Скачать или смотреть Hybrid Search in Legal AI with Qdrant & n8n

You asked us to demo real-life use cases, so let’s build an end-to-end hybrid retrieval pipeline with Qdrant and n8n, from text embedding and indexing data in Qdrant to evaluating and testing a simple legal AI assistant.

You’ll learn how to use:
the Qdrant community node for batch uploads and hybrid retrieval (BM25 + dense embeddings);
Qdrant Cloud Inference (or OpenAI as an external embedding provider);

Public n8n templates you can build on:
Part 1, Indexing: https://n8n.io/workflows/7945-index-l...
Part 2, Retrieval: https://n8n.io/workflows/7946-evaluat...

00:00 Use Case Covered: Hybrid Retrieval in Legal AI
03:07 Part 1: Indexing Data to Qdrant
16:17 Part 2: Hybrid Retrieval (Setup & Evaluation) with Qdrant and n8n
23:30 Part 3: Testing Hybrid Retrieval on a Legal RAG Chatbot
27:16 Outro