Evaluate Hybrid Search for Legal QA with Qdrant & BM25/mxbai

Evaluates hybrid search (BM25 + mxbai embeddings + RRF) on LegalQAEval dataset using Qdrant, calculating hits@1 accuracy for top retrievals.

This n8n workflow is the second part of a hybrid search series for Legal AI, focusing on evaluation after indexing (Part 1). It performs hybrid retrieval on a Qdrant collection using questions from the LegalQAEval dataset. Hybrid search combines BM25 keyword matching, mxbai-embed-large-v1 semantic embeddings, and Reciprocal Rank Fusion (RRF) for optimal ranking. Embeddings are generated via Qdrant Cloud Inference or external providers like OpenAI. On a subset of questions, it retrieves top text
Platform
n8n
Category
Business Operations & ERPs
Price
$24.99
Creator
Pierre Farouk

How to import this workflow into n8n

  1. 1Purchase or download the workflow to get the n8n workflow JSON file.
  2. 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
  3. 3Open each node marked with a credential warning and connect your own accounts and API keys.
  4. 4Run the workflow once manually to verify the data flow, then toggle it to Active.

Related Business Operations & ERPs workflows

More from Pierre Farouk

Need this deployed? We'll set it up for you.

Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.