My solution for the "Agentic Arena Community Contest" (RAG, Qdrant, Mistral OCR)

by Davide Boizza ✓ · 1,188 views · created 2025-09-26 · AI RAG

What this workflow does

This AI workflow has 34 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Evaluation, OpenAI Chat Model, Embeddings OpenAI and Qdrant Vector Store and 2 more. It also calls xx.xx.xx:6333 and api.mistral.ai over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).

1. Refresh collection (HTTP Request): calls xx.xx.xx:6333 (POST)
2. Get PDF (Google Drive): download
3. Eval Input (Edit Fields (Set)): sets 2 fields: chatInput, sessionId
4. Search PDFs (Google Drive): work with file folder
5. Mistral Upload (HTTP Request): calls api.mistral.ai (POST)
6. Filter: keeps only the items that match a condition
7. Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
8. Mistral Signed URL (HTTP Request): calls an HTTP API
9. AI Agent: runs an AI agent, with model: OpenAI Chat Model; 1 tool (RAG); memory: Simple Memory
10. Get File ID (Edit Fields (Set)): sets 1 field: file_id

…plus 12 more steps. See the full node list below.

Services it uses

EvaluationOpenAI Chat ModelEmbeddings OpenAIQdrant Vector StoreGoogle DriveReranker Cohere

HTTP calls to: xx.xx.xx:6333, api.mistral.ai

Before you upgrade to n8n 3.0

Nodes used (21)

• Evaluationn8n-nodes-base.evaluation
• Edit Fields (Set)n8n-nodes-base.set
• Evaluation Triggern8n-nodes-base.evaluationTrigger
• Chat@n8n/n8n-nodes-langchain.chat
• Filtern8n-nodes-base.filter
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Manual Triggern8n-nodes-base.manualTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Coden8n-nodes-base.code
• Waitn8n-nodes-base.wait
• Qdrant Vector Store@n8n/n8n-nodes-langchain.vectorStoreQdrant
• Execute Workflow Triggern8n-nodes-base.executeWorkflowTrigger
• Google Driven8n-nodes-base.googleDrive
• Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter
• AI Agent@n8n/n8n-nodes-langchain.agent
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• Reranker Cohere@n8n/n8n-nodes-langchain.rerankerCohere
• Execute Sub-workflown8n-nodes-base.executeWorkflow

From the author

🤖📈 This workflow is my personal solution for the Agentic Arena Community Contest, where the goal is to build a Retrieval-Augmented Generation (RAG) AI agent capable of answering questions based on a provided PDF knowledge base. --- Key Advantages ✅…

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