apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-21 18:55:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: enhance web search tool integration with citation management and UI enhancements

Browse source
This commit is contained in:
Anish Sarkar 2026-03-30 01:38:36 +05:30
parent 9eab427b56
commit 74826b3714
13 changed files with 133 additions and 209 deletions
Download patch file Download diff file Expand all files Collapse all files

27
surfsense_backend/app/tasks/chat/stream_new_chat.py
View file

@ -1075,6 +1075,33 @@ async def _stream_agent_events(
"thread_id": thread_id_str,
},
)
elif tool_name == "web_search":
xml = tool_output.get("result", str(tool_output)) if isinstance(tool_output, dict) else str(tool_output)
citations: dict[str, dict[str, str]] = {}
for m in re.finditer(
r"<title><!\[CDATA\[(.*?)\]\]></title>\s*<url><!\[CDATA\[(.*?)\]\]></url>",
xml,
):
title, url = m.group(1).strip(), m.group(2).strip()
if url.startswith("http") and url not in citations:
citations[url] = {"title": title}
for m in re.finditer(
r"<chunk\s+id='([^']*)'><!\[CDATA\[([\s\S]*?)\]\]></chunk>",
xml,
):
chunk_url, content = m.group(1).strip(), m.group(2).strip()
if (
chunk_url.startswith("http")
and chunk_url in citations
and content
):
citations[chunk_url]["snippet"] = (
content[:200] + "…" if len(content) > 200 else content
)
yield streaming_service.format_tool_output_available(
tool_call_id,
{"status": "completed", "citations": citations},
)
else:
yield streaming_service.format_tool_output_available(
tool_call_id,