How sayedalihassaan/vector_database_qdrant-semantic works
Project type and purpose
• This is a backend‐only Python service (an open-source tool) that implements a semantic search engine.
• It reads text data (e.g. articles), generates embeddings via a configurable model, and stores/queries vectors in a Qdrant vector database.
File structure
• Top level:
• Backend.py – the API/CLI entrypoint
• temp.py – scratch/testing script
• .env.example, requirements.txt – environment and dependencies
• src/
• config.py – loads env vars and global settings
• notebooks/ – Jupyter notebooks for data-prep and exploration
• services/ – core modules:
– EmbeddingModel.py (encapsulates the embedding provider)
– VectorDBClient.py (high-level interface for upsert/search)
– QdrantClient.py (low-level wrapper around the Qdrant REST/gRPC API)
README
• Confirms the purpose: “Semantic Search Engine using qdrant as a vector database.”