AI Data Engineer | PySpark · Databricks · AWS · Airflow | MSc ML & AI
-
Updated
Jun 8, 2026
#
ai-data-engineering
Here are 4 public repositories matching this topic...
面向在职传统数据工程师的 Data + AI 职业转型项目：基于 DeepSeek smallpond、3FS 与论文的可复现实战
-
Updated
Sep 1, 2026 - Python
Earnings call RAG pipeline: Hugging Face → chunk → pgvector + Chroma → FastAPI Q&A → 92% retrieval hit rate
-
Updated
Oct 7, 2026 - Python
Production-grade RAG data platform: lakehouse-backed chunks (Delta/Iceberg) + multi-backend vector stores (pgvector/Qdrant/LanceDB) + hybrid retrieval (BM25 + vector + RRF + reranker) + RAGAS eval. 72 hermetic tests, zero-cost CI.
python airflow embeddings data-engineering semantic-search iceberg reranker rag fastapi delta-lake vector-database hybrid-search qdrant llm pgvector retrieval-augmented-generation lancedb langfuse ragas ai-data-engineering
-
Updated
Apr 23, 2026 - Python
Add this topic to your repo
To associate your repository with the ai-data-engineering topic, visit your repo's landing page and select "manage topics."