Tensorlake + Qdrant: Fast, filtered retrieval for structured and unstructured documents
Just dropped a new integration for developers working with real-world documents and vector search: Tensorlake + Qdrant = structure-aware retrieval at scale. Instead of flat blobs, you can: • Parse PDFs into labeled fields extracting metadata like names, dates, balances, etc • Embed with semantic structure • Store and query with Qdrant filters that actually match your use case Built for RAG,...
Tensorlake API V2 and SDK 0.2.20
Over the last few weeks we have been working a ton on some huge improvements to our API and SDK. They are finally live 🥳 More announcements around this is coming soon, but if you didn't see the announcement in our Slack, make sure you use v2 API and SDK 0.2.20 🙌
📦 New Python Package: langchain-tensorlake
What’s New We just launched a native integration between LangChain and Tensorlake! Now you can pass unstructured documents to a LangGraph agent and trust that parsing, chunking, and field-level accuracy are handled by Tensorlake’s document engine — no hacky pipelines required. Why it matters Many LangChain projects break down when document structure is inconsistent, or field extraction needs to...
🚀 New Feature: Signature Detection just launched in Tensorlake!
Signatures might feel like a formality — until they delay a claim, break compliance, or derail a deal. That’s why we built Signature Detection into Tensorlake, giving you the power to track and act on signature presence inside your documents: 🔍 Basic Detection Detects whether any signature is present Returns bounding box coordinates and presence/absence flags 📚 Contextual Detection Associates...
