https://github.com/jnlandu/nextjs-chatbot

https://github.com/jnlandu/nextjs-chatbot

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/jnlandu/nextjs-chatbot
• Owner: jnlandu
• Created: 2024-11-17T20:30:03.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-11-17T20:35:37.000Z (about 1 month ago)
• Last Synced: 2024-11-17T21:29:21.359Z (about 1 month ago)
• Language: Python
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# A Chatbot build with NextJs, Groq, FASTApi, Astra DB, Langchain and Huggingface.

## Getting Started with Vercel

1. [Create or sign in](https://astra.datastax.com/register) to your Astra DB account.

2. Create a vector database. Store the database id, region and namespace, and token for later.

3. [Create or sign in](https://groq.com/) to your OpenAI account. Create an API Key and Store your Groq API key for later.

4. Click to deploy the app to Vercel: [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/datastax/astra-db-chatbot-starter&env=ASTRA_DB_NAMESPACE,OPENAI_API_KEY,ASTRA_DB_ID,ASTRA_DB_REGION,ASTRA_DB_APPLICATION_TOKEN).

  

   Set your environment variables to the values created in steps 1 and 3.

##

Set python virtual environment on linux

   apt-get install python3.11-venv

   python3 -m venv venv

   source venv/bin/activate

   clone repository and install all requirements.txt

## Setting up your database and seeding with data

1. Navigate to your IDE, set up the following environment variables:

- ASTRA_DB_APPLICATION_TOKEN=Generate app token for Astra database

- ASTRA_DB_NAMESPACE=existing Astra DB namespace in vector database

- ASTRA_DB_API_ENDPOINT="https://ASTRA_DB_ID-ASTRA_REGION.apps.astra.datastax.com"

- ASTRA_DB_COLLECTION=Name of collection/table to be created in Astra database

- VECTOR_DIMENSION=Collection to be created with number of vector dimensions

- SCRAPED_FILE=Scraped data file location

- GROQ_API_KEY=api key for GROQ API KEY

- VECTOR_MODEL = Vector Model to be used. Future, models are expected to change due to deprecation and expect new model to be used 

2. Install Python dependencies:

```

pip install -r requirements.txt

```

3. Run the collection creation script:

```

python populate_db/create_collection.py

```

4. Run the data loading script:

```

python populate_db/load_data.py

```