- Replace sequential Qdrant scroll calls with batch retrieve
(50 HTTP requests → 1 request, ~50x faster vector fetch)
- Add point_id to SearchResult to enable batch retrieval by Qdrant point ID
- Reuse query embedding from search algorithm in viz_routes
(eliminates redundant embedding call, saves ~30ms)
- Make BM25 encode() async with thread pool to avoid blocking event loop
(~4.4s was blocking, now properly async)
- Run PCA computation in thread pool to avoid blocking event loop
(~1.2s was blocking, now properly async)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Drawing directly with ImageDraw on RGBA mode doesn't blend alpha
properly. Use Image.alpha_composite() with a transparent overlay
to achieve correct semi-transparent highlight fills.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Phase 1 - PDF Highlighting Optimization:
- Render each page ONCE instead of once per chunk (N chunks = 1 render, not N)
- Use PIL to draw bounding boxes on copied base images (fast) instead of
re-rendering page via pymupdf (slow)
- Add _find_chunk_bbox() to extract bbox without modifying page
Phase 2 - Parallel Page Extraction:
- Use anyio task group with run_sync() for parallel page extraction
- Each page extracted in separate thread via anyio.to_thread.run_sync()
- Event loop stays responsive during extraction
- Remove obsolete _process_sync() method
Expected improvement: 30-50% reduction in total PDF processing time.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Previously, pymupdf4llm.to_markdown() was called twice - once in
PyMuPDFProcessor during indexing and again in PDFHighlighter during
visualization. Different image path lengths caused different character
offsets, leading to highlighted pages not matching their chunks.
Also fixed issue where all chunks on the same page showed all highlights
instead of just their own highlight. Now restores original page contents
between chunks using xref stream caching.
Changes:
- Add PDFHighlighter class requiring pre-computed page_boundaries and
full_text from document processor (no fallback extraction)
- Pass pre-computed data from processor to highlighter
- Extract page-relative portion of chunk text for cross-page chunks
- Add bounding box highlighting using text anchor search
- Run highlight generation in parallel with embedding/BM25
- Cache and restore page contents to isolate highlights per chunk
Results: Highlighting success rate improved from 51% to 95% (121/128).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements optional context expansion for semantic search results that
fetches adjacent chunks (N-1 and N+1) from Qdrant to provide before/after
context. Removes configurable chunk overlap (default 200 chars) to avoid
duplicate text appearing in both context and excerpt.
Key changes:
- Add include_context and context_chars parameters to nc_semantic_search
and nc_semantic_search_answer tools
- Implement Qdrant cache fast path for chunk retrieval (avoids re-fetching
and re-parsing documents, especially important for PDFs)
- Add _get_chunk_by_index_from_qdrant() to fetch adjacent chunks
- Remove chunk overlap from before_context (last N chars) and after_context
(first N chars) to prevent duplicate text
- Fetch context in parallel with anyio.Semaphore (max 20 concurrent)
- Pass through page_number from SearchResult to SemanticSearchResult
- Remove document-level deduplication (keep chunk-level dedup from algorithm)
Context expansion is opt-in via include_context=true parameter. When enabled:
- Populates has_context_expansion, marked_text, before_context, after_context
- Adds truncation flags when context exceeds context_chars limit
- Falls back to document fetch for legacy data with truncated excerpts
Related: nextcloud_mcp_server/search/context.py:87-382,
nextcloud_mcp_server/server/semantic.py:161-255
Introduces a placeholder-based state tracking system to prevent duplicate
document processing during the gap between scanner queuing and processor
completion.
