Chat with PDF docs using AI (quoting sources)
Embeddings OpenAI
Google Drive
OpenAI Chat Model
Pinecone Vector Store
Recursive Character Text Splitter
Structured Output ParserThis workflow allows you to ask questions about a PDF document. The answers are provided by an AI model of your choice, and the answer includes a citation pointing to the information it used. You can use n8n’s built-in chat interface to ask the questions, or you could customise this workflow to use another one (e.g. Slack, Teams, etc.) Example The workflow is set up with the Bitcoin whitepaper. So you could ask things like: Question: “Which email provider does the creator of Bitcoin use?“ Answer: “GMX [Bitcoin whitepaper.pdf, lines 1-35]” Requirements A Pinecone account (they have a free tier at the time of writing that is easily enough for this workflow) Access to a large language model (e.g. an OpenAI account) Customizing this workflow The workflow only reads in one document, but you could customise it to read in all the documents in a folder (or more). The workflow is set up to use GPT 3.5, but you could swap that out for any other model (including self-hosted ones).
Tags
Embeddings OpenAIGoogle DriveOpenAI Chat ModelRelated workflows
See all AI Automation→Run AI employee onboarding with Groq, Google Workspace, and Gemini
Quick overview This workflow ingests onboarding documents from Google Drive into an in-memory vector store with Google Gemini embeddings, then runs a multi-channel onboarding chatbot powered by Groq, sends role-based welcome emails via Gmail when a new hire appears in Google Sheets, and schedules day 1/7/30 check-in emails. How it works Manually runs an ingestion flow that lists files in a specified Google Drive folder, downloads them, extracts text, and indexes them into an in-memory vector store using Google Gemini embeddings. Receives employee questions via n8n Chat (and optionally Slack or Telegram), normalizes the message into a single format, and rejects empty or overly long inputs. Uses a Groq LLM agent with per-user session memory to retrieve relevant excerpts from the in-memory company_docs knowledge base and generate a grounded answer, or directs the user to HR when no relevant content is found. Routes the assistant’s response back to the originating channel (n8n Chat, and optionally Slack or Telegram). Triggers every minute on updates to a Google Sheets “Hires” sheet, validates rows marked as Hired, and skips hires already present in the “Tracking” sheet. Builds a depart
Ask questions about a PDF using AI
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.
AI: Summarize podcast episode and enhance using Wikipedia
The workflow automates the process of creating a summarized and enriched podcast digest, which is then sent via email. Note that to use this template, you need to be on n8n version 1.19.4 or later.