docling-studio/document-parser
Pier-Jean Malandrino 4c3870bf3e feat(#72): orchestrated ingestion pipeline — Docling → embedding → OpenSearch
Add IngestionService chaining analysis chunks → EmbeddingClient → OpenSearchStore.
Idempotent: existing doc chunks deleted before re-indexing. REST API:
  POST /api/ingestion/{jobId}, DELETE /api/ingestion/{docId}, GET /api/ingestion/status.
Wired in lifespan when OPENSEARCH_URL + EMBEDDING_URL are set. 25 new tests.
2026-04-10 21:45:52 +02:00
..
api feat(#72): orchestrated ingestion pipeline — Docling → embedding → OpenSearch 2026-04-10 21:45:52 +02:00
domain feat: add embedding microservice and EmbeddingService port 2026-04-10 20:53:24 +02:00
infra feat: add embedding microservice and EmbeddingService port 2026-04-10 20:53:24 +02:00
persistence fix(arch): inject repositories and extract domain logic 2026-04-10 11:44:33 +02:00
services feat(#72): orchestrated ingestion pipeline — Docling → embedding → OpenSearch 2026-04-10 21:45:52 +02:00
tests feat(#72): orchestrated ingestion pipeline — Docling → embedding → OpenSearch 2026-04-10 21:45:52 +02:00
.dockerignore Work on full Docker integration 2026-03-17 13:33:36 +01:00
conftest.py Format backend codebase with ruff 2026-04-02 12:33:07 +02:00
Dockerfile Fix RapidOCR model download permission in local image 2026-04-03 10:44:20 +02:00
main.py feat(#72): orchestrated ingestion pipeline — Docling → embedding → OpenSearch 2026-04-10 21:45:52 +02:00
package-lock.json Add slide on side bar in Studio mode 2026-03-20 16:24:38 +01:00
pyproject.toml Add qualityt check and contributing doc 2026-03-21 15:34:54 +01:00
pytest.ini Add a stronger testing strategy 2026-03-18 14:46:37 +01:00
requirements-local.txt Move bbox.py from domain/ to infra/ and unify coordinate logic 2026-04-03 13:17:26 +02:00
requirements.txt feat(infra): add OpenSearch adapter implementing VectorStore port 2026-04-10 20:48:50 +02:00