**Key Changes:**
1. **Placeholder Helper Functions** (`vector/placeholder.py`):
- `write_placeholder_point()` - Creates zero-vector placeholder when queuing
- `query_document_metadata()` - Queries for existing entry (placeholder or real)
- `delete_placeholder_point()` - Removes placeholder before writing real vectors
- `get_placeholder_filter()` - Filters placeholders from user-facing queries
2. **Scanner Updates** (`vector/scanner.py`):
- Replace `indexed_at` comparison with `modified_at` comparison
- Write placeholder before queuing each document
- Query per-document metadata instead of bulk-querying indexed_at
- Fixes bug where files were resubmitted every scan cycle
3. **Processor Updates** (`vector/processor.py`):
- Delete placeholder before upserting real vectors
- Ensures no duplicate points in Qdrant
4. **Query Filters** (all search files):
- Add `get_placeholder_filter()` to all user-facing queries
- Ensures placeholders never appear in search results or visualizations
- Applied to: bm25_hybrid.py, semantic.py, viz_routes.py, algorithms.py
**Architecture:**
- Placeholders use zero vectors with dimension from embedding service
- Payload includes `is_placeholder: True` flag for filtering
- Status field tracks: "pending", "processing", "completed", "failed"
- Deterministic UUIDs using uuid5 for consistent point IDs
**Impact:**
- Eliminates duplicate processing of same documents
- Fixes race condition where long-running documents get queued multiple times
- Prevents scanner from resubmitting files every scan cycle
- Maintains clean separation between in-flight and indexed documents
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This commit fixes two critical issues with PDF processing:
1. **Text extraction mismatch (context expansion bug)**:
- Indexing used pymupdf4llm.to_markdown() producing markdown text
- Context expansion used page.get_text() producing plain text
- Different text formats caused character offset misalignment
- Search would find correct chunk, but expansion showed wrong section
- Fixed by making context.py use pymupdf4llm.to_markdown() consistently
2. **Diagnostic logging for page number assignment**:
- Added logging to verify page_boundaries exist in metadata
- Added logging to verify assign_page_numbers() assigns values
- Helps diagnose why page numbers show as null in search results
3. **mime_type storage bug**:
- Fixed incorrect field reference in processor.py:405
- Was using file_metadata.get("content_type", "")
- Should use content_type from WebDAV response
Changes:
- nextcloud_mcp_server/search/context.py: Use pymupdf4llm.to_markdown()
for PDF text extraction to match indexing method
- nextcloud_mcp_server/vector/processor.py: Add diagnostic logging for
page boundaries and assignment, fix mime_type storage
- tests/unit/client/test_webdav.py: Fix import sorting
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- algorithms.py: Revert SearchResult.id to int (all docs use int IDs now)
- semantic.py: Revert SemanticSearchResult.id to int, remove Union import
- viz_routes.py: Remove str() conversion when querying doc_id from Qdrant
- viz_routes.py: Convert doc_id from query param to int in chunk context
Fixes vector visualization which was collapsing all chunks to a single
point because Qdrant queries were failing to match doc_id (string vs int).
- scanner.py: Use file_info['id'] as doc_id instead of file_path
- scanner.py: Pass file_path in DocumentTask for content retrieval
- processor.py: Store file_path in Qdrant payload for later lookup
- context.py: Add _get_file_path_from_qdrant() to resolve file_id → file_path
- context.py: Update get_chunk_with_context() to handle file ID resolution
This makes the system resilient to file renames since file IDs are stable
identifiers in Nextcloud, while file paths can change.
Notes are indexed as "{title}\n\n{content}" in processor.py but were
being retrieved as just content during chunk expansion, causing
chunk_start_offset and chunk_end_offset to be misaligned.
This fix reconstructs the full content structure when fetching notes
for chunk expansion, ensuring the displayed chunks match the excerpts
shown in search results.
