test this under libs/neo4j/tests/unit_tests/chains/test_graph_qa.py
|
Sorry for the delay, I've added some comments to clarify the |
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Outdated suggestions cannot be applied.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.
Extends/Improves
GraphCypherQAChainto perform queries based on semantics via vector indexes (listed from auto-generated schema), instead of generating queries with strict/exact matching filters which fail on some use cases.This means having the following user's query:
resulting to:
Embeddings are then computed for generated filter and passed as
search_embparameter inqueryNodes.Without this improvement, the same input resulted to the query below, which fails to respond to user's input.
Change is backward compatible (selection of prompt and further logic is based on passing an
embeddingsmodel (optional)