Skip to content

Optimize sequential namespace search using asyncio.gather #73

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

Open
ishaanxgupta wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Optimize sequential namespace search using asyncio.gather #73

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8e5f4b3
Optimize multi-repo search in CodeRetrievalPipeline using asyncio.gather
ishaanxgupta Mar 9, 2026
a09c710
Delete .jules/bolt.md
ishaanxgupta Mar 9, 2026
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
32 changes: 24 additions & 8 deletions src/pipelines/code_retrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@

from __future__ import annotations

import asyncio
import logging
from typing import Any, Callable, Dict, List, Optional

Expand Down Expand Up @@ -589,14 +590,22 @@ async def _search_symbols(
) -> List[SourceRecord]:
if not repo:
logger.warning("search_symbols called without repo — searching all repos")
results = []
for r in self.repos:
results.extend(await self._search_namespace(

async def _search(r: str) -> List[SourceRecord]:
return await self._search_namespace(
namespace=symbols_namespace(self.org_id, r),
query=query,
domain="symbol",
top_k=top_k,
))
)

tasks = [_search(r) for r in self.repos]
all_results = await asyncio.gather(*tasks)

results = []
for res in all_results:
results.extend(res)

return results[:top_k]

return await self._search_namespace(
Expand All @@ -612,14 +621,21 @@ async def _search_files(
self, query: str, repo: str, top_k: int = 10,
) -> List[SourceRecord]:
if not repo:
results = []
for r in self.repos:
results.extend(await self._search_namespace(
async def _search(r: str) -> List[SourceRecord]:
return await self._search_namespace(
namespace=files_namespace(self.org_id, r),
query=query,
domain="file",
top_k=top_k,
))
)

tasks = [_search(r) for r in self.repos]
all_results = await asyncio.gather(*tasks)

results = []
for res in all_results:
results.extend(res)

return results[:top_k]

return await self._search_namespace(
Expand Down