Fixes chunk/excerpt mismatch reported in vector visualization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements to vector visualization page:
- Refactor PCA to display individual chunks instead of averaged documents
- Add context expansion module for fetching surrounding text from notes and PDFs
- Update deduplication to use (doc_id, doc_type, chunk_start, chunk_end) keys
- Fix Alpine.js rendering with chunk-specific keys including offsets
- Refactor authentication helper to return NextcloudClient for better reuse
- Add async context manager support to NextcloudClient
Technical details:
- viz_routes.py: Fetch specific chunk vectors instead of averaging per document
- context.py: New module supporting both notes and PDF text extraction via PyMuPDF
- search algorithms: Extract page_number, chunk_index, total_chunks from Qdrant
- vector-viz.js/html: Use chunk positions in expansion tracking keys
This enables users to see which specific chunks match their query
and view them with surrounding context in the PCA visualization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This commit addresses multiple issues with async operations, PDF metadata
extraction, and type safety in document processing and search.
## Async/Await Fixes
- processor.py:259 - Added await for chunker.chunk_text(content)
- processor.py:270 - Added await for bm25_service.encode_batch(chunk_texts)
- tests/unit/test_document_chunker.py - Converted all 12 test methods to async
## PDF Metadata Enhancement
- pymupdf.py:143 - Added file_size metadata extraction
- pymupdf.py:145-206 - Refactored to extract text page-by-page
- Manually loop through pages instead of using page_chunks=True
- Generate page_boundaries metadata for precise page tracking
- Works around pymupdf.layout.activate() breaking page_chunks=True
- processor.py:32-66 - Added assign_page_numbers() helper function
- Assigns page numbers to chunks based on overlap with page boundaries
- Handles chunks spanning multiple pages
- processor.py:298-300 - Call assign_page_numbers() for PDF files
## Type Safety Fixes
- bm25_hybrid.py:184 - Removed int() conversion of doc_id
- semantic.py:131 - Removed int() conversion of doc_id
- viz_routes.py:275 - Removed int() conversion of doc_id
- Added comments documenting that doc_id can be int (notes) or str (file paths)
## Testing
- All 18 tests passing (12 unit + 6 integration)
- No type errors in modified files
- Container logs show successful processing
- Vector viz searches working correctly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Track character offsets (start_offset, end_offset) for each chunk in vector
database metadata, enabling precise chunk highlighting in visualization pane.
Changes:
- processor.py: Store chunk_start_offset and chunk_end_offset in Qdrant metadata
- processor.py: Added metadata_version=2 to indicate position tracking support
- search/semantic.py: Return chunk positions from search results
- server/semantic.py: Expose chunk positions in API responses (SemanticSearchResult)
Enables viz pane to:
1. Display exact matched chunk with surrounding context
2. Highlight the precise portion of text that matched the query
3. Build user trust by showing what the RAG system actually retrieved
Position tracking uses ChunkWithPosition dataclass from document_chunker.py
which provides character-accurate offsets in the original document.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fix false-positive validation error where DBSF (Distribution-Based Score
Fusion) correctly produces scores > 1.0 but SearchResult validation
incorrectly rejected them.
**Root Cause**: SearchResult.__post_init__() enforced scores in [0.0, 1.0]
range, but DBSF sums normalized scores from multiple retrieval systems
(dense semantic + sparse BM25), resulting in scores like 1.55 when both
systems strongly agree a document is relevant.
**Changes**:
- Relaxed validation to allow any score ≥ 0.0 (algorithms.py:147-157)
- Updated SearchResult and SemanticSearchResult documentation to explain
score ranges for RRF ([0.0, 1.0]) vs DBSF (unbounded)
- Added comprehensive test coverage for both fusion methods
- Added DBSF fusion option to vector visualization UI
- Updated viz routes and vizApp() to support fusion parameter selection
**Testing**: All 157 unit tests pass, type checking passes, ruff passes
Fixes error: "Configuration error: Score must be between 0.0 and 1.0, got 1.1528953"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- viz_routes.py: Extract "dense" vector from named vector dict
- semantic.py: Specify using="dense" for BM25 hybrid collections
- Fixes "X must be 2D array" error in hybrid search
- Fixes "Dense vector is not found" error in semantic search
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This commit addresses critical performance issues with vector visualization
search (reducing time from 40s to ~2s) and improves result visualization
through better visual encoding.
