mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-05-31 19:45:15 +02:00
refactor: remove search_surfsense_docs tool and related references
- Deleted the `search_surfsense_docs` tool and its associated files, streamlining the agent's toolset. - Updated various components and prompts to remove references to the now-removed tool, ensuring consistency across the codebase. - Adjusted documentation to direct users to the SurfSense documentation link for product-related queries instead.
This commit is contained in:
DESKTOP-RTLN3BA\$punk
parent
9b9e6828c7
commit
40ca9e6ed2
71 changed files with 232 additions and 1676 deletions
|
|
@ -5,7 +5,6 @@ This module contains all the tools available to the SurfSense agent.
|
|||
To add a new tool, see the documentation in registry.py.
|
||||
|
||||
Available tools:
|
||||
- search_surfsense_docs: Search Surfsense documentation for usage help
|
||||
- generate_podcast: Generate audio podcasts from content
|
||||
- generate_video_presentation: Generate video presentations with slides and narration
|
||||
- generate_image: Generate images from text descriptions using AI models
|
||||
|
|
@ -31,7 +30,6 @@ from .registry import (
|
|||
get_tool_by_name,
|
||||
)
|
||||
from .scrape_webpage import create_scrape_webpage_tool
|
||||
from .search_surfsense_docs import create_search_surfsense_docs_tool
|
||||
from .update_memory import create_update_memory_tool, create_update_team_memory_tool
|
||||
from .video_presentation import create_generate_video_presentation_tool
|
||||
|
||||
|
|
@ -47,7 +45,6 @@ __all__ = [
|
|||
"create_generate_podcast_tool",
|
||||
"create_generate_video_presentation_tool",
|
||||
"create_scrape_webpage_tool",
|
||||
"create_search_surfsense_docs_tool",
|
||||
"create_update_memory_tool",
|
||||
"create_update_team_memory_tool",
|
||||
"format_documents_for_context",
|
||||
|
|
|
|||
|
|
@ -101,7 +101,6 @@ from .podcast import create_generate_podcast_tool
|
|||
from .report import create_generate_report_tool
|
||||
from .resume import create_generate_resume_tool
|
||||
from .scrape_webpage import create_scrape_webpage_tool
|
||||
from .search_surfsense_docs import create_search_surfsense_docs_tool
|
||||
from .teams import (
|
||||
create_list_teams_channels_tool,
|
||||
create_read_teams_messages_tool,
|
||||
|
|
@ -258,15 +257,6 @@ BUILTIN_TOOLS: list[ToolDefinition] = [
|
|||
),
|
||||
requires=[],
|
||||
),
|
||||
# Surfsense documentation search tool
|
||||
ToolDefinition(
|
||||
name="search_surfsense_docs",
|
||||
description="Search Surfsense documentation for help with using the application",
|
||||
factory=lambda deps: create_search_surfsense_docs_tool(
|
||||
db_session=deps["db_session"],
|
||||
),
|
||||
requires=["db_session"],
|
||||
),
|
||||
# =========================================================================
|
||||
# SERVICE ACCOUNT DISCOVERY
|
||||
# Generic tool for the LLM to discover connected accounts and resolve
|
||||
|
|
|
|||
|
|
@ -1,174 +0,0 @@
|
|||
"""
|
||||
Surfsense documentation search tool.
|
||||
|
||||
This tool allows the agent to search the pre-indexed Surfsense documentation
|
||||
to help users with questions about how to use the application.
|
||||
|
||||
The documentation is indexed at deployment time from MDX files and stored
|
||||
in dedicated tables (surfsense_docs_documents, surfsense_docs_chunks).
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
|
||||
from langchain_core.tools import tool
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.db import SurfsenseDocsChunk, SurfsenseDocsDocument, async_session_maker
|
||||
from app.utils.document_converters import embed_text
|
||||
from app.utils.surfsense_docs import surfsense_docs_public_url
|
||||
|
||||
|
||||
def format_surfsense_docs_results(results: list[tuple]) -> str:
|
||||
"""
|
||||
Format search results into XML structure for the LLM context.
|
||||
|
||||
Uses the same XML structure as format_documents_for_context from knowledge_base.py
|
||||
but with 'doc-' prefix on chunk IDs. This allows:
|
||||
- LLM to use consistent [citation:doc-XXX] format
|
||||
- Frontend to detect 'doc-' prefix and route to surfsense docs endpoint
|
||||
|
||||
Args:
|
||||
results: List of (chunk, document) tuples from the database query
|
||||
|
||||
Returns:
|
||||
Formatted XML string with documentation content and citation-ready chunks
|
||||
"""
|
||||
if not results:
|
||||
return "No relevant Surfsense documentation found for your query."
