mayooear/ai-pdf-chatbot-langchain

★ 16,503TypeScriptAudience · developerComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((repo))
    What it does
      PDF chatbot template
      RAG pattern reference
      Book companion code
    How it works
      PDF ingestion graph
      Vector embeddings
      Retrieval graph
      Streaming responses
    Tech stack
      TypeScript and Next.js
      LangChain and LangGraph
      Supabase vectors
    Use cases
      Document Q-and-A app
      LangGraph learning
      RAG starter project
    Audience
      Developers
      AI builders

mindmap root((repo)) What it does PDF chatbot template RAG pattern reference Book companion code How it works PDF ingestion graph Vector embeddings Retrieval graph Streaming responses Tech stack TypeScript and Next.js LangChain and LangGraph Supabase vectors Use cases Document Q-and-A app LangGraph learning RAG starter project Audience Developers AI builders

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Clone the template to bootstrap a PDF question-answering chatbot for your own documents in a weekend.

USE CASE 2

Study the LangGraph retrieval-augmented generation pattern as a reference for building your own document-aware AI app.

USE CASE 3

Follow along with the O'Reilly book Learning LangChain using this repo as the working code example.

Tech stack

TypeScriptNext.jsReactNode.jsLangChainLangGraphSupabaseTurborepo

Getting it running

Difficulty · moderate Time to first run · 1h+

Requires a Supabase project for vector storage and an OpenAI API key, the repository is not actively maintained and is kept as a reference.

License information is not mentioned in the explanation.

In plain English

This project is a customizable template for building an AI chatbot that lets users upload PDF documents and then ask questions about them in plain English, with the AI's answers grounded in the contents of those PDFs. The maintainer notes the repository is not actively maintained and is kept as a reference, it also serves as the accompanying example for the book Learning LangChain (O'Reilly). The way it works follows a common pattern called retrieval-augmented generation. When a user uploads a PDF the backend runs an ingestion graph that parses the document, splits it up and turns each piece into a numeric fingerprint called a vector embedding, those embeddings are stored in a vector database (Supabase in this example) so that text passages can later be looked up by meaning rather than by exact keyword. When the user asks a question, a separate retrieval graph decides whether it needs to pull relevant passages out of the database or answer directly, calls a large language model such as OpenAI's to compose a reply, and streams the response back to the user interface in real time with references to the source passages. LangChain and LangGraph are the orchestration libraries that wire these steps together as a state machine, and LangSmith can optionally be plugged in for tracing and debugging. Someone would clone this template to bootstrap their own document-Q&A app, learn how a LangGraph-based agent is structured, or follow along with the book. The stack is a TypeScript monorepo managed with Turborepo, with a Next.js and React frontend and a Node.js backend that runs the LangGraph server locally on port 2024. The full README is longer than what was provided here.

Copy-paste prompts

Prompt 1

I cloned mayooear/ai-pdf-chatbot-langchain. Walk me through the setup steps, what environment variables do I need, how do I run the ingestion script to load a PDF, and how do I start the chat UI?

Prompt 2

Explain how the retrieval-augmented generation flow in this repo works, from PDF upload through vector embedding to streaming the AI answer back to the browser.

Prompt 3

I want to swap Supabase for a different vector store in this LangGraph chatbot. Show me where the vector store is configured and what I would change to use Pinecone instead.

Prompt 4

The chatbot retrieves wrong passages. How does the retrieval graph in this repo decide which chunks to pull, and how can I tune the similarity threshold to get better results?

Open on GitHub → Explain another repo

← mayooear on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.