🚀 Attention Bay Area Generative AI developers and startups! I'm thrilled to invite you to join me at the MongoDB GenAI Hackathon with Amazon Web Services, sponsored by UnstructuredIO!

This event is also co-hosted with local communities: Women Founders Bay (@marianebekker) and

💡Last week, we announced an exciting collaboration with Microsoft and UnstructuredIO for a joint workshop on June 4th!

❗️We want to spotlight some details to showcase the value of this free event.

Our workshop aims to provide comprehensive training in deploying and

🚨New chunking strategies in the Unstructured API!

Chunk by page: on top of preserving semantic structure of the document, make sure the content from different pages doesn’t end up in the same chunk.
Chunk by similarity: make sure different topics are not mixed within the same

Join our Staff Developer Advocate Nina Lopatina at this upcoming workshop, and learn to build efficient RAG pipelines!

Building your own RAG system may seem daunting, but with the right tech stack, it becomes a manageable and rewarding task.

Making your #data ready for RAG is another challenge as the data might be in different format. That is where UnstructuredIO comes into handy.

I have

Ready to build your own RAG? Here’s the tech stack you need 👇

- LangChain as framework
- UnstructuredIO for data prep
- Fastembed for embedding
- Qdrant as vectorstore
- Llama3 via Groq Inc

Video: youtu.be/m_3q3XnLlTI

#rag #llm #groq #langchain #unstructured

Open Source Startup Podcast🎙 Robby Timothy Chen UnstructuredIO Thanks Open Source Startup Podcast🎙 for having me on!! It was great chatting about ingestion and preprocessing for LLMs and what it means to render your unstructured data 'Rag ready' lnkd.in/gwND-7ud

Another great tutorial on RAG with Llama3, incorporating Unstructured for data prep. In contrast to the tutorial we shared earlier that runs locally in a Colab notebook colab.research.google.com/drive/1BJYYyrP…, this one runs on Groq Inc

New Open Source Startup Podcast on making complex data RAG ready💪

Robby & Timothy Chen talk w/ UnstructuredIO Founder Brian Raymond on:

⚡️Why LLMs need their own ETL
⚡️Why the long tail of data matters for LLMs
⚡️Building a world-class brand

Want to extract metadata and chunking for better RAG, use UnstructuredIO ✨

Uploaded another video in the unstructured video series
👉extracting metadata and chunking
👉Used Chroma as Vector DB

YT video: youtu.be/JjSCezpZbI0

#unstructured #rag #chromadb #llm #metadata

🐍 Are you at PyCon US this week? Stop by JetBrains booth this Friday, say hi to Maria Khalusova 👋, get some fun stickers and learn to build you personal local RAG app for any combination of unstructured documents, in under 20 minutes.

🚀Have you tried GPT-4o yet? We just used it for 2x cheaper and 2x faster synthetic data generation for RAG evaluation with GPT-4! In this quick tutorial, we combine Unstructured's API for pdf document preprocessing with OpenAI's GPT-4o + ragas for RAG synthetic test data

📢 If you are at SW2 Conference today, don’t miss Christopher Maddock’s keynote at 5:40pm: 'LLMs Beyond the Lab: Refining RAG Performance'.
sw2con.com/#agenda

Chris will talk about enhancing RAG performance with better unstructured data on production systems. He’ll be going through

📢 If you are at SW2 Conference today, don’t miss Christopher Maddock’s keynote at 5:40pm: 'LLMs Beyond the Lab: Refining RAG Performance'.
sw2con.com/#agenda

Chris will talk about enhancing RAG performance with better unstructured data on production systems. He’ll be going through

Catch me at JetBrains booth at PyCon US this Friday, May 17th, at 4:10pm building a local RAG app with all sorts of documents -PDFs, markdown, HTML, emails...
Happy to chat about RAG, LLMs, unstructured data and AI in general 🤓

Streamline and optimize the data processing pipelines for LLMs with the Clarifai and UnstructuredIO integration! 🚀

Unstructured IO provides libraries with open-source components for ingesting and pre-processing data.

The following notebook is a step-by-step guide on how to

This is a great, accessible tutorial by Santiago on building a RAG application with open-source models. If you watch it and want to extend it to RAG with text in your pdfs, check out Unstructured's library for pre-processing unstructured data: github.com/Unstructured-I…

Want to extract image and image data from PDF ? Use
UnstructuredIO

Uploaded a video to 👇
👉 Extract image and image content from PDF
👉 Explain the image using LLaVA via ollama
👉 LangChain as framework for LLM

YT video: youtu.be/Ad-87wzJouk

#langchain #unstructured