NEOPOLIS AKADEMY
RAG agent to analyze companies' financial results
Advanced lab for financial analysts: build a RAG agent to analyze corporate financial results. Uses n8n to orchestrate GPT/Gemini, Pinecone for vector storage and Google Docs for outputs, with fictional datasets and human validation.
View this course on Akademy ↗Enrolment and practical details are available on Neopolis Akademy.
What you will explore
Designed for financial and BI analysts, this lab covers setting up a Retrieval-Augmented Generation (RAG) agent for analyzing financial reports.
Architecture: document ingestion, vector indexing in Pinecone, querying with GPT/Gemini orchestrated by n8n, and output into Google Docs.
Works on fictional datasets with control measures and human validation steps to ensure interpretation quality.
STEP BY STEP
Course programme
01RAG agent to analyze companies' financial results
Practical session to build a RAG agent for analyzing company financial results: integrate sources, vectorize with Pinecone, orchestrate in n8n and synthesize findings with GPT/Gemini into Google Docs. Covers environment prep, stepwise assembly and security checks.
Objective: create a RAG agent to ingest financial documents, index them and produce consolidated analyses.
Prepare Pinecone, model access (GPT/Gemini), n8n and Google Docs for textual output.
Progressively build pipelines: extraction, embeddings, contextual retrieval and model querying.
Security checkpoint: verify controls on access to sensitive data and API calls.
Explore this module on Akademy ↗Programme source: Neopolis Akademy. Original course page