vrr/SurfSense
2
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2025-09-02 10:39:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #225 from MODSetter/dev
Some checks are pending
pre-commit / pre-commit (push) Waiting to run
Details

Browse source 
refactor: fix for linkup
This commit is contained in:
Rohan Verma 2025-07-24 22:28:28 +05:30 • committed by GitHub
commit 505a005bac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 25 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
surfsense_backend/app/agents/researcher/nodes.py
View file

@ -696,9 +696,6 @@ async def fetch_relevant_documents(
) )
elif connector == "LINKUP_API": elif connector == "LINKUP_API":
if top_k > 10:
linkup_mode = "deep"
else:
linkup_mode = "standard" linkup_mode = "standard"
source_object, linkup_chunks = await connector_service.search_linkup( source_object, linkup_chunks = await connector_service.search_linkup(
@ -789,12 +786,36 @@ async def fetch_relevant_documents(
if source_id and source_type: if source_id and source_type:
source_key = f"{source_type}_{source_id}" source_key = f"{source_type}_{source_id}"
current_sources_count = len(source_obj.get('sources', []))
if source_key not in seen_source_keys: if source_key not in seen_source_keys:
seen_source_keys.add(source_key) seen_source_keys.add(source_key)
deduplicated_sources.append(source_obj) deduplicated_sources.append(source_obj)
print(f"Debug: Added source - ID: {source_id}, Type: {source_type}, Key: {source_key}, Sources count: {current_sources_count}")
else:
# Check if this source object has more sources than the existing one
existing_index = None
for i, existing_source in enumerate(deduplicated_sources):
existing_id = existing_source.get('id')
existing_type = existing_source.get('type')
if existing_id == source_id and existing_type == source_type:
existing_index = i
break
if existing_index is not None:
existing_sources_count = len(deduplicated_sources[existing_index].get('sources', []))
if current_sources_count > existing_sources_count:
# Replace the existing source object with the new one that has more sources
deduplicated_sources[existing_index] = source_obj
print(f"Debug: Replaced source - ID: {source_id}, Type: {source_type}, Key: {source_key}, Sources count: {existing_sources_count} -> {current_sources_count}")
else:
print(f"Debug: Skipped duplicate source - ID: {source_id}, Type: {source_type}, Key: {source_key}, Sources count: {current_sources_count} <= {existing_sources_count}")
else:
print(f"Debug: Skipped duplicate source - ID: {source_id}, Type: {source_type}, Key: {source_key} (couldn't find existing)")
else: else:
# If there's no ID or type, just add it to be safe # If there's no ID or type, just add it to be safe
deduplicated_sources.append(source_obj) deduplicated_sources.append(source_obj)
print(f"Debug: Added source without ID/type - {source_obj.get('name', 'UNKNOWN')}")
# Stream info about deduplicated sources # Stream info about deduplicated sources
if streaming_service and writer: if streaming_service and writer: