Index legal documents for hybrid search with Qdrant, OpenAI & BM25

by Jenny ✓ · 3,237 views · created 2025-08-27 · AI RAG, Multimodal AI

What this workflow does

This workflow has 30 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Qdrant (community). It also calls datasets-server.huggingface.co and api.openai.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Get Dataset Splits (HTTP Request): calls datasets-server.huggingface.co
2. Check Collection Exists (Qdrant): collection exists
3. Split Them All Out (Split Out): splits a list into separate items
4. If: checks a condition and branches into true / false
5. Get Dataset Rows (Pagination) (HTTP Request): calls an HTTP API
6. Create Collection (Qdrant): create collection
7. Divide Per Row (Split Out): splits a list into separate items
8. Restructure for Deduplicating (Edit Fields (Set)): sets 2 fields: id_qa, text
9. Deduplicate Texts (Summarize): summarizes / groups the items
10. Restructure for Batching (Edit Fields (Set)): sets 3 fields: idx, text, ids_qa

…plus 19 more steps. See the full node list below.

Services it uses

Qdrant (community)

HTTP calls to: datasets-server.huggingface.co, api.openai.com

Before you upgrade to n8n 3.0

Nodes used (11)

• Qdrantn8n-nodes-qdrant.qdrant
• Ifn8n-nodes-base.if
• Manual Triggern8n-nodes-base.manualTrigger
• Split Outn8n-nodes-base.splitOut
• HTTP Requestn8n-nodes-base.httpRequest
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Aggregaten8n-nodes-base.aggregate
• Limitn8n-nodes-base.limit
• Mergen8n-nodes-base.merge
• Summarizen8n-nodes-base.summarize
• Edit Fields (Set)n8n-nodes-base.set

From the author

Index Legal Dataset to Qdrant for Hybrid Retrieval This pipeline is the first part of "Hybrid Search with Qdrant & n8n, Legal AI". The second part, "Hybrid Search with Qdrant & n8n, Legal AI: Retrieval", covers retrieval and simple evaluation. Overview This…

View the original on n8n.io → Check your own copy