FeaturedDocument Ops#RAG#Search#LLM#Grounded AI

RAG Q&A Agent

Search your Qdrant vector store for relevant context, then answer with an LLM — grounded in your own documents.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#RAG#Search#LLM#Grounded AI

Click a node to select it — same as the Heym editor; the panel shows its settings.

4 nodes · Free & source-available

RAG Q&A Agent

The retrieval-augmented answer pattern in four nodes: questionsearchansweroutput. Ground your LLM in your own documents and stop hallucinations at the source.

What this workflow does

  1. Input receives the user question
  2. RAG node (search mode) retrieves the top-K most relevant chunks from Qdrant
  3. LLM node uses the retrieved context to answer accurately
  4. Output returns the grounded answer

Use cases

  • Internal knowledge base chatbot
  • Policy and compliance Q&A
  • Product documentation assistant

Setup

Configure the RAG node with your Qdrant collection (same one used in the RAG Document Ingest template). The LLM system instruction already references $RagSearch.context — connect your preferred model.

FAQ

Can I combine both RAG templates? Yes — run Ingest once per document, then re-use Q&A for every question.

Which embedding model should I use? Use the same model in both Ingest and Q&A to ensure vector compatibility.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates