"Indexify Unveiled: A Scalable and Near Real-time Content Extraction Engine for Multimodal Unstructured Data" by Diptanu Gon Choudhury, Founder at Tensorlake
Abstract:
Talk about Indexify our product, vector database, retrieval systems, memory in agents, and RAG.
The need for compute engines for Unstructured Data
Importance of Hybrid Search
RAG vs Finetuning
Talk Takeaways: We need powerful online systems that can keep indexes updated for building real-world LLM applications
Diptanu's Bio:
Diptanu is the founder of Tensorlake. They are building Indexify - an open-source scalable structured extraction engine for unstructured data to build near-real-time knowledgebase for AI/agent-driven workflows and query engines.
Before building Indexify, Diptanu created the Nomad cluster scheduler at Hashicorp, inventor of the Titan/Titus cluster scheduler at Netflix, led the FBLearner machine learning platform, and built the real-time speech inference engine at Facebook.
--------------------------------------------------------------------------------
Connect with Diptanu and Indexify:
/ diptanu
/ diptanu
https://getindexify.ai
Connect with Demetrios:
/ dpbrinkm
Follow Qdrant:
/ qdrant
/ qdrant_engine
Join the Qdrant Discord server:
/ discord