https://github.com/engageintellect/nexum-search
Turns data into vectors, stores it on Pinecone DB, then allows users to ask contextual questions about the data using semantic search.
https://github.com/engageintellect/nexum-search
Last synced: 10 months ago
JSON representation
Turns data into vectors, stores it on Pinecone DB, then allows users to ask contextual questions about the data using semantic search.
- Host: GitHub
- URL: https://github.com/engageintellect/nexum-search
- Owner: engageintellect
- Created: 2023-06-20T04:23:51.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2024-02-16T06:21:11.000Z (over 2 years ago)
- Last Synced: 2025-07-06T06:44:43.206Z (11 months ago)
- Language: TypeScript
- Homepage: https://nexum-search.vercel.app
- Size: 3.96 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Langchain, Pinecone, and GPT with Next.js
## Technologies Used
- Next.js
- LangchainJS
- Pineceone Vector Database
- GPT3
## Getting Started
### Prerequisites
To run this app, you need the following:
1. An [OpenAI](https://platform.openai.com/) API key
2. [Pinecone](https://app.pinecone.io/) API Key
### Up and running
To run the app locally, follow these steps:
1. Clone this repo
```sh
git clone https://github.com/engageintellect/pinecone-gpt.git
```
2. Change into the directory and install the dependencies using either NPM, PNPM or Yarn
3. Copy `.example.env.local` to a new file called `.env.local` and update with your API keys and environment.
**Be sure your environment is an actual environment given to you by Pinecone, like `us-west4-gcp-free`**
4. (Optional) - Add your own custom text or markdown files into the `/documents` folder.
5. Run the app:
```sh
pnpm run dev
```