admin/mcp-nextcloud
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,102 Commits 1 Branch 0 Tags
main
Commit Graph
5 Commits
Author SHA1 Message Date
Chris CoutinhoandClaude Opus 4.8 c21804fbbc feat(ingest): split OCR into tier2 in-cluster (GPU, gateway-only) + tier3 upstream 
Insert a configurable in-cluster OCR rung into the escalation ladder (Deck #353):
a tier2-eligible doc is OCR'd on the on-demand burst GPU before falling through to
paid upstream OCR. The in-cluster backend is reached ONLY via the embedding gateway
(model prefix routes to the GPU over the tailnet) and is a config value (default
surya/surya-ocr-2, swappable to e.g. lightonocr) — never hard-coded.

Ladder: fast -> structured -> ocr-incluster -> ocr-upstream
(queues ingest-ocr-incluster / ingest-ocr-upstream).

- escalation.py: 4-tier ladder; in-cluster flag folded into the dead-letter signature.
- ocr.py: OcrProcessor(name, tier, model_setting, gateway_only); build_ocr_backend(
  ..., model=, gateway_only=) — gateway_only forces the gateway backend (never the
  direct Mistral fallback), disabling the tier with a warning if no gateway URL.
- registry.py: per-rung enable map; scanned docs target minimum="ocr-incluster";
  inline path runs the cheapest available OCR rung.
- procrastinate.py: two OCR queues; legacy ingest-ocr kept as a drain target.
- config.py: DOCUMENT_OCR_INCLUSTER_ENABLED (off) + DOCUMENT_OCR_INCLUSTER_MODEL.
- __init__.py: register the two OCR instances; vector/processor.py: pages_ocr
  metered for the upstream (paid) rung only; cli.py: new --tier choices + legacy drain.
- metrics.py: zero the legacy ingest-ocr queue gauge during rollout.
- tests: migrated to the split ladder + new tests (gateway-only forcing, per-tier
  model incl. lightonocr override, no-hard-coded-surya guard). 1792 pass; ruff + ty green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-17 23:28:29 +02:00
Chris CoutinhoandClaude Opus 4.8 3bd1b46d9c feat: tier-3 OCR processor (gateway or direct Mistral) 
Adds the OCR escalation target the tiered registry already routes to. Scanned /
no-text-layer PDFs (the tier-0 "ocr" verdict) escalate here when
document_ocr_enabled (default off).

Two interchangeable backends, selected by document_ocr_provider
(auto | gateway | mistral | none):
- gateway: POST to the Astrolabe Cloud model gateway's /v1/ocr -- the same
  M2M-authenticated gateway as embeddings, so NO provider keys live in the pod
  (the platform default; reuses EMBEDDING_GATEWAY_URL + the M2M creds).
- mistral: call the Mistral OCR API directly from the pod (MISTRAL_API_KEY), for
  self-hosters / deployments without the gateway.
"auto" prefers the gateway, then direct Mistral.

Both return per-page markdown joined into text + exact page_boundaries (the
pdf_highlighter contract; bbox re-derived from the PDF bytes as for other tiers).
Validated end-to-end via direct Mistral on the scanned Student 147.pdf:
success, 15 pages, 22k chars, offsets exact, ~4s.

Settings: document_ocr_provider (enum-validated), document_ocr_model
("mistral/mistral-ocr-latest" -- gateway routes on the prefix, the direct mistral
backend strips it). OcrProcessor registered at lowest priority so it is never the
non-tiered default.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-05 01:42:35 +02:00
Chris CoutinhoandClaude Opus 4.8 c48a797896 feat: tiered PDF processor with pypdfium2 fast path (deprecate pymupdf4llm) 
Replaces single-engine pymupdf4llm extraction with a tiered pipeline (Deck #205,
follows the tier-0 classifier #855). pypdfium2 becomes the default and only
hot-path PDF extractor; pymupdf4llm is deprecated to a rollback toggle.

Why: pymupdf4llm's O(n^2) find_tables drove the OOM (#852) and the form-PDF
parse timeouts (#856), carries AGPL/commercial licensing liability, and -- per
the benchmarks -- recovers near-zero usable tables on the real corpus. pypdfium2
(Apache/BSD) extracts the same text far faster (Student 1a.pdf: 120s timeout ->
0.2s) with no table-detection bomb.

- document_processors/pypdfium2_fast.py: tier-1 "fast" processor emitting text +
  exact page_boundaries (the pdf_highlighter contract). pymupdf processor is now
  tier "structured" (the rollback engine), registered but not default.
- registry: tiered routing in ProcessorRegistry. tier-1 fast extracts, then
  classification is DERIVED from that text (classifier.classify_from_text -- no
  PDF re-open), records the classification metrics, and escalates scanned /
  no-text-layer docs to the "ocr" tier when document_ocr_enabled (default off;
  no provider yet, so fast is terminal). Wires record_document_escalation + the
  real "escalated" span attribute (was hardcoded False).
- Removes the separate _shadow_classify pass from vector/processor.py -- it
  re-opened every PDF and re-extracted text (~0.5-1.3s/doc of pure duplicated
  CPU that lowered throughput); classification now rides the tier-1 extraction.
- Settings: document_tier1_engine ("pypdfium2" default | "pymupdf" rollback,
  enum-validated), document_ocr_enabled (default false).

