phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: Remove double filtering based on score threshold (#3019)

Browse source 
# What does this PR do?
Remove score_threshold based check from `OpenAIVectorStoreMixin`

Closes: https://github.com/meta-llama/llama-stack/issues/3018

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
This commit is contained in:
Varsha 2025-08-02 15:57:03 -07:00 • committed by GitHub
parent 1e3b5aa9b8
commit 3c2aee610d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 13 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/inline/vector_io/faiss/faiss.py
View file

@ -160,8 +160,11 @@ class FaissIndex(EmbeddingIndex):
for d, i in zip(distances[0], indices[0], strict=False):
if i < 0:
continue
score = 1.0 / float(d) if d != 0 else float("inf")
if score < score_threshold:
continue
chunks.append(self.chunk_by_index[int(i)])
scores.append(1.0 / float(d) if d != 0 else float("inf"))
scores.append(score)
return QueryChunksResponse(chunks=chunks, scores=scores)