Keyflow
Contact

Search Keyflow

Find a shortcut, workflow, MCP server or skill

Ask questions about a PDF using AI

n8n template #1960

Summary

Use template
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.

How to set it up

  1. Open template #1960 on n8n.io and click Use for free, or copy the template JSON and paste it onto an empty canvas in n8n.
  2. Create 6 credentials under Credentials → Add credential: Google Drive, Binary Input Loader, Embeddings OpenAI, OpenAI Chat Model, Pinecone: Insert, Pinecone: Load. Then open each of those nodes and pick the credential.
  3. Check the model in the OpenAI Chat Model node. The template may point at a model your account can't use; swap it for one you have access to.
  4. Click Execute workflow and step through each node's output to confirm the data looks right.
  5. Toggle the workflow to Active so its trigger runs on its own.

Hand off to your agent

Prompt

Help me set up the n8n workflow "Ask questions about a PDF using AI" (https://n8n.io/workflows/1960). It uses: Google Drive, Question and Answer Chain, Binary Input Loader, Embeddings OpenAI, OpenAI Chat Model, Vector Store Retriever, Recursive Character Text Splitter, Pinecone: Insert, Pinecone: Load. Import the template JSON into my n8n instance, list every credential I need to create, and walk me through testing it.

Paste into Claude Code and it will do the rest.

Apps and nodes

Google DriveQuestion and Answer ChainBinary Input LoaderEmbeddings OpenAIOpenAI Chat ModelVector Store RetrieverRecursive Character Text SplitterPinecone: InsertPinecone: Load

Questions

Yes. David Roberts published it free on n8n.io as a verified creator, and it has 118K views. It runs on n8n Cloud or a self-hosted n8n instance.

Google Drive, Binary Input Loader, Embeddings OpenAI, OpenAI Chat Model, Pinecone: Insert, Pinecone: Load. The other 3 nodes are built into n8n.

Similar workflows

NameViews
  1. AI Crew to Automate Fundamental Stock Analysis - Q&A Workflow28K
  2. Supabase Insertion & Upsertion & Retrieval24K
  3. Advanced AI Demo (Presented at AI Developers #14 meetup)24K
  4. Chat with PDF docs using AI (quoting sources)95K
  5. Automate sales cold calling pipeline with Apify, gpt-5.6-terra, and WhatsApp34K
  6. Build a PDF Document RAG System with Mistral OCR, Qdrant and Gemini AI20K
  7. Telegram chat with PDF16K
  8. Upsert huge documents in a vector store with Supabase and Notion12K