Design and implementation of a distributed pipeline to automate the ingestion, processing, and vector indexing of scientific documents at scale.
- Published On
data engineering
Tags
AI (4)RAG (3)Computer Vision (2)Langchain (2)Python (2)Data Engineering (1)Distributed Systems (1)Vector Search (1)Graph Databases (1)E-commerce (1)Recommendation Systems (1)Document AI (1)Multimodal AI (1)LLM (1)ESP32 (1)Embedded Systems (1)HSV Filtering (1)IoT (1)Arduino (1)Data analytics (1)AI agents (1)Data pipeline (1)Data lake (1)ETL (1)SBert (1)LLM-as-a-judge (1)Deep Learning (1)Training technique (1)Machine Learning (1)Time Series (1)ARIMA (1)Data Science (1)Forecasting (1)LLMs (1)Vector Databases (1)Football Analytics (1)Video Analytics (1)YOLO (1)