Run multi-model research analysis and email reports with GPT-4, Claude and NVIDIA NIM

by Cheng Siong Chin ✓ · 306 views · created 2026-01-07 · Document Extraction, AI RAG

What this workflow does

This workflow has 39 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Postgres and Slack.

How it runs

Trigger: When an HTTP POST request hits its webhook URL.

1. Workflow Configuration (Edit Fields (Set)): sets 14 fields: azureHealthEndpoint, awsHealthEndpoint, googleHealthEndpoint…
2. Parse Request & Validate (Code): runs custom JavaScript code
3. Analyze Prompt Complexity (Code): runs custom JavaScript code
4. Check Azure OpenAI Health (HTTP Request): calls an HTTP API
5. Check AWS Bedrock Health (HTTP Request): calls an HTTP API
6. Merge: merges the data from its input branches
7. Score & Rank Models (Code): runs custom JavaScript code
8. Check Policy Constraints (If): checks a condition and branches into true / false
9. Apply Policy Routing (Code): runs custom JavaScript code
10. Route to Selected Model (Switch): routes items into 4 branches

…plus 28 more steps. See the full node list below.

Services it uses

PostgresSlack

Before you upgrade to n8n 3.0

Nodes used (11)

• Webhookn8n-nodes-base.webhook
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• HTTP Requestn8n-nodes-base.httpRequest
• Mergen8n-nodes-base.merge
• Ifn8n-nodes-base.if
• Switchn8n-nodes-base.switch
• Waitn8n-nodes-base.wait
• Postgresn8n-nodes-base.postgres
• Slackn8n-nodes-base.slack
• Send Emailn8n-nodes-base.emailSend

From the author

How It Works This workflow automates end-to-end research analysis by coordinating multiple AI models—including NVIDIA NIM (Llama), OpenAI GPT-4, and Claude to analyze uploaded documents, extract insights, and generate polished reports delivered via email.…

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