Files
Anton_wireframe/app/db/db.py
T
bolade bbf6af58f0 Implement LLM-powered Investor Parser with CSV processing, SQL and vector database integration
- Added FastAPI application with a simple root endpoint.
- Developed LLMInvestorParser class for processing investor data from CSV files.
- Integrated OpenAI API for LLM enhancements and JSON cleaning.
- Implemented structured data extraction and saving to SQL database.
- Added functionality to save investor descriptions to ChromaDB for vector similarity search.
- Created command-line interface for processing files and searching investors.
- Added schema definitions for Investor and related data models using SQLAlchemy and Pydantic.
- Implemented logging for better traceability and error handling.
- Included requirements.txt for dependency management.
2025-08-28 22:51:58 +01:00

43 lines
1.0 KiB
Python

import os
from contextlib import contextmanager
from typing import Generator
from sqlalchemy import create_engine
from sqlalchemy.orm import Session, sessionmaker
from schema import Base
# Database configuration
DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///investors.db")
# Create engine
engine = create_engine(DATABASE_URL, echo=False)
# Create session factory
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
def init_database():
"""Initialize the database by creating all tables"""
Base.metadata.create_all(bind=engine)
print("Database initialized successfully!")
@contextmanager
def get_session() -> Generator[Session, None, None]:
"""Get a database session with automatic cleanup"""
session = SessionLocal()
try:
yield session
session.commit()
except Exception as e:
session.rollback()
raise e
finally:
session.close()
def get_session_sync() -> Session:
"""Get a database session for synchronous operations"""
return SessionLocal()