Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/andreped/referencebot
KnowledgeGPT + Azure OpenAI = <3
https://github.com/andreped/referencebot
ai azure bot chatbot huggingface huggingface-spaces knowledge-gpt langchain llm mit openai streamlit
Last synced: about 1 month ago
JSON representation
KnowledgeGPT + Azure OpenAI = <3
- Host: GitHub
- URL: https://github.com/andreped/referencebot
- Owner: andreped
- License: mit
- Created: 2023-10-30T09:14:54.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-30T14:48:18.000Z (over 1 year ago)
- Last Synced: 2024-12-19T22:09:55.794Z (about 2 months ago)
- Topics: ai, azure, bot, chatbot, huggingface, huggingface-spaces, knowledge-gpt, langchain, llm, mit, openai, streamlit
- Language: Python
- Homepage:
- Size: 46.9 KB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
---
title: "ReferenceBot: KnowledgeGPT + Azure OpenAI = <3"
colorFrom: indigo
colorTo: indigo
sdk: docker
app_port: 8501
emoji: 💬
pinned: false
license: mit
app_file: knowledge_gpt/main.py
---
# [ReferenceBot](https://github.com/andreped/referencebot#referencebot)
[](https://opensource.org/licenses/MIT)
[](https://referencebot.streamlit.app)
[](https://github.com/andreped/ReferenceBot/actions/workflows/deploy.yml)
## [Continuous integration](https://github.com/andreped/referencebot#continuous-integration)
| Build Type | Status |
| - | - |
| **HF Deploy** | [](https://github.com/andreped/referencebot/actions) |
| **File size check** | [](https://github.com/andreped/referencebot/actions) |
| **Formatting check** | [](https://github.com/andreped/ReferenceBot/actions) |
## [Installation](https://github.com/andreped/referencebot#installation)
Follow the instructions below to run the Streamlit server locally.
### [Prerequisites](https://github.com/andreped/referencebot#prerequisites)
Make sure you have Python `≥3.10` installed.
### [Steps](https://github.com/andreped/referencebot#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
```
2. Setup virtual environment and install dependencies:
```bash
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
3. Create the secrets file at `.streamlit/secrets.toml` and fill in the relevant info:
```bash
OPENAI_API_KEY = ""
CHATGPT_MODEL = ""
OPENAI_API_BASE = "https://.openai.azure.com"
OPENAI_API_VERSION = ""
ENGINE = ""
ENGINE_EMBEDDING = ""
```
4. Run the Streamlit server
```bash
streamlit run knowledge_gpt/main.py
```
## [Build with Docker](https://github.com/andreped/referencebot#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](https://github.com/andreped/referencebot#demo)
A live demonstration is hosted at Hugging Face! Click the 🤗 badge above.
## [Acknowledgements](https://github.com/andreped/referencebot#acknowledgements)
We have built on-top of [KnowledgeGPT](https://github.com/mmz-001/knowledge_gpt) to enable the tool be be used with Azure OpenAI Services. Thus, all credit should go towards the original developers.
## [License](https://github.com/andreped/referencebot#license)
Distributed under the MIT License. See [LICENSE](https://github.com/andreped/ReferenceBot/blob/main/LICENSE) for more information.