GPT-4 & LangChain - Create a ChatGPT Chatbot for Your PDF Files

Use the new GPT-4 api to build a chatGPT chatbot for multiple Large PDF files.

Tech stack used includes LangChain, Pinecone, Typescript, Openai, and Next.js. LangChain is a framework that makes it easier to build scalable AI/LLM apps and chatbots. Pinecone is a vectorstore for storing embeddings and your PDF in text to later retrieve similar docs.

Tutorial video

Join the discord if you have questions

The visual guide of this repo and tutorial is in the visual guide folder.

If you run into errors, please review the troubleshooting section further down this page.

Prelude: Please make sure you have already downloaded node on your system and the version is 18 or greater.

Development

1. Clone the repo or download the ZIP

git clone [github https url]

2. Set up your .env file

• Copy .env.example into .env Your .env file should look like this:

OPENAI_API_KEY=
PINECONE_API_KEY=
PINECONE_ENVIRONMENT=
PINECONE_INDEX_NAME=
PINECONE_NAME_SPACE=

3. DMake sure you have these two things setup.

• Check that you've set the vector dimensions to 1536.

• Make sure your pinecone namespace is in lowercase.

• Index name is the one you supplied, not the long url link as I wrongly assumed and got weird PDF errors. (This is what prompted the addition of the python pdf uploads)

• Visit openai to retrieve API keys and insert into your .env file.

• Visit pinecone to create and retrieve your API keys, and also retrieve your environment and index name from the dashboard.

3. Build the app.

docker compose build app

4. In utils/makechain.ts chain change the QA_PROMPT for your own usecase. Change modelName in new OpenAI to gpt-3.5, if you don't have access to gpt-4 api.

Convert your PDF files to embeddings

This repo can load multiple PDF files

1. Inside docs folder, add your pdf files or folders that contain pdf files.

2. Run the script docker compose run app npm run ingest to 'ingest' and embed your docs. If you run into errors troubleshoot below.

3. Check Pinecone dashboard to verify your namespace and vectors have been added.

Run the app

Once you've verified that the embeddings and content have been successfully added to your Pinecone, you can run the app docker compose up app to launch the local dev environment, and then type a question in the chat interface.

Troubleshooting

In general, keep an eye out in the issues and discussions section of the cloned repo for solutions. https://github.com/mayooear/gpt4-pdf-chatbot-langchain

General errors

• Make sure you're running the latest Node version. Run node -v
• Try a different PDF or convert your PDF to text first. It's possible your PDF is corrupted, scanned, or requires OCR to convert to text.
• Console.log the env variables and make sure they are exposed.
• Make sure you're using the same versions of LangChain and Pinecone as this repo.
• Check that you've created an .env file that contains your valid (and working) API keys, environment and index name.
• If you change modelName in OpenAI, make sure you have access to the api for the appropriate model.
• Make sure you have enough OpenAI credits and a valid card on your billings account.
• Check that you don't have multiple OPENAPI keys in your global environment. If you do, the local env file from the project will be overwritten by systems env variable.
• Try to hard code your API keys into the process.env variables if there are still issues.

Pinecone errors

• Make sure your pinecone dashboard environment and index matches the one in the pinecone.ts and .env files.
• Check that you've set the vector dimensions to 1536.
• Make sure your pinecone namespace is in lowercase.
• Pinecone indexes of users on the Starter(free) plan are deleted after 7 days of inactivity. To prevent this, send an API request to Pinecone to reset the counter before 7 days.
• Retry from scratch with a new Pinecone project, index, and cloned repo.

Credit

Frontend of this repo is inspired by langchain-chat-nextjs