https://github.com/chibuikeeugene/llm_app_question_and_answer

A large language model that takes any website as an input together with a user query prompt and returns a suitable human response. This program uses a llama3 model locally hosted to return human readable and understandable results.
https://github.com/chibuikeeugene/llm_app_question_and_answer

generative-ai langchain-python llm

Last synced: about 1 month ago
JSON representation

A large language model that takes any website as an input together with a user query prompt and returns a suitable human response. This program uses a llama3 model locally hosted to return human readable and understandable results.

• Host: GitHub
• URL: https://github.com/chibuikeeugene/llm_app_question_and_answer
• Owner: chibuikeeugene
• Created: 2024-07-03T08:15:14.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-09-12T10:25:56.000Z (4 months ago)
• Last Synced: 2024-09-12T21:50:56.245Z (4 months ago)
• Topics: generative-ai, langchain-python, llm
• Language: Jupyter Notebook
• Homepage:
• Size: 1.42 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# LLM Q&A with any website  

A large language model that takes any website as an input together with a user query prompt and returns a suitable human response. This program uses a **llama3 model locally hosted** to return human readable and understandable results.  

## Dependencies and packages  

1. python = "^3.10"

2. streamlit = "^1.36.0"

3. langchain = "^0.2.6"

4. llama 3

5. huggingface-hub = "^0.23.4"

6. python-dotenv = "^1.0.1"

7. langchain-community = "^0.2.6"

8. langchain-ollama = "^0.1.0"

9. beautifulsoup4 = "^4.12.3"

10. faiss-cpu = "^1.8.0.post1"

11. sphinx = "^8.0.2"

12. loguru = "^0.7.2"

13. fire = "^0.6.0"

## To run the application

1. install llama3 and run server locally - using the command -  ollama run llama3

2. Install the package dependencies using poetry install command. Ensure you do this in a virual environment.

3. navigate to the q_and_a sub-folder and run the command -  streamlit run main.py

4. Good luck !

## Snapshots

### Q&A architecture

![Q&A app schema]()

### Live view of our application in workmode with Streamlit as the frontend

![Streamlit app 1]()

![Streamlit app 2]()