feat: Add multi-document Protocol with cross-app search support
Implements NextcloudClientProtocol for multi-document type search following user requirement that document types are not 1:1 with apps (e.g., Notes app specializes in markdown, while Files/WebDAV handles multiple file types). Key Changes: - NextcloudClientProtocol: Generic protocol with app-specific client properties - get_indexed_doc_types(): Query Qdrant for actually-indexed document types - Document dispatch: All algorithms check Qdrant before attempting access - Cross-type deduplication: Use (doc_id, doc_type) tuples in hybrid RRF Search Algorithm Updates: - Semantic: Added _verify_document_access() with dispatch to appropriate client - Deduplication by (doc_id, doc_type) tuple - Only "note" verification implemented, others return None with info log - Keyword: Added _fetch_documents() dispatch method - Queries Qdrant for available types before fetching - Supports cross-app search when doc_type=None - Fuzzy: Same pattern as keyword search - Hybrid: Already uses (doc_id, doc_type) for deduplication (no changes needed) Future-Proof Design: - File/calendar verification stubs in place - Clear logging when unsupported types found - Easy to extend when processor indexes new document types Currently Supported: - "note" documents fully implemented and tested - Other types gracefully handled (logged but skipped) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
@@ -6,11 +6,14 @@ from typing import Any
|
||||
from httpx import HTTPStatusError
|
||||
from qdrant_client.models import FieldCondition, Filter, MatchValue
|
||||
|
||||
from nextcloud_mcp_server.client import NextcloudClient
|
||||
from nextcloud_mcp_server.config import get_settings
|
||||
from nextcloud_mcp_server.embedding import get_embedding_service
|
||||
from nextcloud_mcp_server.observability.metrics import record_qdrant_operation
|
||||
from nextcloud_mcp_server.search.algorithms import SearchAlgorithm, SearchResult
|
||||
from nextcloud_mcp_server.search.algorithms import (
|
||||
NextcloudClientProtocol,
|
||||
SearchAlgorithm,
|
||||
SearchResult,
|
||||
)
|
||||
from nextcloud_mcp_server.vector.qdrant_client import get_qdrant_client
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -45,7 +48,7 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
|
||||
user_id: str,
|
||||
limit: int = 10,
|
||||
doc_type: str | None = None,
|
||||
nextcloud_client: NextcloudClient | None = None,
|
||||
nextcloud_client: NextcloudClientProtocol | None = None,
|
||||
**kwargs: Any,
|
||||
) -> list[SearchResult]:
|
||||
"""Execute semantic search using vector similarity.
|
||||
@@ -144,9 +147,13 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
|
||||
self,
|
||||
points: list[Any],
|
||||
limit: int,
|
||||
nextcloud_client: NextcloudClient | None,
|
||||
nextcloud_client: NextcloudClientProtocol | None,
|
||||
) -> list[SearchResult]:
|
||||
"""Deduplicate results by doc_id and verify access.
|
||||
"""Deduplicate results by (doc_id, doc_type) and verify access.
|
||||
|
||||
Supports multiple document types with dispatch to appropriate client methods.
|
||||
Deduplication is now by (doc_id, doc_type) tuple to handle cases where
|
||||
the same ID might exist across different document types.
