Implement investor processing and querying functionality

- Added InvestorProcessor class for processing CSV data in batches and saving to SQL and vector databases.
- Introduced QueryProcessor class for querying investor information from SQL and vector databases.
- Integrated OpenAI's ChatGPT for structured output generation.
- Implemented data cleaning and control character removal in CSV processing.
- Added asynchronous processing capabilities for batch handling.
- Established connection to ChromaDB for vector storage of investor descriptions.
- Defined structured output schemas using Pydantic for investor data validation.
- Enhanced settings management for API key and database configurations.

app/db/db.py

@@ -1,11 +1,12 @@
 import os
-from contextlib import contextmanager
-from typing import Generator
+from typing import Annotated
 
+from fastapi import Depends
 from sqlalchemy import create_engine
+from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import Session, sessionmaker
 
-from schema import Base
+Base = declarative_base()
 
 # Database configuration
 DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///investors.db")
@@ -17,26 +18,23 @@ engine = create_engine(DATABASE_URL, echo=False)
 SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
 
 
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()
+
+
+db_dependency = Annotated[Session, Depends(get_db)]
+
+
 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()

app/db/tables.py

@@ -0,0 +1,23 @@
+import datetime
+
+from sqlalchemy import Column, DateTime, Integer, String
+
+from db.db import Base
+
+
+class InvestorTable(Base):
+    __tablename__ = "investors"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    aum = Column(Integer, nullable=False)
+    check_size = Column(String, nullable=False)
+    sector_focus = Column(String, nullable=False)
+    stage_focus = Column(String, nullable=False)
+    region = Column(String, nullable=False)
+    created_at = Column(DateTime, default=datetime.datetime.now(datetime.UTC))
+    updated_at = Column(
+        DateTime,
+        default=datetime.datetime.now(datetime.UTC),
+        onupdate=datetime.datetime.now(datetime.UTC),
+    )