Chat with your PDFs in seconds. Powered by Together AI and Pinecone.
Tech Stack · Deploy Your Own · Common Errors · Credits · Future Tasks
- Next.js App Router for the framework
- Mixtral through Together AI inference for the LLM
- M2 Bert 80M through Together AI for embeddings
- Langchain.js for the RAG code
- Pinecone for the vector database
- Bytescale for the PDF storage
- Vercel for hosting and for the postgres DB
- Clerk for user authentication
- Tailwind CSS for styling
You can deploy this template to Vercel or any other host. Note that you'll need to:
- Set up Together.ai
- Set up Pinecone
- Set up Bytescale
- Set up Clerk
- Set up Vercel
See the .example.env for a list of all the required environment variables.
- Check that you've created an
.envfile that contains your valid (and working) API keys, environment and index name. - Check that you've set the vector dimensions to
768and thatindexmatched your specified field in the.env variable. - Check that you've added a credit card on Together AI if you're hitting rate limiting issues due to the free tier
- Youssef for the design of the app
- Mako for the original RAG repo and inspiration
- Joseph for the langchain help
- Together AI, Bytescale, Pinecone, and Clerk for sponsoring
These are some future tasks that I have planned. Contributions are welcome!
- Add a trash icon for folks to delete PDFs from the dashboard and implement delete functionality
- Add footer to the dashboard page with a support email so folks can contact me with questions
- Research best practices for chunking and retrieval and play around with them – ideally run benchmarks
- Try out Langsmith for more observability into how the RAG app runs
- Explore best practices for auto scrolling based on other chat apps like chatGPT
- Do some prompt engineering for Mixtral to make replies as good as possible
- Change the header at the top with something more similar to roomGPT to make it cleaner
- Configure emails on Clerk if I want to eventually add this
- Add demo video to the homepage to demonstrate functionality more easily
- Upgrade to Next.js 14 and fix any issues with that
- Implement sources like perplexity to be clickable with more info
- Add analytics to track the number of chats & errors with Vercel Analytics events
- Make some changes to the default tailwind
proseto decrease padding - Add an initial message with sample questions or just add them as bubbles on the page
- Protect API routes by making sure users are signed in before executing chats
- Add an option to get answers as markdown or in regular paragraphs
- Implement something like SWR to automatically revalidate data
- Save chats for each user to get back to later in the postgres DB
- Clean up and customize how the PDF viewer looks to be very minimal
- Bring up a message to direct folks to compress PDFs if they're beyond 10MB
- Migrate to the latest bytescale library and use a self-designed custom uploader
- Use a session tracking tool to better understand how folks are using the site
- Add better error handling overall with appropriate toasts when actions fail
- Add support for images in PDFs with something like Nougat
- Add rate limiting for uploads to only allow up to 5-10 uploads a day using upstash redis