Developed and deployed a scalable Retrieval-Augmented Generation (RAG) application to support researchers in leveraging AI-driven insights.
- Utilized Sentence Transformers from Hugging Face to generate high-quality, domain-specific embeddings for scientific literature.
- Engineered an advanced data extraction pipeline using Python and state-of-the-art machine learning frameworks.
- Streamlined model management and experimentation with MLflow, ensuring reproducibility and scalability.
- Optimized deployment processes through containerization with Docker, enhancing system reliability and portability.