|
||||
|
||||
Args:
|
||||
points: Qdrant search results
|
||||
@@ -156,58 +163,32 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
|
||||
Returns:
|
||||
List of SearchResult objects
|
||||
"""
|
||||
seen_doc_ids = set()
|
||||
seen_docs = set() # Track (doc_id, doc_type) tuples
|
||||
results = []
|
||||
|
||||
for result in points:
|
||||
doc_id = int(result.payload["doc_id"])
|
||||
doc_type = result.payload.get("doc_type", "note")
|
||||
doc_key = (doc_id, doc_type)
|
||||
|
||||
# Skip if we've already seen this document
|
||||
if doc_id in seen_doc_ids:
|
||||
if doc_key in seen_docs:
|
||||
continue
|
||||
|
||||
seen_doc_ids.add(doc_id)
|
||||
seen_docs.add(doc_key)
|
||||
|
||||
# Verify access via Nextcloud API if client provided
|
||||
# Currently only supports notes
|
||||
if nextcloud_client and doc_type == "note":
|
||||
try:
|
||||
note = await nextcloud_client.notes.get_note(doc_id)
|
||||
# Dispatch to appropriate client based on doc_type
|
||||
verified_result = None
|
||||
|
||||
results.append(
|
||||
SearchResult(
|
||||
id=doc_id,
|
||||
doc_type="note",
|
||||
title=result.payload["title"],
|
||||
excerpt=result.payload["excerpt"],
|
||||
score=result.score,
|
||||
metadata={
|
||||
"category": note.get("category", ""),
|
||||
"chunk_index": result.payload["chunk_index"],
|
||||
"total_chunks": result.payload["total_chunks"],
|
||||
},
|
||||
)
|
||||
)
|
||||
if nextcloud_client:
|
||||
verified_result = await self._verify_document_access(
|
||||
nextcloud_client, doc_id, doc_type, result
|
||||
)
|
||||
|
||||
if len(results) >= limit:
|
||||
break
|
||||
|
||||
except HTTPStatusError as e:
|
||||
if e.response.status_code in (403, 404):
|
||||
# User lost access or document deleted
|
||||
logger.debug(
|
||||
f"Skipping note {doc_id}: {e.response.status_code}"
|
||||
)
|
||||
continue
|
||||
else:
|
||||
# Log other errors but continue processing
|
||||
logger.warning(
|
||||
f"Error verifying access to note {doc_id}: "
|
||||
f"{e.response.status_code}"
|
||||
)
|
||||
continue
|
||||
else:
|
||||
if verified_result:
|
||||
results.append(verified_result)
|
||||
elif not nextcloud_client:
|
||||
# No access verification, return result directly
|
||||
results.append(
|
||||
SearchResult(
|
||||
@@ -223,7 +204,72 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
|
||||
)
|
||||
)
|
||||
|
||||
if len(results) >= limit:
|
||||
break
|
||||
if len(results) >= limit:
|
||||
break
|
||||
|
||||
return results
|
||||
|
||||
async def _verify_document_access(
|
||||
self,
|
||||
nextcloud_client: NextcloudClientProtocol,
|
||||
doc_id: int,
|
||||
doc_type: str,
|
||||
qdrant_result: Any,
|
||||
) -> SearchResult | None:
|
||||
"""Verify user has access to a document via Nextcloud API.
|
||||
|
||||
Dispatches to appropriate client method based on document type.
|
||||
|
||||
Args:
|
||||
nextcloud_client: Client for API access
|
||||
doc_id: Document ID
|
||||
doc_type: Document type ("note", "file", "calendar", etc.)
|
||||
qdrant_result: Original Qdrant search result
|
||||
|
||||
Returns:
|
||||
SearchResult if access verified, None if access denied or error
|
||||
"""
|
||||
try:
|
||||
if doc_type == "note":
|
||||
note = await nextcloud_client.notes.get_note(doc_id)
|
||||
return SearchResult(
|
||||
id=doc_id,
|
||||
doc_type="note",
|
||||
title=qdrant_result.payload["title"],
|
||||
excerpt=qdrant_result.payload["excerpt"],
|
||||
score=qdrant_result.score,
|
||||
metadata={
|
||||
"category": note.get("category", ""),
|
||||
"chunk_index": qdrant_result.payload["chunk_index"],
|
||||
"total_chunks": qdrant_result.payload["total_chunks"],
|
||||
},
|
||||
)
|
||||
elif doc_type == "file":
|
||||
# Future: verify file access when files are indexed
|
||||
logger.info(
|
||||
f"File {doc_id} found in search but file verification not yet implemented"
|
||||
)
|
||||
return None
|
||||
elif doc_type == "calendar":
|
||||
# Future: verify calendar access when calendar events are indexed
|
||||
logger.info(
|
||||
f"Calendar event {doc_id} found in search but calendar verification not yet implemented"
|
||||
)
|
||||
return None
|
||||
else:
|
||||
logger.warning(
|
||||
f"Unknown document type '{doc_type}' for doc_id {doc_id}"
|
||||
)
|
||||
return None
|
||||
|
||||
except HTTPStatusError as e:
|
||||
if e.response.status_code in (403, 404):
|
||||
# User lost access or document deleted
|
||||
logger.debug(f"Skipping {doc_type} {doc_id}: {e.response.status_code}")
|
||||
return None
|
||||
else:
|
||||
# Log other errors but continue processing
|
||||
logger.warning(
|
||||
f"Error verifying access to {doc_type} {doc_id}: {e.response.status_code}"
|
||||
)
|
||||
return None
|
||||
|
||||
Reference in New Issue
Block a user