Show HN: Morphik – Open-source RAG that understands PDF images, runs locally

Re:Show HN: Morphik – Open-source RAG that understands PDF i... by Imanari on Tuesday April 22, 2025 @02:50PM (#43765104)

Looks really nice! How does it handle tables?

[ Parent | on HN ]

Re:Show HN: Morphik – Open-source RAG that understands PDF i... by Adityav369 on Tuesday April 22, 2025 @02:58PM (#43765182)

We have two ingestion pathways: 1. regular OCR + text embeddings; 2. Colpali. We've observed that Colpali does a much better job with tables since it can encode positional stuff and layouts as well.

[ Parent | on HN ]

Re:Show HN: Morphik – Open-source RAG that understands PDF i... by th0ma5 on Tuesday April 22, 2025 @04:06PM (#43765751)

Whenever I ask people wanting to use such features at scale which figure could be out of place or have a transposed digit it generally makes the project evaporate.

[ Parent | on HN ]