E134: Making Complex Data RAG-Ready with Unstructured

Topics covered
Popular Clips
Episode Highlights
Community
Unstructured's approach to community engagement is both practical and strategic. emphasizes the importance of providing practical tools and support, such as tutorials and Google Colab notebooks, to help users navigate data complexities 1. Despite a limited number of external contributors, the company focuses on coaching and assisting users in getting data to vector databases. This approach differentiates their community from others, as notes, "We're just doing a lot of coaching and a lot of help on that." 1
  Â
Market Fit
Achieving product market fit was a strategic goal for Unstructured, leveraging open source as a key mechanism. describes how open source allowed them to rapidly align with market needs, avoiding high customer concentration issues experienced at Primer 2. The open source project attracted a large user base, providing valuable feedback that informed both open source and commercial developments. "The amount of product feedback that we get from that is enormous and it is so valuable," he states, highlighting its role in refining their offerings 3.
  Â
Challenges
Balancing open source development with commercial priorities presents unique challenges. Brian Raymond4. The company employs a "white glove treatment" approach, with core engineers directly engaging with the community to provide support. This hands-on interaction helps manage the complexity of their projects, as Raymond notes, "You literally have the folks that are building it are the ones that are answering questions." 4
Related Episodes


E28: Rudderstack & Open Source Data Pipelines
Answers 383 questions

E13: Open-Source Data Streaming with Vectorized & Redpanda
Answers 383 questions

E143: Bringing Software Engineering Best Practices to Data
Answers 383 questions

E26: Cube.dev - Open Source Headless BI for Building Data Apps
Answers 383 questions

E21: Airbyte & Open-Source Data Integration
Answers 383 questions

E116: From Open Source DataHub to Closed Source Metaphor
Answers 383 questions

E117: Taking on Datadog with Open Source Observability
Answers 383 questions

E29: Building Data Intensive Applications Fast with Source-Available Materialize
Answers 383 questions

E30: Open Source Time-Series Data (simplified) with TimescaleDB
Answers 383 questions

E64: Open Source Data Observability with Elementary Data
Answers 383 questions

E14: Great Expectations for Your Data (Or, Building Superconductive)
Answers 383 questions

E82: Creating Apache Iceberg & Headless Data Warehouse Tabular
Answers 383 questions

E12: Open-Source Feature Management with Unleash
Answers 383 questions

E98: Creating the Time Series Data Category with InfluxData
Answers 383 questions

E105: Bringing Great Developer Experience to Data Teams with Dagster
Answers 383 questions
