Skip to content

ilmedova/llama3_chatbot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is AI chatbot using Python, Langchain, and LLMs (specifically Llama3 model)

If you want to get more information on Llama models, check out this link: https://llama.meta.com/docs/get-started/

1. Requirements

  1. Python and anaconda environment
  2. You will need 4.7GB of memory to download Llama3 model, so if you don't have enough space on your device work in Google Colab

2. Installation

  1. Go to project directory and run the following command:
pip install -r requirements.txt
  1. Dowload and install Ollama into your system. You can download it using the following link: https://ollama.com/download
  2. After you installed Ollama you can make sure if it is installed correctly by typing the following in your terminal:
ollama serve
  1. After you make sure you installed Ollama correctly, go and run this command in your project directory:
ollama pull llama3

3. Running the app

streamlit run app.py

4. You can also run it using Docker by using the included Dockerfile

Releases

No releases published

Packages

No packages published