Skip to content

perf: optimize fallback entity matching via lazy metadata caching (#805) #810

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
suhaniiz wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

perf: optimize fallback entity matching via lazy metadata caching (#805) #810

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
19 changes: 15 additions & 4 deletions backend/app/rag/graph_retriever.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,14 +43,25 @@ def _match_query_nodes(graph: nx.Graph, query: str) -> Set[str]:
return matched

query_text = query.casefold()
for node_id, data in graph.nodes(data=True):
name = data.get("name", "").casefold()
if name and name in query_text:

# Check if the inverted index is already built and cached on the graph metadata
if "_name_to_node_id" not in graph.graph:
name_index = {}
for node_id, data in graph.nodes(data=True):
name = data.get("name", "")
if name:
name_index[name.casefold()] = node_id
graph.graph["_name_to_node_id"] = name_index
else:
name_index = graph.graph["_name_to_node_id"]

# O(M) lookup over unique names instead of scanning full node data arrays
for name, node_id in name_index.items():
if name in query_text:
matched.add(node_id)

return matched


def _format_pages(pages: List[int]) -> str:
if not pages:
return "unknown pages"
Expand Down
Loading