https://github.com/tomarakanksha/hallucination-identification
It is an API that takes in a user query and AI response, then processes it to verify if this is a hallucination. It has set of documents that are the ground truth.
https://github.com/tomarakanksha/hallucination-identification
Last synced: 3 months ago
JSON representation
It is an API that takes in a user query and AI response, then processes it to verify if this is a hallucination. It has set of documents that are the ground truth.
- Host: GitHub
- URL: https://github.com/tomarakanksha/hallucination-identification
- Owner: tomarakanksha
- Created: 2024-02-21T04:11:54.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-02-21T05:09:18.000Z (over 1 year ago)
- Last Synced: 2025-02-05T07:23:35.433Z (4 months ago)
- Language: Python
- Size: 1.95 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Hallucination-Identification
It is an API that takes in a user query and AI response, then processes it to verify if this is a hallucination. It has set of documents that are the ground truth.
## Setup
1. Create a virtual environment: `python -m venv venv`
2. Activate the virtual environment: `source venv/bin/activate` (Linux/Mac) or `venv\Scripts\activate` (Windows)
3. Install dependencies: `pip install -r requirements.txt`
4. Load your environment variables: `cp .env.example .env` (Linux/Mac) or `copy .env.example .env` (Windows)
## Usage
1. Fill in the required API keys in the code.
2. Add your txt file in '/Data' folder.
3. Run the FastAPI application: `uvicorn main:app --reload`
4. Visit `http://127.0.0.1:8000/docs` in your browser to interact with the API using Swagger documentation.