LLM Chain Query Processing and Response Chat Interface

This workflow automates text summarization and quality evaluation, replacing manual review and comparison that takes 20-40 minutes per document for content teams. The Manual Trigger node starts processing, the Input Validation Set node prepares text, the Validate Input Text If node checks length, the Set Baseline Set node loads reference summary, the Set Article Code node sets document, the Summary Simple Map LangChain node generates summary with OpenAI GPT-3.5-turbo, the Check Summary Success If node verifies output, the Evaluate to Baseline LangChain Code node scores against baseline using criteria like helpfulness, and Format Success Response Set node outputs metrics. Error paths (Format Validation/Summary Error Set nodes) handle failures. It aids editors in small media firms (10-30 staff) evaluating 50+ summaries weekly, ensuring consistent quality without bias, streamlining QA for blogs or reports and improving content standards.\n\nThis workflow saves 3-5 hours weekly on 50 summaries, boosting accuracy by 80%. Use cases include article QA for newsrooms, RAG validation for AI tools in agencies. Suitable for small teams. Requires OpenAI ($0.03/1k tokens); n8n (free self-hosted or $20/month cloud). Scalable to 200 summaries/day with paid tiers.\n\nInstall n8n via n8n.io or cloud.n8n.io. Get OpenAI API key at platform.openai.com (enable billing). Set OPENAI_API_KEY env var. Import JSON; manual trigger—no webhook. Update Set Baseline Set with custom reference. Configure OpenAI Chat Model with 'gpt-3.5-turbo-0125'.\n\nTest manually: Set input_text to article excerpt. Verify summary and score. Errors: Short text (400), invalid key (500—regenerate). Activate workflow. Monitor dashboard weekly. Optimize chunk size; refresh key quarterly.", "businessValue": "Saves 3-5 hours/week evaluating 50 text summaries", "setupTime": "15-25 minutes", "difficulty": "Beginner", "requirements": ["OpenAI API ($0.03/1k tokens)", "API key access", "n8n instance"], "useCase": "Automated summarization QA for content teams"