## Performance Fixes
### 1. Fix blocking sleep in retry decorator (base.py:51)
- Changed `time.sleep(5)` to `await anyio.sleep(5)` in @retry_on_429
- Prevents entire event loop from freezing during rate limit retries
- Impact: Reduced search time from 22s to 16s initially
### 2. Add concurrency limiting for verification (verification.py:77-93)
- Added `anyio.Semaphore(20)` to limit concurrent HTTP requests
- Prevents connection pool exhaustion (RequestError) from 90+ simultaneous requests
- Fixes false filtering (was filtering 77/90 results incorrectly)
- Note: Semaphore still in code but verification removed from viz endpoint
### 3. Remove unnecessary verification from viz endpoint (viz_routes.py:483-486)
- Visualization only needs Qdrant metadata (title, excerpt), not full content
- Verification only required for sampling (LLM needs full note content)
- Impact: Reduced search time from 43.7s to ~2s (final fix)
### 4. Restore streaming scanner pattern (scanner.py)
- Process notes one-at-a-time using async generator
- Avoids loading all notes into memory
## Visualization Improvements
### 5. Result-relative score normalization (viz_routes.py:489-504)
- Normalize scores within result set: best=1.0, worst=0.0
- Removes arbitrary RRF normalization (theoretical max didn't make sense)
- Makes visual encoding meaningful regardless of algorithm scores
### 6. Power scaling for marker sizes (userinfo_routes.py:743)
- Changed from linear `8 + (score * 12)` to power `6 + (score² * 14)`
- Creates dramatic visual contrast: 0.0→6px, 0.5→9.5px, 1.0→20px
- Combined with opacity (0.2-1.0) for clear visual hierarchy
### 7. Multi-channel visual encoding (userinfo_routes.py:740-745)
- Size: Exponentially scaled with score²
- Opacity: Linear 0.2-1.0 (keeps all points visible)
- Color: Viridis gradient (blue→yellow)
- Effect: Top results are large/bright/opaque, context results small/dim/transparent
## Result
- Search time: 40s → ~2s (20x faster)
- Visual contrast: Subtle → dramatic (clear result hierarchy)
- No arbitrary cutoffs: All results visible, best naturally highlighted
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Replace asyncio primitives with anyio equivalents throughout the codebase
to establish a single async pattern. This provides better structured
concurrency with automatic cancellation on errors and aligns with the
pytest anyio configuration.
Changes:
- hybrid.py: Replace asyncio.gather() with anyio task groups
- token_broker.py: Replace asyncio.Lock() with anyio.Lock()
- storage.py: Replace asyncio.run() with anyio.run()
- app.py: Replace tg.start_soon() with await tg.start() for task status
- processor.py: Add task_status parameter for structured startup
- scanner.py: Add task_status parameter for structured startup
- CLAUDE.md: Update async/await patterns guidance
The change from start_soon() to await tg.start() enables proper task
initialization signaling, ensuring background tasks are ready before
proceeding. This follows anyio best practices for structured concurrency.
All 118 unit tests pass with the new implementation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Improve user comprehension by scaling RRF scores to match the intuitive
0-1 range used by other search algorithms.
## Problem
RRF (Reciprocal Rank Fusion) scores had a drastically different scale
than semantic/keyword/fuzzy scores:
- Semantic similarity: 0.0 to 1.0 (typical: 0.5-0.9)
- RRF scores: 0.0 to ~0.016 (typical: 0.005-0.015)
This caused user confusion - a score of 0.0078 looked terrible but was
actually excellent (near theoretical maximum).
