#69 · Primary category: Knowledge Base & RAG

morphik-core

artificial-intelligence cache-augmented-generation colpali database litellm multimodal rag rules-based-ingestion

Open-source multimodal retrieval engine (Morphik Core). By Morphik — AI back office for skilled nursing & senior living (morphik.ai).

Project last updated:07/23/26

GitHub Stars

3.7K

Forks

327

Contributors

21

License

Other

Why we included this project

Classic text-only retrieval has a blind spot for documents where the meaning lives in the layout: in a technical PDF, the tables, diagrams, and page structure carry information that disappears when you strip the file down to its extracted text. Morphik Core is a multimodal retrieval engine built for exactly this case, using visual-document techniques like ColPali so a query matches what is actually rendered on the page. Ingesting a file is a single SDK call, and a natural-language question about a 500-page manual returns the right fragments without you stitching together your own OCR, embedding, and vector-search stack. It is a standalone, self-hostable platform with a Python SDK, REST API, web console, and MCP interface, which fits managed setups and teams that want to control their own deployment alike. Before a large commercial rollout, check the Business Source license, since the free tier is tied to revenue thresholds.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category