Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/geremyjampiersalasgarcia-eng/Caso_Practico_Semillero_IA/llms.txt

Use this file to discover all available pages before exploring further.

Mesa de Ayuda IA is an intelligent help desk built for the sales team of Patito S.A. It uses a multi-agent architecture orchestrated by LangGraph — five specialized agents handle product catalog queries, commercial policy lookups, sales process guidance, multimodal image analysis, and CRM opportunity registration, all powered by Google Gemini and a RAG pipeline backed by ChromaDB.

Quickstart

Get the backend and frontend running locally in under 10 minutes.

Architecture

Understand the multi-agent StateGraph, RAG pipeline, and security layers.

Agents

Explore all five specialized agents and how they are routed.

API Reference

Full REST API reference with request/response schemas and examples.

How It Works

A sales rep sends a question (or uploads a product image) through the Next.js chat UI. The FastAPI backend passes it to the LangGraph orchestrator, which:
1

Classifies the intent

Gemini (temperature 0) determines whether the query is about catalog pricing, commercial policies, the sales process, image analysis, a CRM registration action, or a mixed query.
2

Routes to the right agent(s)

The LangGraph StateGraph dispatches to one or more specialized agents. Mixed-intent queries fan out to three agents simultaneously.
3

Retrieves relevant context

Each agent searches its dedicated ChromaDB collection using semantic similarity (top-k=4 chunks) with Gemini embeddings.
4

Generates a grounded response

The agent builds a prompt from its system instructions plus the retrieved context, invokes Gemini, and returns a cited answer. For multi-agent responses, a consolidator merges the partial answers.

Key Features

5 Specialized Agents

Catalog, Policies, Sales Process, Multimodal Vision, and CRM Action Registration agents — each with its own knowledge base.

RAG with ChromaDB

Three isolated ChromaDB collections with Google Gemini embeddings provide accurate, document-grounded answers.

Prompt Injection Security

Four security layers: input validation, prompt hardening, server-side sandboxing, and output validation.

Observability

Arize Phoenix traces every LangGraph span via OpenTelemetry OTLP. Token cost tracking per intent category.

LLM-as-Judge Evaluation

Offline batch evaluator scores responses on relevance, precision, and completeness using a Pydantic rubric.

Multimodal Vision

Upload a product image and the Gemini Vision agent identifies it, retrieves catalog data, and returns pricing.

Stack

LayerTechnology
Backend frameworkFastAPI + Uvicorn
AI orchestrationLangGraph (StateGraph)
LLM & embeddingsGoogle Gemini (gemini-flash-lite-latest, gemini-embedding-001)
Agent frameworkLangChain
Vector storeChromaDB (local persistence)
DatabasePostgreSQL (SQLite fallback)
FrontendNext.js 14 + TypeScript + Tailwind CSS
ObservabilityArize Phoenix + OpenTelemetry
This project was built for the Semillero de Inteligencia Artificial program by Geremy Jampier Salas Garcia. It is designed as a production-quality reference architecture for multi-agent RAG systems.

Build docs developers (and LLMs) love