Generate due diligence reports with LlamaIndex, Pinecone, and GPT-5-mini
UnknownWhat this workflow does
This AI workflow has 31 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Pinecone Vector Store, Embeddings OpenAI, OpenAI Chat Model and S3 and 1 more. It also calls api.cloud.llamaindex.ai over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Split Uploaded Files + Build Deal ID (Code): runs custom JavaScript code
- Get Pinecone Index Stats (HTTP Request): calls an HTTP API (POST)
- Check Deal Namespace Cache (Code): runs custom JavaScript code
- Cache Hit? (If): checks a condition and branches into true / false
- Prepare Analysis Context (Code): runs custom JavaScript code
- Iterate Files for Parsing (Loop Over Items (Split in Batches)): loops over the items in batches
- Run Due Diligence AI Analysis (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Retrieve Context from Pinecone); output parser: Parse Structured Analysis JSON
- Collect Ingested Deal IDs (Aggregate): combines items into one
- Upload File to LlamaParse (HTTP Request): calls api.cloud.llamaindex.ai (POST)
- Map Analysis to Report Fields (Code): runs custom JavaScript code
…plus 14 more steps. See the full node list below.
Services it uses
HTTP calls to: api.cloud.llamaindex.ai
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-puppeteer is verified or supports 3.0 (used in Render PDF from HTML).
Nodes used (19)
- HTTP Request
n8n-nodes-base.httpRequest - Webhook
n8n-nodes-base.webhook - Code
n8n-nodes-base.code - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Aggregate
n8n-nodes-base.aggregate - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - HTML
n8n-nodes-base.html - Puppeteer
n8n-nodes-puppeteer.puppeteer - Convert to File
n8n-nodes-base.convertToFile - S3
n8n-nodes-base.s3 - Merge
n8n-nodes-base.merge - If
n8n-nodes-base.if - Wait
n8n-nodes-base.wait - Respond to Webhook
n8n-nodes-base.respondToWebhook
From the author
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…