## Solution
Normalize RRF scores using the formula:
`normalized_score = rrf_score * (rrf_k + 1) / total_weight`
Where:
- rrf_k = 60 (RRF constant)
- total_weight = sum of algorithm weights (default: 1.0)
**Example transformation:**
- Before: 0.0078 (confusing)
- After: 0.477 (intuitive)
## Changes
**nextcloud_mcp_server/search/hybrid.py:**
- Store total_weight as instance variable (line 63)
- Calculate normalization factor in _reciprocal_rank_fusion() (line 209)
- Apply normalization to all RRF scores (line 217)
- Preserve raw RRF score in metadata for debugging (line 222)
## Impact
**User Experience:**
- Hybrid search scores now comparable with semantic/keyword/fuzzy
- Score of 0.5 indicates good match across all algorithms
- Consistent scale improves score threshold usability
**Backward Compatibility:**
- Raw RRF scores preserved in metadata["rrf_score_raw"]
- Result ordering unchanged (normalization is linear transformation)
- Breaking change: Existing score thresholds need adjustment
**Performance:**
- Negligible overhead (single multiplication per result)
## Testing
Verified with nc_semantic_search and nc_semantic_search_answer:
- Hybrid scores now 0.47-0.7 range (was 0.003-0.011)
- Semantic scores unchanged (0.75)
- Result ordering preserved
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Move access verification from individual search algorithms to final output
stage, eliminating redundant API calls and improving performance.
## Changes
**New:**
- `search/verification.py`: Centralized verification using anyio task groups
- Deduplicates results by (doc_id, doc_type) before verification
- Verifies all unique documents in parallel using structured concurrency
- Filters out inaccessible documents in single pass
**Modified Search Algorithms:**
- `search/semantic.py`: Removed _deduplicate_and_verify() and _verify_document_access()
- `search/keyword.py`: Removed _verify_access() and parallel verification
- `search/fuzzy.py`: Removed _verify_access() and parallel verification
- `search/hybrid.py`: Removed nextcloud_client parameter passing
All algorithms now return unverified results from Qdrant payload.
**Modified Output Stages:**
- `server/semantic.py`: Added verify_search_results() call after search
- `auth/viz_routes.py`: Added verify_search_results() call after search
Both endpoints now verify access once at final stage with deduplication.
## Performance Impact
**Before:**
- Hybrid mode (limit=10): 30 API calls (10 per algorithm × 3 algorithms)
- Single algorithm: 10-20 API calls (with verification buffer)
**After:**
- Hybrid mode (limit=10): 10 API calls (deduplicated verification)
- Single algorithm: 10 API calls (deduplicated verification)
**Performance Gain:** 3x reduction in API calls for hybrid search
## Architecture Benefits
- **Separation of concerns**: Algorithms handle scoring, output stage handles security
- **Deduplication**: Each document verified exactly once
- **Parallel execution**: All verifications run concurrently via anyio task groups
- **Consistency**: Same verification logic across MCP tools and viz endpoints
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Vector Visualization Improvements:
- Add interactive vector viz tab with Alpine.js and Plotly.js to user info page
- Refactor viz route CSS for better scoping and maintainability
- Remove unused nextcloud_host variable
Performance Optimizations:
- Parallelize access verification in fuzzy and keyword search algorithms
- Use asyncio.gather() to verify multiple documents concurrently
- Add exception handling with return_exceptions=True for resilience
Dependencies:
- Update third_party/oidc submodule to include RFC 9728 resource_url support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Skip tracing for /app/vector-sync/status to reduce noise from HTMX polling.
Metrics collection continues for this endpoint.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
BREAKING CHANGE: Search algorithms now require Qdrant to be populated.
Vector sync must be enabled and documents indexed for search to work.
- Keyword and fuzzy search now query Qdrant scroll API for title/excerpt
- Remove inefficient Nextcloud API fetching pattern
- Add optional Nextcloud verification for security
- Deduplicate by (doc_id, doc_type) tuple, keeping chunk_index=0
- Align with document processor pattern that already stores text in Qdrant
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>
Chris Coutinho