Propagate Docling `self_ref` through PageElement so bboxes and graph nodes
share a stable identity. Add a Document/Graph mode switch to the reasoning
workspace; selecting a node highlights its bbox (numbered badge, focus ring,
optional dim of non-visited) and clicking a bbox re-centers the graph.
Backend — live runner
- New `POST /api/documents/:id/rag` endpoint. Loads `document_json` from
SQLite, reconstructs the DoclingDocument, wraps the model id in
`ModelIdentifier(ollama_name=...)`, and calls `agent._rag_loop`
off-thread (blocking sync call). Returns a `RAGResult` in the shape
the existing v1 import path already consumes, so the frontend overlay
is fully reused.
- `_rag_loop` is private upstream; we call it because `run()` wraps the
answer in a synthetic DoclingDocument and drops the iteration trace.
- Settings: `RAG_ENABLED`, `OLLAMA_HOST`, `RAG_MODEL_ID`. Router mounts
unconditionally; handler 503s when the flag is off or deps aren't
installed. `rag_available` surfaced in `/api/health`.
- Maps known docling-agent bugs to readable HTTP errors: 502 with
"the model couldn't produce a parseable answer" when `_rag_loop`
raises `IndexError` from `find_json_dicts([])[0]` after 3 + 3
rejection-sampling retries (model-dependent).
- Tests: 11 cases (flag off, query empty, no analysis, happy path,
model_id wrap, Ollama env, IndexError → 502, other errors → 500,
deps missing → 503).
Backend — bug fix
- Default `BATCH_PAGE_SIZE` flipped from `10` to `0` to match the
dataclass default. The old default silently dropped `document_json`
(see `domain/services.merge_results`) for any doc > 10 pages, which
broke the reasoning tunnel. Set `BATCH_PAGE_SIZE>0` explicitly on
memory-constrained deploys if batching is wanted.
Frontend — runner UX
- `features/reasoning/api.ts:runReasoning()` — POST wrapper.
- `RunReasoningDialog.vue` — query textarea + optional model_id
override. Blocks close while running, 20-40s loading state,
synthesises a sidecar-shaped envelope so the panel surfaces query +
model the same way an imported trace would.
- `ReasoningWorkspace.vue` — primary "Run reasoning" button; "Import
trace" relegated to ghost secondary.
- Store: `runDialogOpen`, `running`, `setRunning`.
Frontend — answer polish
- Answer rendered through `marked` + DOMPurify (models emit markdown
lists; `pre-wrap` rendered them as plain "1. …" strings).
- Dedicated answer block with orange border, "ANSWER" label, "Copy"
button (clipboard + "Copied ✓" feedback).
- IterationCard: drop the duplicate `response` block (the main answer
is authoritative); style reasons equal to `"fallback"` (docling-agent
`select_from_failure` placeholder) as italic muted "— no structured
rationale".
Frontend — node details contents
- Clicking a SectionHeader (or any node with compound children) lists
its contained elements in `NodeDetailsPanel` under a new "Contents"
block. Children come from the same `parentMap` used for Cytoscape
compound parenting (explicit PARENT_OF + synthetic section scope),
inverted once and cached as a computed.
- Click a child row → pan the viewport to it + swap the selection.
Housekeeping
- `cytoscape-navigator` removed from `package-lock.json` (follow-up
from the minimap removal in the previous commit).
Adds the `docling-agent` reasoning-trace viewer as a Studio tunnel, per
`docs/design/reasoning-trace.md`. Users pick an analyzed document, import
a RAGResult JSON, and the iterations are overlaid on the document graph.
Graph source is decoupled from Neo4j: a new pure builder
(`infra/docling_graph.build_graph_payload`) reads `document_json` from
SQLite and emits the same Cytoscape-shaped payload that `fetch_graph`
returns from Neo4j. Neo4j stays exclusive to the Maintain ingestion
pipeline. Shared DoclingDocument helpers live in `infra/docling_tree.py`
so TreeWriter and the builder can't drift on label taxonomy or tree walks.
Also removes the Cytoscape minimap (cytoscape-navigator) from GraphView:
second render instance hurt perf on large documents for no UX win.
Backend
- new `GET /api/documents/:id/reasoning-graph` (SQLite-only)
- new `infra/docling_tree.py`, `infra/docling_graph.py`
- `analysis_repo.find_latest_completed_by_document`
- tests: `test_docling_graph.py` (builder), `test_graph_api.py` (endpoint)
Frontend
- `features/reasoning/` — store, overlay, types, panel, import dialog,
workspace, doc picker
- new `ReasoningPage` + `/reasoning` and `/reasoning/:docId` routes
- `GraphView` gains a `fetcher` prop so reasoning can inject the
SQLite-backed fetcher while Maintain keeps using the Neo4j one
- drops minimap (nav container, dep, CSS)
- legend filters + section parenting extracted for reuse
- i18n base strings (FR + EN)
The `doc_items` field was added to `ChunkResult` earlier in the
feature branch (used by ChunkWriter for DERIVED_FROM edges), but the
test fixture was never updated. CI caught it now that the PR is open.
