Morphik – Open-source RAG that understands PDF images, runs locally
Hey HN, we’re Adi and Arnav. A few months ago, we hit a wall trying to get LLMs to answer questions over research papers and instruction manuals. Everything worked fine, until the answer lived inside an image or diagram embedded in the PDF. Even GPT‑4o flubbed it (we recently tried O3 with the same, and surprisingly it flubbed it too). Naive RAG pipelines just pulled in some text chunks and ignored the rest. We took an invention disclosure PDF (https://drive.google.com/file/d/1ySzQgbNZkC5dPLtE3pnnVL2rW_9...) containing an IRR‑vs‑frequency graph and asked GPT “From…
Morphik – Open-source RAG that understands PDF images, runs locally launched on April 22, 2025 with 200 votes, #176 of 7,818 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
Morphik is an open-source retrieval-augmented generation system designed to extract and answer questions from PDF documents containing images, diagrams, and embedded visual content. Built for researchers and professionals working with technical manuals and research papers, it runs locally and addresses the limitation of standard RAG pipelines that ignore images within PDFs. Unlike conventional approaches that struggle with visual information, Morphik processes both text and images to provide accurate answers to questions about document content.
written from the facts on this page · September 2026
From the sources
Open-source multimodal retrieval engine (Morphik Core). By Morphik — AI back office for skilled nursing & senior living (morphik.ai). - morphik-org/morphik-core
In the maker’s words, at launch
Hey HN, we’re Adi and Arnav. A few months ago, we hit a wall trying to get LLMs to answer questions over research papers and instruction manuals. Everything worked fine, until the answer lived inside an image or diagram embedded in the PDF. Even GPT‑4o flubbed it (we recently tried O3 with the same, and surprisingly…
Does a similar job
all alternatives →
Open-source Rule-based PDF parser for RAG2024 · github.com · ▲293The PDF parser is a rule based parser which uses text co-ordinates (boundary box), graphics and font data. The PDF parser works off text layer and also offers a OCR option to automatically use OCR if there are scanned pages in your PDFs. The OCR feature is based off a modified version of tika which uses tesseract underneath. The PDF Parser offers the following features: * Sections and subsections along with their levels. * Paragraphs - combines lines. * Links between sections and paragraphs. * Tables along with the section the tables are found in. * Lists and nested lists. * Join content…
Morphik – Open-source MCP server for technical document search2025 · docs.morphik.ai · ▲7Hey HN - we built Morphik MCP to solve a common problem: finding specific information across scattered technical docs. We've experimented with GraphRAG, ColPali, contextual embeddings, and more. MCP emerged as the solution that unifies these approaches. Features: - Multimodal search across text, diagrams, and videos - Natural language knowledge base management - Fully open-source with responsive support What sets MCP apart is its ability to return images (including diagrams) directly to the MCP client. Users have applied it to search over data ranging from blood tests to patents, and we use…
PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o2024 · github.com · ▲191I've developed a Python API service that uses GPT-4o for OCR on PDFs. It features parallel processing and batch handling for improved performance. Not only does it convert PDF to markdown, but it also describes the images within the PDF using captions like `[Image: This picture shows 4 people waving]`. In testing with NASA's Apollo 17 flight documents, it successfully converted complex, multi-oriented pages into well-structured Markdown. The project is open-source and available on GitHub. Feedback is welcome.
I built an open-source NotebookLM alternative using Morphik2025 · github.com · ▲23I really like using NoteBook LM, especially when I have a bunch of research papers I'm trying to extract insights from. For example, if I'm implementing a new feature (like re-ranking) into Morphik, I like to create a notebook with some papers about it, and then compare those models with each other on different benchmarks. I thought it would be cool to create a free, completely open-source version of it, so that I could use some private docs (like my journal!) and see if a NoteBook LM like system can help with that. I've found it to be insanely helpful, so I added a version of it onto the…
Demystifying Advanced RAG Pipelines2023 · github.com · ▲131I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features: -- An implementation of a sub-question query engine from scratch to answer complex user questions. -- Illustrative explanations that unveil the inner workings of the system. -- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation. -- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective. Key Takeaway:…
Questions this answers
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, April 2025
the whole month →
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.
Life & fun · 2025 · filiph.github.io
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
