This FastAPI project is designed to analyze and interact with textual data, focusing on Natural Language Processing (NLP) and sentiment analysis. It utilizes OpenAI's GPT-3.5 to generate conversational responses and conducts various analyses on word frequencies and example sentences from a dataset.
Explore the full API documentation here: API Documentation
This comprehensive guide provides detailed information on all API endpoints, their usage, and examples.
- ChatGPT Integration: Utilizes OpenAI's GPT-3.5 model to generate conversational responses based on user input.
- Word Frequency Analysis: Retrieves word frequencies, filtered by sentiment categories like neutral, positive, and negative.
- Example Sentences: Provides example sentences for a given word, helping in understanding the context of its usage.
- Comments and Sentences Data Retrieval: Fetches data for specific comments or sentences based on their IDs.
- Word Data Analysis: Offers detailed analysis of words including frequency and TF-IDF values across different sentiment categories.
- Python 3.8 or higher
- FastAPI
- Uvicorn (for running the server)
- SQLAlchemy
- OpenAI API key
-
Clone the repository to your local machine.
-
Install the required dependencies:
pip install -r requirements.txt
-
Set your OpenAI API key as an environment variable:
export OPENAI_API_KEY='your_api_key_here'
Run the server using Uvicorn:
uvicorn main:app --reloadThe API will be available at http://localhost:8000.
This project is configured for automatic deployment. Whenever you commit to the main branch, the application will automatically deploy, ensuring that the latest version is always live.
The project uses an SQLite database to store and retrieve word, sentence, and comment data. SQLAlchemy is used for database interactions.
Cross-Origin Resource Sharing (CORS) is configured to allow requests from specific origins including local development environments and deployed frontend applications.