Skip to content

removal of keyword 1st phase #4590

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 23, 2025
Merged

removal of keyword 1st phase #4590

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 4 additions & 31 deletions backend/onyx/context/search/retrieval/search_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,9 +164,7 @@ def doc_index_retrieval(
top_base_chunks_standard_ranking_thread: (
TimeoutThread[list[InferenceChunkUncleaned]] | None
) = None
top_base_chunks_keyword_ranking_thread: (
TimeoutThread[list[InferenceChunkUncleaned]] | None
) = None

top_semantic_chunks_thread: TimeoutThread[list[InferenceChunkUncleaned]] | None = (
None
)
Expand All @@ -190,20 +188,6 @@ def doc_index_retrieval(
query.offset,
)

# same query but with 1st vespa phase as keyword retrieval
top_base_chunks_keyword_ranking_thread = run_in_background(
document_index.hybrid_retrieval,
query.query,
query_embedding,
query.processed_keywords,
query.filters,
query.hybrid_alpha,
query.recency_bias_multiplier,
query.num_hits,
QueryExpansionType.KEYWORD,
query.offset,
)

if (
query.expanded_queries
and query.expanded_queries.keywords_expansions
Expand Down Expand Up @@ -264,21 +248,14 @@ def doc_index_retrieval(
top_base_chunks_standard_ranking = wait_on_background(
top_base_chunks_standard_ranking_thread
)
top_base_chunks_keyword_ranking = wait_on_background(
top_base_chunks_keyword_ranking_thread
)

top_keyword_chunks = wait_on_background(top_keyword_chunks_thread)

if query.search_type == SearchType.SEMANTIC:
assert top_semantic_chunks_thread is not None
top_semantic_chunks = wait_on_background(top_semantic_chunks_thread)

all_top_chunks = (
top_base_chunks_standard_ranking
+ top_base_chunks_keyword_ranking
+ top_keyword_chunks
)
all_top_chunks = top_base_chunks_standard_ranking + top_keyword_chunks

# use all three retrieval methods to retrieve top chunks

Expand All @@ -293,12 +270,8 @@ def doc_index_retrieval(
top_base_chunks_standard_ranking = wait_on_background(
top_base_chunks_standard_ranking_thread
)
top_base_chunks_keyword_ranking = wait_on_background(
top_base_chunks_keyword_ranking_thread
)
top_chunks = _dedupe_chunks(
top_base_chunks_standard_ranking + top_base_chunks_keyword_ranking
)

top_chunks = _dedupe_chunks(top_base_chunks_standard_ranking)

logger.info(f"Overall number of top initial retrieval chunks: {len(top_chunks)}")

Expand Down
Loading