Pinned Loading

1. Kafka-AirQulity-Pipeline Kafka-AirQulity-Pipeline Public

   A real-time data streaming pipeline for processing air quality data using Apache Kafka, with multiple storage backends and visualization capabilities.

   Java

2. sakila25 sakila25 Public

   Re-creation of sakila database with 2025 data from TMDB API, available with multiple database engines

   Python 3 1

3. ProofRAG ProofRAG Public

   Compare RAG techniques: simple vs. proposition-based embedding, standard vs. reliable retrieval with proof extraction. Includes demo scripts and performance benchmarks.

   Python

4. InterVox InterVox Public

   Voice interview agent that analyzes a candidate's resume and job description, conducts a structured voice interview turn by turn using speech-to-text and text-to-speech, and generates a final evalu…

   Python

5. LSTM-PySpark-Stream-Prediction LSTM-PySpark-Stream-Prediction Public

   Streaming pipeline using PySpark for updating predictions using LSTM for time series data

   Jupyter Notebook 1 1

6. LLMs-Dictionary LLMs-Dictionary Public

   Composite guide for the LLMs out there