trustgraph/.gitignore
cybermaggedon bdfdbb3c1f
feat: add Docling-based document decoder as alternative to unstructured (#1054)
Add trustgraph-docling package providing a document decoder powered by
IBM's Docling library. Supports PDF, DOCX, XLSX, PPTX, HTML, Markdown,
and CSV with two chunking modes:

- page mode (default): groups output by page for page-based formats,
  emits TextDocument messages for the existing downstream chunker
- hybrid mode: uses Docling's HybridChunker for structure-aware
  semantic chunking, emits Chunk messages directly

Tables are preserved as HTML markup. Images are stored in the librarian
with provenance but excluded from the text pipeline. Full provenance
chain is maintained for explainability tracing.

Includes Containerfile, CI/CD integration (PR checks and release
workflows), Makefile targets, and tech spec documentation.

Added unit tests for the package.
2026-07-20 21:25:33 +01:00

23 lines
684 B
Text

*~
__pycache__/
env/
*/build/
*.egg-info/
*.parquet
templates/values/version.jsonnet
trustgraph-base/trustgraph/base_version.py
trustgraph-cli/trustgraph/cli_version.py
trustgraph-bedrock/trustgraph/bedrock_version.py
trustgraph-embeddings-hf/trustgraph/embeddings_hf_version.py
trustgraph-flow/trustgraph/flow_version.py
trustgraph-ocr/trustgraph/ocr_version.py
trustgraph-parquet/trustgraph/parquet_version.py
trustgraph-vertexai/trustgraph/vertexai_version.py
trustgraph-unstructured/trustgraph/unstructured_version.py
trustgraph-mcp/trustgraph/mcp_version.py
trustgraph-docling/trustgraph/docling_version.py
trustgraph/trustgraph/trustgraph_version.py
vertexai/
venv/
.venv/
.env