|
||||
|
||||
# Group chunks by document
|
||||
grouped: dict[int, dict] = {}
|
||||
for chunk, doc in results:
|
||||
public_url = surfsense_docs_public_url(doc.source)
|
||||
if doc.id not in grouped:
|
||||
grouped[doc.id] = {
|
||||
"document_id": f"doc-{doc.id}",
|
||||
"document_type": "SURFSENSE_DOCS",
|
||||
"title": doc.title,
|
||||
"url": public_url,
|
||||
"metadata": {"source": doc.source, "public_url": public_url},
|
||||
"chunks": [],
|
||||
}
|
||||
grouped[doc.id]["chunks"].append(
|
||||
{
|
||||
"chunk_id": f"doc-{chunk.id}",
|
||||
"content": chunk.content,
|
||||
}
|
||||
)
|
||||
|
||||
# Render XML matching format_documents_for_context structure
|
||||
parts: list[str] = []
|
||||
for g in grouped.values():
|
||||
metadata_json = json.dumps(g["metadata"], ensure_ascii=False)
|
||||
|
||||
parts.append("<document>")
|
||||
parts.append("<document_metadata>")
|
||||
parts.append(f" <document_id>{g['document_id']}</document_id>")
|
||||
parts.append(f" <document_type>{g['document_type']}</document_type>")
|
||||
parts.append(f" <title><![CDATA[{g['title']}]]></title>")
|
||||
parts.append(f" <url><![CDATA[{g['url']}]]></url>")
|
||||
parts.append(f" <metadata_json><![CDATA[{metadata_json}]]></metadata_json>")
|
||||
parts.append("</document_metadata>")
|
||||
parts.append("")
|
||||
parts.append("<document_content>")
|
||||
|
||||
for ch in g["chunks"]:
|
||||
parts.append(
|
||||
f" <chunk id='{ch['chunk_id']}'><![CDATA[{ch['content']}]]></chunk>"
|
||||
)
|
||||
|
||||
parts.append("</document_content>")
|
||||
parts.append("</document>")
|
||||
parts.append("")
|
||||
|
||||
return "\n".join(parts).strip()
|
||||
|
||||
|
||||
async def search_surfsense_docs_async(
|
||||
query: str,
|
||||
db_session: AsyncSession,
|
||||
top_k: int = 10,
|
||||
) -> str:
|
||||
"""
|
||||
Search Surfsense documentation using vector similarity.
|
||||
|
||||
Args:
|
||||
query: The search query about Surfsense usage
|
||||
db_session: Database session for executing queries
|
||||
top_k: Number of results to return
|
||||
|
||||
Returns:
|
||||
Formatted string with relevant documentation content
|
||||
"""
|
||||
# Get embedding for the query
|
||||
query_embedding = await asyncio.to_thread(embed_text, query)
|
||||
|
||||
# Vector similarity search on chunks, joining with documents
|
||||
stmt = (
|
||||
select(SurfsenseDocsChunk, SurfsenseDocsDocument)
|
||||
.join(
|
||||
SurfsenseDocsDocument,
|
||||
SurfsenseDocsChunk.document_id == SurfsenseDocsDocument.id,
|
||||
)
|
||||
.order_by(SurfsenseDocsChunk.embedding.op("<=>")(query_embedding))
|
||||
.limit(top_k)
|
||||
)
|
||||
|
||||
result = await db_session.execute(stmt)
|
||||
rows = result.all()
|
||||
|
||||
return format_surfsense_docs_results(rows)
|
||||
|
||||
|
||||
def create_search_surfsense_docs_tool(db_session: AsyncSession):
|
||||
"""
|
||||
Factory function to create the search_surfsense_docs tool.
|
||||
|
||||
The tool acquires its own short-lived ``AsyncSession`` per call via
|
||||
:data:`async_session_maker` so the closure is safe to share across
|
||||
HTTP requests by the compiled-agent cache. Capturing a per-request
|
||||
session here would surface stale/closed sessions on cache hits.
|
||||
|
||||
Args:
|
||||
db_session: Reserved for registry compatibility. Per-call sessions
|
||||
are opened via :data:`async_session_maker` inside the tool body.
|
||||
|
||||
Returns:
|
||||
A configured tool function for searching Surfsense documentation
|
||||
"""
|
||||
del db_session # per-call session — see docstring
|
||||
|
||||
@tool
|
||||
async def search_surfsense_docs(query: str, top_k: int = 10) -> str:
|
||||
"""
|
||||
Search Surfsense documentation for help with using the application.
|
||||
|
||||
Use this tool when the user asks questions about:
|
||||
- How to use Surfsense features
|
||||
- Installation and setup instructions
|
||||
- Configuration options and settings
|
||||
- Troubleshooting common issues
|
||||
- Available connectors and integrations
|
||||
- Browser extension usage
|
||||
- API documentation
|
||||
|
||||
This searches the official Surfsense documentation that was indexed
|
||||
at deployment time. It does NOT search the user's personal knowledge base.
|
||||
|
||||
Args:
|
||||
query: The search query about Surfsense usage or features
|
||||
top_k: Number of documentation chunks to retrieve (default: 10)
|
||||
|
||||
Returns:
|
||||
Relevant documentation content formatted with chunk IDs for citations
|
||||
"""
|
||||
async with async_session_maker() as db_session:
|
||||
return await search_surfsense_docs_async(
|
||||
query=query,
|
||||
db_session=db_session,
|
||||
top_k=top_k,
|
||||
)
|
||||
|
||||
return search_surfsense_docs
|
||||
Loading…
Add table
Add a link
Reference in a new issue