Fixes: tests/test_chunking.py::TestChunkResult::test_serializable
Previous query chained 6 OPTIONAL MATCH clauses for edges with no
intervening WITH collect(), producing a cartesian product. At 6 pages
(~60 elements, ~300 edges) Neo4j hit 102% CPU and hung > 5min.
Rewritten with one CALL {} subquery per node/edge type: each block
returns a single row with its collected list — no multiplication across
types. 6-page doc now returns in 213ms (was: no return).
Python reshape code (queries.py:137-210) untouched — record keys and
edge map shape preserved.
Refs: https://neo4j.com/developer/kb/using-subqueries-to-control-the-scope-of-aggregations/
ChunkWriter mirrors chunks into Neo4j after OpenSearch indexing, creating
HAS_CHUNK edges and DERIVED_FROM back-references to the source Elements
(via doc_items propagated from the local chunker).
Graph API: GET /api/documents/{id}/graph returns a cytoscape-shaped
payload with nodes + edges for Document / Element / Page / Chunk.
Hard cap at 200 pages returns HTTP 413 per design §8.4.
Frontend: new Graph tab in Studio results, rendered with Cytoscape.js +
dagre layout (lazy-loaded, ~175 KB gz). Legend, node styling per element
label, directional edges styled per edge type.
README gains a Neo4j section with the schema, three demo Cypher
queries, and env vars. Backend tests skip cleanly when the neo4j python
package is not installed locally.
Refs #186
Serialize a DoclingDocument to a Neo4j graph: Document + Page + Element
nodes with dynamic specific labels (SectionHeader, Paragraph, Table,
Figure, …), plus HAS_ROOT / PARENT_OF / NEXT / ON_PAGE edges. Replace-on-
write for idempotent re-ingestion.
The reader returns the verbatim document_json stored on the Document
node — reconstruction from graph nodes is deferred to v0.6.
Wired into AnalysisService._finalize_analysis: runs after conversion,
degrades gracefully by default, fails fast when neo4j_required is set.
Refs #186
Add Neo4j as an optional graph-native storage layer (ingestion profile).
Introduces infra/neo4j with a singleton async driver wrapper and an
idempotent bootstrap of constraints + indexes, wired into the FastAPI
lifespan. Integration tests skip when no live Neo4j is reachable.
Refs #186
Hybrid approach: reuse LocalChunker to chunk the DoclingDocument JSON
returned by Serve, so chunking works identically in both local and
remote modes without calling Serve's chunk endpoint.
Backend:
- _build_chunker() always returns LocalChunker (remove engine guard)
- Use docling-core[chunking] extra for required dependencies
- Skip client-side batching in remote mode (Serve manages its own
resources, and batching discards document_json needed for chunking)
- Fix Serve form fields: remove generate_page_images (not a Serve
field), use repeated form keys for to_formats and page_range
- Log Serve error response body on 4xx/5xx for diagnosis
- Fix FastAPI 204 DELETE routes missing response_model=None
Frontend:
- Update chunking feature flag to enable Prepare UI in remote mode
Closes#51
- Move DEFAULT_PAGE_WIDTH/HEIGHT to domain/value_objects.py and import in both converters
- Add opensearch_default_limit to Settings (configurable via OPENSEARCH_DEFAULT_LIMIT env var)
- Pass settings.conversion_timeout to ServeConverter, removing independent _DEFAULT_TIMEOUT
- Update OpenSearchStore to accept default_limit from Settings via constructor
Default value of 5 is now in the application code (settings.py) instead
of only in the Docker image ENV. Consistent across all deployment modes
(dev local, Docker, tests). Aligned docker-compose files and docs.
- Conditionally mount ingestion router only when OpenSearch + embedding are configured
- Add `ingestionAvailable` field to /api/health response
- Add `ingestion` feature flag to frontend (hides Search nav, Ingest button,
OpenSearch badge, indexed badges/filters when disabled)
- Skip ingestion polling when flag is off
- Make OpenSearch + embedding optional in docker-compose via profiles
- Add docker-compose.ingestion.yml override for full-stack ingestion
- Set BATCH_PAGE_SIZE=5 default in Docker local image
- Lead Quick Start with one-liner docker run command
- Document ingestion as opt-in with dedicated section
- Add BATCH_PAGE_SIZE, MAX_FILE_SIZE_MB, MAX_PAGE_COUNT, RATE_LIMIT_RPM to config tables
- Update test counts (380 backend, 159 frontend)
- Date CHANGELOG 0.4.0, bump frontend version to 0.4.0
- Sync CONTRIBUTING.md with E2E Karate test sections
Closes#180
Backend: GET /api/ingestion/search?q=…&doc_id=… endpoint with
SearchResponse schema. Frontend: search bar in Documents page, results
with filename, page, chunk index, relevance score. 3 new API tests.
Visual stepper in Studio topbar: Embedding → Indexing → Done.
Each step shows pending/active/done with animated dot. Store tracks
currentStep through the pipeline. Auto-resets after 2s.
