Apppublic

andreped/ReferenceBot

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes

App README

ReferenceBot

![License](https://opensource.org/licenses/MIT) <a target="blank" href="https://huggingface.co/spaces/andreped/ReferenceBot"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-yellow.svg"></a> [![Streamlit App](https://static.streamlit.io/badges/streamlitbadgeblackwhite.svg)](https://referencebot.streamlit.app) ![CI/CD](https://github.com/andreped/ReferenceBot/actions/workflows/deploy.yml)

Continuous integration

Build Type	Status
HF Deploy	![Deploy](https://github.com/andreped/referencebot/actions)
File size check	![Filesize](https://github.com/andreped/referencebot/actions)
Formatting check	![Filesize](https://github.com/andreped/ReferenceBot/actions)

Installation

Follow the instructions below to run the Streamlit server locally.

Prerequisites

Make sure you have Python ≥3.10 installed.

Steps

These instructions were tested on macOS 13.6 Ventura with ARM CPU and Python 3.10.11.

1.Clone the repository:

bash

git clone https://github.com/andreped/ReferenceBot
cd ReferenceBot

1.Setup virtual environment and install dependencies:

bash

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

1.Create the secrets file at .streamlit/secrets.toml and fill in the relevant info:

bash

OPENAI_API_KEY = "<insert OpenAI API key>"
CHATGPT_MODEL = "<insert model name>"
OPENAI_API_BASE = "https://<insert-openai-service-name>.openai.azure.com"
OPENAI_API_VERSION = "<insert version>"
ENGINE = "<insert deployment model name>"
ENGINE_EMBEDDING = "<insert deployment embedding name>"

1.Run the Streamlit server

bash

streamlit run knowledge_gpt/main.py

Build with Docker

Run the following commands to build and run the Docker image.

bash

docker build -t reference-bot .
docker run -p 8501:8501 reference-bot

Open http://localhost:8501 in your browser to access the app.

Demo <a target="_blank" href="https://huggingface.co/spaces/andreped/ReferenceBot"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-yellow.svg"></a>

A live demonstration is hosted at Hugging Face! Click the 🤗 badge above.

Screenshot 2023-10-30 at 15 35 51

Acknowledgements

We have built on-top of KnowledgeGPT to enable the tool be be used with Azure OpenAI Services. Thus, all credit should go towards the original developers.

License

Distributed under the MIT License. See LICENSE for more information.