RAG Workflow for Stock Earnings Report Analysis
detail.loadingPreview
Analyze stock earnings reports using Retrieval Augmented Generation (RAG). This workflow leverages Pinecone for vector storage and Google Gemini for embeddings and chat, enabling detailed trend and outlier analysis from financial documents.
🚀Ready to Deploy This Workflow?
About This Workflow
Overview
This n8n workflow implements a Retrieval Augmented Generation (RAG) system to analyze stock earnings reports. It automates the process of ingesting PDF earnings reports, embedding them using Google Gemini, and storing them in a Pinecone vector database. When a query is made, the workflow retrieves relevant information from the vector store and uses an AI agent (specifically, the n8n AI Agent node) to synthesize this information and provide a detailed analysis, including trends and outliers. The final report can be saved to Google Docs. This approach allows for sophisticated analysis of financial data without requiring the LLM to have prior knowledge of specific reports, improving accuracy and relevance.
Key Features
- Ingests PDF financial reports using a
Default Data Loader. - Splits documents into manageable chunks using
Recursive Character Text Splitter. - Generates embeddings with
Embeddings Google Gemini. - Stores and retrieves data from
Pinecone Vector Store. - Utilizes an
AI Agentnode to process queries and generate reports. - Integrates with
Google Docsto save the analyzed reports.
How To Use
- Set up Credentials: Ensure you have configured your Pinecone API and Google Gemini API credentials within n8n.
- Configure Pinecone: Set up your Pinecone index named 'company-earnings' and ensure your API key is correctly entered.
- Load Earnings Reports: Place your PDF earnings reports in a location accessible by the
Default Data Loadernode. Configure the node to usepdfLoader. - Split and Embed: The
Recursive Character Text Splitterwill process the loaded documents, andEmbeddings Google Geminiwill generate vector embeddings. - Index Data: The
Pinecone Vector Storenode will insert these embeddings into your Pinecone index. - Query and Analyze: Use the
AI Agentnode. Enter your specific query (e.g., 'Give me a report on Google's last 3 quarter earnings. Format it in markdown. Focus on the differences and trends. Spot any outliers.'). The agent will use the tools (Vector Store and Google Docs) to retrieve information and generate a report. - Save Report: The
Save Report to Google Docsnode is configured to update a specific Google Doc. Ensure the document ID and credentials are correct if you wish to save the output.
Apps Used
Workflow JSON
{
"id": "81248077-9cbe-4c2b-8e18-0fb86a0bf791",
"name": "RAG Workflow for Stock Earnings Report Analysis",
"nodes": 0,
"category": "AI & LLMs",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 81248077-9cbe...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Verification Info
Related Workflows
Discover more workflows you might like
Build a Voice RAG Chatbot with ElevenLabs and OpenAI
Create an interactive voice-enabled RAG chatbot using ElevenLabs for speech synthesis and OpenAI for AI agent capabilities. This workflow integrates with Qdrant Vector Store and Google Drive for knowledge retrieval, enabling intelligent responses to user queries.
AI Chatbot for Health Insurance Lead Qualification and Data Enrichment
This n8n workflow creates an AI-powered chatbot that captures lead data, enriches it, and queries databases for health insurance product recommendations. It utilizes the Chat Trigger, OpenAI, and various tool nodes for comprehensive lead management.
AI-Powered Conversational Agent with Tools
This n8n workflow creates an AI conversational agent that leverages multiple tools, including Wikipedia and a weather API, to answer complex user queries. It utilizes a buffer memory to maintain conversation context.