cdc-si/preprocessing
Watch
2
mirror of https://github.com/cdc-si/preprocessing.git synced 2026-08-26 10:14:18 +00:00
Code Releases Activity
Read-only mirror of https://github.com/cdc-si/preprocessing — Zentrale Ausgleichsstelle ZAS. Issues & pull requests at the source.
26 commits 4 branches 0 tags 18 MiB
  • Python 100%
Find a file
Exact
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Schubert Kieran 88cb39089c update gitignore
2026-06-18 16:41:29 +02:00
examples add VLM pipeline example with docling 2026-05-07 16:58:27 +02:00
src/pdf-ocr-pipeline feat: enable authentication and specify service account for the inference service 2026-06-18 16:41:17 +02:00
.env.example add VLM pipeline example with docling 2026-05-07 16:58:27 +02:00
.gitignore update gitignore 2026-06-18 16:41:29 +02:00
README.md feat: add README.md 2026-03-10 09:52:23 +01:00

README.md

Preprocessing

A collection of preprocessing pipelines for ingesting documents into a RAG vector database.

Pipelines

Pipeline Description
pdf-ocr-pipeline Converts PDFs into chunked, embedded documents via VLM-based OCR