mirror of
https://github.com/Cinnamon/kotaemon.git
synced 2026-07-09 20:09:10 +02:00
9ad3e4e49a
* docs: typo * fix: enhance mention @ (file, websearch) in chat * fix: shorter placeholder guide in chat * fix: enhance UI (file filter, chunks preview, lightrag reader settings) * feat: feat: integrate paddleocr (PaddleOCR-VL, PP-StructureV3) * fix: import * fix: support both urls and mention files when chatting * feat: restore the test connection panel in resources * fix: paddleocr output adapter * tests: update * fix: parse image block content * fix: docker gpu stage for paddleocr * tests: update unit tests * tests: add skip_when_paddleocr_not_installed * fix: reset chunk preview filter when re-selecting file * fix: paddleocr[all] -> paddleocr[doc-parser] * fix: allow configure paddleocr device with env * feat: parameterize CUDA version in Dockerfile for paddlepaddle installation * docs: add integration guides for PaddleOCR and Docling * fix: updating mcp server must reflect in the tool choice UI * fix: disable enable_mkldnn for cpu inference * docs: update installation doc with uv * fix: use chat_input_text for llm input instead of the UI display message * fix: render file mentions as HTML and support unquoted names * fix: ensures proper cleanup of event listeners before replacing the Tribute instance. * test: updae unit tests --------- Co-authored-by: GSD Agent <kotaemon@example.com>
1.0 KiB
1.0 KiB
Docling
Kotaemon provides a Docling reader to enable local document ingestion with structure-aware parsing, including text, tables, and figures.
The reader is located under kotaemon/loaders/docling_loader.
Prerequisites
- Install Docling:
uv pip install -e "libs/kotaemon[docling]"
- Configure optional figure captioning:
Docling can generate figure captions when a VLM endpoint is available. Set KH_VLM_ENDPOINT in your .env file or application settings to enable captioning.
KH_VLM_ENDPOINT=http://your-vlm-endpoint
If KH_VLM_ENDPOINT is not set, Docling will still extract text, tables, and figure metadata, but it will skip generated figure captions.
Configure the loader
- Run Kotaemon and open the app UI.
- Navigate to Settings → Retrieval Settings → File loader.
- Select
Docling (figure+table extraction). - Save the settings, then upload or ingest a document. Kotaemon will use Docling during indexing and convert extracted content into
Documentobjects.