Top all-time · #7318
Unstructured
Company blog · unstructured.io/blogaidata
Unstructured is the company blog at unstructured.io, writing about ai and data. Since 2024, 11 different Hacker News readers have linked it 19 times. No feed was found, so read it on the site itself.
Too few sampled comments (8) to say how often HN recommends it.?
Why HN links it
Linked as a document-parsing tool for preparing files such as PDFs for LLM and RAG use, and as a comparison point against similar products like LlamaParse. Comments do not assess any writing.
Summarised by Claude from a sample of 8 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Turn PDFs, scans, spreadsheets and 50+ file types into clean, structured data for RAG and AI agents. Use Unstructured Transform via API or MCP. Start free.
Most-linked posts?
- /6 people · 7 mentions · first linked 2024-01-22
What Hacker News says?
Other Document parsers for use in LLM/RAG that are not mentioned in this thread https://unstract.com/llmwhisperer/ https://unstructured.io/ https://docs.llamaindex.ai/en/stable/llama_cloud/llama_parse... https://www.eyelevel.ai/
Comment linking /
on “Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs”Submitted Understanding What Matters for LLM Ingestion and Preprocessing as a story · 60 points
HN discussionThe primary challenge is not just about harnessing AI for search; it's about preparing complex documents of various formats, structures, designs, scans, multi-layout tables, and even poorly captured images for LLM consumption. This is a crucial issue. There is a 20 min read on why parsing PDFs is hell: https://unstract.com/blog/pdf-hell-and-practical-rag-applica... To parse PDFs for RAG applications, you'll need too…
Comment linking /
on “Ask HN: I have many PDFs – what is the best local way to leverage AI for search?”Submitted Choosing the right embedding model for a RAG system as a story · 4 points
HN discussionCurious - what do you guys use for the T step of your ELT? With nested blocks 12 layers deep, I can imagine it gets complicated to try to de-normalize using regular SQL. Have you explored a pattern like https://runtrellis.com or https://unstructured.io/ for unnesting?
Comment linking /
on “Building and scaling Notion's data lake”Submitted Why frontier models haven't replaced document processing as a story · 3 points
HN discussionReally cool project! I'm doing something similar at a very small scale for my personal project using TypeChat with Zod ( https://github.com/microsoft/Typechat ) and Unstructured ( https://unstructured.io/ )
Comment linking /
on “Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data”Submitted How to chose an embedding model for your RAG as a story · 2 points
HN discussionCurious how this compares to platforms like https://unstructured.io/
Comment linking /
on “Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data”Submitted Understanding embedding models: make an informed choice for your RAG as a story · 2 points
HN discussionI wonder how LlamaParse compares head to head with https://unstructured.io
Comment linking /
on “LlamaCloud and LlamaParse”Submitted Understanding embedding models: make an informed choice for your RAG as a story · 2 points
HN discussionVery nice tool! Just last week, I was working on extracting information from PDFs for an automation flow I’m building. I used Unstructured ( https://unstructured.io/ ), which supports multiple file types, not just PDFs. However, my main issue is that I need to work with confidential client data that cannot be uploaded to a third party. Setting up the open-source, locally hosted version of Unstructured was quite cumb…
Comment linking /
on “Show HN: Documind – Open-source AI tool to turn documents into structured data”Submitted Understanding embedding models: make an informed choice for your RAG as a story · 2 points
HN discussionFine-tuning is not a good approach to integrating new knowledge into an LLM. It's a good way to drive the direction of the LLM's style, structure of responses (e.g., length, format). I'd say RAG is still very much the way to go. What you need to then do is optimize how you chunk and embed data into the RAG database. Pinecone has a good post on this[1] and I believe others[2] are working on more automated solutions.…
Comment linking /
on “Ask HN: What's the state of LLM knowledge retrieval in Jan 2024?”Submitted Understanding embedding models: make an informed choice for your RAG as a story · 2 points
HN discussionSubmitted Unstructured's New Models Outparse GPT-6, Claude and Gemini as a story · 1 points
HN discussionSubmitted How to Parse a Form as a story · 1 points
HN discussionSubmitted RAG Chat with Unstructured Data as a story · 1 points
HN discussion