Learn how to use Engram effectively, from writing topic descriptions that control extraction to choosing bounded topics and scopes, selecting a retrieval mode, and placing memories in your prompt without hurting prompt-cache efficiency.
PDFs full of charts and tables are notoriously hard to put through a traditional RAG pipeline. In this post, we show how late-interaction multi-vector retrieval lets you search PDFs by what the page looks like: no OCR, no chunking, no text extraction.
Server-side batching, retries, the blobHash data type, and multimodal ingestion — what to use when, with code.
Use Weaviate's built-in MCP server to give Claude Code, Cursor, and VS Code hybrid search over your codebase and docs. No glue code.
Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind how this all works and walks through three practical implementations using Weaviate and Gemini.
Learn how we built a production-ready, end-to-end RAG application in just 36 hours using the Query Agent and the new Weaviate Agent Skills library.
Hands-on patterns: Design pattern for gen-AI enterprise applications, with Arize AI.
A guide to seamlessly transform data sitting in lakes and warehouses for GenAI capable applications
Learn about how you can build multi-agent systems with CrewAI and Weaviate.
Elysia is an open-source, decision tree-based agentic RAG framework that dynamically displays data, learns from user feedback, and chunks documents on-demand. Built with pure Python logic and powered by Weaviate, it's designed to be the next evolution beyond traditional text-only AI assistants.
LangChain and the Weaviate TypeScript v3 client power scalable AI with fast, type-safe RAG workflows, practical code, and future-ready features like LLM eval and event-driven design.
Design for speed, build for experience.