- local_converter.py: remove redundant `_default_converter = None` in
except block of `_ensure_default_converter` (variable was already None,
re-raised immediately — dead store)
- test_analysis_service.py: replace bare `await task` with
`await asyncio.gather(task)` to satisfy static analysis
- Replace French mode strings (configurer/verifier/preparer) with English
equivalents (configure/verify/prepare) in StudioPage.vue and tests
- Extract _build_conversion_options, _run_conversion, _finalize_analysis
from _run_analysis_inner to respect Single Responsibility Principle
- Rename _get_default_converter to _ensure_default_converter to reflect
its lazy-init side effect
Closes#136, closes#137, closes#138
Frontend decoupling:
- Create shared/appConfig.ts as reactive bridge (locale, maxFileSizeMb,
maxPageCount) eliminating shared→features and feature→feature imports
- Give history feature its own Pinia store and API layer (was re-export
of analysis store)
- Give chunking feature its own Pinia store and API layer (was importing
from analysis)
- ChunkPanel receives analysis data via props instead of cross-feature
store import
- document/store reads maxFileSizeMb from shared config instead of
importing feature-flags store
- shared/i18n reads locale from shared config instead of importing
settings store
Backend:
- Add HealthResponse Pydantic schema for /api/health endpoint
Closes#140, closes#141, closes#142, closes#143
Add state-machine guard clauses to AnalysisJob transition methods
(mark_running, mark_completed, mark_failed, update_progress) to prevent
invalid status transitions. Make all domain value objects immutable with
frozen=True. Add 11 tests covering guard clause behavior.
Closes#132, closes#133
- Add DocumentRepository and AnalysisRepository protocols in domain/ports.py (#128)
- Refactor persistence repos from module functions to SqliteDocumentRepository
and SqliteAnalysisRepository classes
- Inject repos into AnalysisService and new DocumentService class via
constructor, removing direct imports of persistence and infra.settings (#129)
- Move _merge_results, _classify_error, _extract_html_body to domain/services.py (#130)
- Update main.py composition root to build and wire all dependencies
- Switch api/documents.py to Depends pattern matching api/analyses.py
- Update all tests to use injected mocks instead of module-level patches
Closes#128, closes#129, closes#130
Re-read the job from DB before mark_completed so that
progress_current/progress_total written during batched conversion
are not overwritten by the stale in-memory object.
Add regression unit test and e2e assertion on final progress values.
Set up a full E2E test suite (39 scenarios) using Karate against
the real API stack. Hybrid architecture: domain-based features +
cross-domain workflows, with data-driven testing and callable helpers.
Structure:
- e2e/pom.xml: Maven + karate-core 1.5
- 3 helpers (upload, analyze+poll, cleanup)
- 3 JSON schemas (health, document, analysis)
- 12 feature files across health, documents, analyses, workflows
- Tags: @smoke (2), @regression (35), @e2e (2)
- generate-test-data.py: fpdf2-based PDF generation (no binaries)
Also adds:
- RATE_LIMIT_RPM env var to make rate limiter configurable (0=disabled)
- CI job e2e with needs: [backend, frontend]
- e2e/ in .dockerignore
Closes#119
Replace hardcoded 5 MB upload limit with a configurable setting.
Backend exposes the value via /api/health, frontend reads it
dynamically for validation and UI messages.
Closes#48
pypdfium2 is imported in analysis_service for PDF page counting
(batch feature #56) but was missing from requirements.txt, causing
CI collection errors on all 4 test modules.
Use Docling's native page_range parameter to split large PDFs into
sequential batches, preventing memory exhaustion and timeouts.
Progress is reported via existing polling mechanism.
Closes#56
Use `import infra.local_converter as lc_mod` consistently instead of
mixing `import` and `from ... import` for the same module.
Addresses CodeQL review comment on PR #58.
Raw PyTorch/Docling stack traces are no longer shown to the user.
Common failures (missing compiler, OOM, lock contention, corrupted
document) are mapped to actionable messages. Unknown errors are
truncated to 200 chars.
Ref #57 (M1)
If the lazy-init of the default converter fails (e.g. model download
error), the singleton was left as None but subsequent calls would not
retry. Now the failed state is cleared so the next request retries.
Ref #57 (H5)
TableFormerMode.ACCURATE is very expensive on CPU (~3-5x slower).
The default can now be set to "fast" on resource-constrained
environments (HF Spaces) via the DEFAULT_TABLE_MODE env var.
User-specified table_mode in the request still takes precedence.
Ref #57 (H1)
Defense-in-depth: even if upload validation passes, Docling itself
now enforces page count and file size limits. Configurable via
MAX_PAGE_COUNT and MAX_FILE_SIZE env vars (0 = unlimited).
Ref #57 (C3)
A frozen conversion holding the lock indefinitely blocks all subsequent
jobs. Using lock.acquire(timeout=300) fails fast with a clear error
instead of waiting forever.
Ref #57 (C2)
Docling's native document_timeout is the only mechanism that can
interrupt processing inside a blocked thread (OCR, table extraction).
Without it, asyncio.wait_for cannot stop a frozen conversion.
Configurable via DOCUMENT_TIMEOUT env var (default: 120s).
Closes#57 (C1)
