pdf-chat-ai-sdk - GitLite

KO | EN

gitlite — search

#javascript #ai #typescript #go #deep-learning #linux #docker #nodejs #macos #java #windows #awesome #security #mcp

pdf-chat-ai-sdk

(★ 166)

An AI powered Next.js app to chat with your PDF files and get a streamed response using Vercel's AI SDK, Langchain and PineconeDB ✨🤖💻🗃️

파일 탐색기

최종 버전 다운로드 (.zip)

- german-basic-law.pdf
- next.svg
- vercel.svg
- - favicon.ico
  - globals.css
  - layout.tsx
  - page.tsx
- - chat-line.tsx
  - chat.tsx
  - dark-mode-toggle.tsx
  - theme-provider.tsx
- - config.ts
  - langchain.ts
  - llm.ts
  - pdf-loader.ts
  - pinecone-client.ts
  - prompt-templates.ts
  - utils.ts
  - vector-store.ts
- - pinecone-prepare-docs.ts
- - index.ts
.env.example
.eslintrc.json
.gitignore
components.json
LICENSE
next.config.js
package-lock.json
package.json
postcss.config.cjs
README.md
tailwind.config.cjs
tsconfig.json

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/rajeshdavidbabu/pdf-chat-ai-sdk

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd pdf-chat-ai-sdk

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Node.js

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Node.js npm 명령어를 쓰려면 Node.js가 설치되어 있어야 합니다. LTS(장기지원) 버전을 추천합니다.

npm install

package.json에 명시된 라이브러리들을 내려받아 설치합니다.

npm start

개발/실행 서버를 켭니다.

✅ 명령어 실행 후 터미널에 나타나는 주소(보통 http://localhost:3000 형태)를 브라우저에서 열어보세요.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# PDF-CHAT AI ✨🤖💻🗃️

An AI-powered PDF chat built with Next.js 13, Vercel's AI SDK, Langchain, and PineconeDB

## 👷🏾‍♂️ Want to Learn How to Build It?
Check out the tutorial on my YT [channel](https://www.youtube.com/watch?v=oiCFr19NtPo&t)

## Demo

https://github.com/rajeshdavidbabu/pdf-chat-ai-sdk/assets/15684795/0b2a1c85-c58d-43a0-b362-80bdf5a5d7ee

## Architecture

<img width="1402" alt="Embed LLM" src="https://github.com/rajeshdavidbabu/pdf-chat-ai-sdk/assets/15684795/b1252438-f5b3-4df3-aecc-245553006a60">

## 👩‍🚀 Description

Built with:
- ✅ Next.js 13
- ✅ Vercel's AI SDK
- ✅ Shadcn-ui
- ✅ Langchain TypeScript integration
- ✅ PineconeDB as the knowledge store
- ✅ Dark Mode with persistent theme-switching

## 🗃️ Pre-requisites
- Create a free account and get an OPEN_AI key from platform.openai.com
- Create a free account and get access to PineconeDB
- And populate your `.env` file with the required information.

## 💬 Good to know
- The PineconeDB index creation happens when we run `npm run prepare:data`, but its better to create it manually if you dont want the command to fail.
- If the command fails, then give sometime for pinecone index to get initialized and try to run the command again, it should work eventually.

## 🧞 Commands

All commands are run from the root of the project, from a terminal:

| Command               | Action                                          |
| :-------------------- | :-----------------------------------------------|
| `npm install`         | Installs dependencies                           |
| `npm run prepare:data`| Splits your PDF file under the /docs folder into chunks, embeds them, uploads them to Pinecone|
| `npm run dev`         | Starts the local dev server at `localhost:3000` |

## 🚸 Roadmap
- ✅ Add sources to the streamed chat bubble
- 🚧 Clean up and show proper error messages
- 🚧 Sanitize input and output source documents

## 👏🏽 Contributing

Pull requests are welcome, before creating a PR talk to me on [discord](https://discord.com/channels/1121796870231040020/1156553471881908275). For major changes, please open an issue first
to discuss what you would like to change.