fix(rag): Fix rerank bug of EmbeddingRetriever #1499
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Outdated suggestions cannot be applied.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.
Description
The EmbeddingRetriever's _aretrieve_with_score and _aretrieve methods do not pass the query parameter to the rank function when calling the ranker to re-rank the retrieval results.
How Has This Been Tested?
retriever = EmbeddingRetriever( vector_store_connector=vector_store_connector, top_k=100, rerank=CrossEncoderRanker(topk=3), )
retriever.aretrieve_with_scores("what is awel talk about", 0.3)
3. debug at "/DB-GPT/dbgpt/rag/retriever/rerank.py", line 211
4. check whether the value of parameter query is None, if not, bug is fixed.
Closes #1498
Snapshots:
Include snapshots for easier review.
Checklist: