Index Legal Documents for Hybrid Search Using Qdrant, OpenAI, and BM25 - n8n Workflow | Neura Market
Index Legal Documents for Hybrid Search Using Qdrant, OpenAI, and BM25
Transform and index a legal dataset into Qdrant for hybrid retrieval, combining dense and sparse vectors for semantic and keyword-based searches.
This workflow is the first part of a two-part series designed to implement hybrid search capabilities using Qdrant and n8n. It processes a legal Q&A corpus from Hugging Face, converting it into vector representations and indexing them into Qdrant. This setup enables hybrid search by leveraging dense vectors for semantic similarity and sparse vectors for keyword-based retrieval using BM25. The workflow supports embedding inference through Qdrant Cloud or external providers like OpenAI.
Platform
n8n
Category
AI & Machine Learning
Price
Free
Creator
Priya Patel
dense-vectors
sparse-vectors
if
set
limit
merge
splitOut
qdrant
aggregate
summarize
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.