Generate due diligence reports with LlamaIndex, Pinecone, and GPT-5-mini

Screen deals in minutes, not days. This n8n workflow parses financial documents with LlamaIndex, embeds them into Pinecone, and generates comprehensive AI-driven reports with GPT-5-mini. Consistent, data-backed insights without the manual review grind. Last updated: September 2026. Why Use This Workflow? Time Savings: Manual document review and report generation drop from days to minutes. Cost Reduction: Far less reliance on expensive human analysts for initial extraction and summaries. Error Prevention: AI-driven analysis extracts consistently, reducing human error and oversight. Scalability: Multiple documents and deals processed in parallel, scaling with your business. Ideal For - Investment Analysts & Private Equity Firms: Evaluate targets fast by automating extraction of financials, risks, and business models from deal documents. - M&A Advisors: Preliminary due diligence with comprehensive overviews, minus the manual effort. - Financial Professionals: Accelerate research on filings, presentations, and market reports for critical decisions. How It Works 1. Trigger: A webhook receives multiple due diligence documents (PDFs, DOCX, XLSX) along with associated metadata. 2. Document Processing & Cache Check: Files are split individually. The workflow first checks Pinecone to see if the deal's documents have been processed before (cache hit). If so, it skips parsing and embedding. 3. Data Extraction (LlamaIndex): For new deals, each document is sent to LlamaIndex for advanced parsing, extracting structured text content. 4. Vectorization & Storage: The parsed text is then converted into numerical vector embeddings using OpenAI and stored in Pinecone, our vector database, with relevant metadata. 5. AI-Powered Analysis (Langchain Agent): An n8n Langchain Agent, acting as a "Senior Investment Analyst," leverages GPT-5-mini to query Pinecone multiple times for specific information (e.g., company profile, financials, risks, business model). It synthesizes these findings into a structured JSON output. 6. Report Generation: The structured AI output is transformed into an HTML report, then converted into a professional PDF document. 7. Secure Storage & Delivery: The final PDF due diligence report is uploaded to an S3 bucket, and a public URL is returned via the initial webhook, providing instant access. Setup Guide Prerequisites | Requirement | Type | Purpose | | :---------- | :--- | :------ | | n8n instance | Essential | Workflow execution platform | | LlamaIndex API Key | Essential | For robust document parsing and text extraction | | OpenAI API Key | Essential | For creating text embeddings and powering the GPT-5-mini AI agent | | Pinecone API Key | Essential | For storing and retrieving vector embeddings | | AWS S3 Account | Essential | For secure storage of generated PDF reports (docs) | Installation Steps 1. Import the JSON file to your n8n instance. 2. Configure credentials: - LlamaIndex: Create an "HTTP Header Auth" credential with x-api-key in the header and your LlamaIndex API key as the value. - OpenAI: Create an "OpenAI API" credential with your OpenAI API key. Ensure the credential name is "Sumopod" or update the workflow nodes accordingly. - Pinecone: Create a "Pinecone API" credential with your Pinecone API key and environment. Ensure the credential name is "w3khmuhtadin" or update the workflow nodes accordingly. - AWS S3: Create an "AWS S3" credential with your Access Key ID and Secret Access Key. 3. Update environment-specific values: - In the "Upload to S3" node, ensure the bucketName is set to your desired S3 bucket. - In the "Create Public URL" node, update the baseUrl variable to match your S3 bucket's public access URL or CDN if applicable (e.g., https://your-s3-bucket-name.s3.amazonaws.com). 4. Customize settings: - Review the prompt in the "Analyze" (Langchain Agent) node to adjust the AI's persona or required queries if needed. 5. Test execution: - Send sample documents (PDF, DOCX, XLSX) to the webhook URL (/webh