Tests: pypdfium2 extractor, registry tiering (fast routing, rollback, classify
recording, OCR escalation on/off), classify_from_text. Full unit suite green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-05 01:32:14 +02:00
Chris CoutinhoandClaude b8010270c1 fix: Add async/await, PDF metadata, and type safety fixes 
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>
 2025-11-20 02:37:07 +01:00
Chris CoutinhoandClaude 2147fc1696 refactor: Transform document parsing into pluggable processor architecture 
Refactors PR #190's hardcoded Unstructured.io integration into a flexible,
extensible plugin system supporting multiple text extraction engines.

- **`DocumentProcessor` ABC**: Abstract interface for all processors
- **`ProcessorRegistry`**: Central registry for discovery and routing
- **`ProcessingResult`**: Standardized output format across processors

- **`UnstructuredProcessor`**: Refactored from `UnstructuredClient`
- **`TesseractProcessor`**: Local OCR for images (lightweight alternative)
- **`CustomHTTPProcessor`**: Generic wrapper for custom HTTP APIs

- New `get_document_processor_config()` returns structured config
- Supports enabling/disabling individual processors
- Per-processor configuration via environment variables
- **Breaking Change**: `ENABLE_UNSTRUCTURED_PARSING` replaced with:
  - `ENABLE_DOCUMENT_PROCESSING=true/false` (master switch)
  - `ENABLE_UNSTRUCTURED=true/false` (per-processor)
  - `ENABLE_TESSERACT=true/false`
  - `ENABLE_CUSTOM_PROCESSOR=true/false`

- `parse_document()` now uses `ProcessorRegistry`
- Auto-selects appropriate processor based on MIME type
- Processor priority system (Unstructured=10, Tesseract=5, Custom=1)

- `initialize_document_processors()` registers processors at startup
- Integrated into both BasicAuth and OAuth lifespans
- Graceful degradation if processors fail to initialize

```env
ENABLE_DOCUMENT_PROCESSING=false

ENABLE_UNSTRUCTURED=false
UNSTRUCTURED_API_URL=http://unstructured:8000
UNSTRUCTURED_STRATEGY=auto  # auto|fast|hi_res
UNSTRUCTURED_LANGUAGES=eng,deu

ENABLE_TESSERACT=false
TESSERACT_LANG=eng

ENABLE_CUSTOM_PROCESSOR=false
CUSTOM_PROCESSOR_URL=http://localhost:9000/process
CUSTOM_PROCESSOR_TYPES=application/pdf,image/jpeg
```

- **Removed**: `tests/test_unstructured_config.py` (legacy tests)
- **Added**: `tests/unit/test_document_processor_config.py`
  - 7 unit tests for new config system
  - Tests individual and multi-processor configurations

- **Added**:
  - `nextcloud_mcp_server/document_processors/__init__.py`
  - `nextcloud_mcp_server/document_processors/base.py`
  - `nextcloud_mcp_server/document_processors/registry.py`
  - `nextcloud_mcp_server/document_processors/unstructured.py`
  - `nextcloud_mcp_server/document_processors/tesseract.py`
  - `nextcloud_mcp_server/document_processors/custom_http.py`
  - `tests/unit/test_document_processor_config.py`

- **Modified**:
  - `nextcloud_mcp_server/config.py` - New plugin config system
  - `nextcloud_mcp_server/app.py` - Processor initialization
  - `nextcloud_mcp_server/utils/document_parser.py` - Uses registry
  - `nextcloud_mcp_server/server/webdav.py` - Import updates
  - `env.sample` - New configuration format
  - `docker-compose.yml` - (profile changes from previous work)

- **Removed**:
  - `nextcloud_mcp_server/client/unstructured_client.py` - Replaced by UnstructuredProcessor
  - `tests/test_unstructured_config.py` - Replaced with new tests

✅ **Extensible**: Add processors without modifying core code
✅ **Testable**: Mock processors for unit tests
✅ **Configurable**: Enable only needed processors
✅ **Flexible**: Choose fast (Tesseract) vs accurate (Unstructured)
✅ **Opt-in**: Disabled by default, no mandatory dependencies

Users upgrading from PR #190 need to update environment variables:
```bash
ENABLE_UNSTRUCTURED_PARSING=true

ENABLE_DOCUMENT_PROCESSING=true
ENABLE_UNSTRUCTURED=true
```

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-25 19:28:35 +02:00