ES | EN
AI

Ask questions about a PDF using AI

Google DriveChain Retrieval QaDocument Binary Input LoaderEmbeddings Open Ai
Nodes 9
Complexity Advanced
Category AI
n8n popularity 118,063 views in n8n library

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.

Apps and nodes included

Step-by-Step Implementation Guide

Preguntas sobre PDF con IA

Este workflow permite hacer preguntas sobre el contenido de un documento PDF utilizando IA y Pinecone.

Nodos utilizados

  • Google Drive: Para cargar el PDF.
  • Chain Retrieval QA (Langchain): Para la lógica de la pregunta y respuesta.
  • Document Binary Input Loader (Langchain): Para cargar el PDF.
  • Embeddings OpenAI (Langchain): Para crear vectores.
  • LLM Chat OpenAI (Langchain): Para generar respuestas.
  • Retriever Vector Store (Langchain): Para buscar en Pinecone.
  • Text Splitter Recursive Character Text Splitter (Langchain): Para dividir el texto.
  • Vector Store Pinecone Insert (Langchain): Para insertar vectores en Pinecone.
  • Vector Store Pinecone Load (Langchain): Para cargar vectores desde Pinecone.

Pasos de configuración

  • Paso 1: Configura el nodo Google Drive para acceder al PDF.
  • Paso 2: Configura los nodos de Langchain (Chain Retrieval QA, Document Binary Input Loader, Embeddings OpenAI, LLM Chat OpenAI, Retriever Vector Store, Text Splitter Recursive Character Text Splitter, Vector Store Pinecone Insert, Vector Store Pinecone Load) con tus claves de API, credenciales de Pinecone y preferencias.
  • Paso 3: Ingresa la pregunta.
⚡ Open and edit in Scriflow ← Browse all n8n templates

Scriflow builds and adapts n8n workflows with AI. Open this template in the editor to get the import-ready JSON.