45 lines
1.4 KiB
Python
45 lines
1.4 KiB
Python
|
import os
|
||
|
|
from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, text
|
||
|
|
from sqlalchemy.orm import declarative_base, sessionmaker
|
||
|
|
from pgvector.sqlalchemy import Vector
|
||
|
|
|
||
|
|
POSTGRES_USER = os.environ.get("POSTGRES_USER", "allmail")
|
||
|
|
POSTGRES_PASSWORD = os.environ.get("POSTGRES_PASSWORD", "postgres")
|
||
|
|
POSTGRES_DB = os.environ.get("POSTGRES_DB", "emails_db")
|
||
|
|
DB_HOST = os.environ.get("DB_HOST", "localhost")
|
||
|
|
|
||
|
|
DATABASE_URL = f"postgresql://{POSTGRES_USER}:{POSTGRES_PASSWORD}@{DB_HOST}/{POSTGRES_DB}"
|
||
|
|
|
||
|
|
engine = create_engine(DATABASE_URL)
|
||
|
|
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
|
||
|
|
|
||
|
|
Base = declarative_base()
|
||
|
|
|
||
|
|
# Gemini gemini-embedding-001 with output_dimensionality=768
|
||
|
|
EMBEDDING_DIMENSIONS = 768
|
||
|
|
|
||
|
|
class Email(Base):
|
||
|
|
__tablename__ = "emails"
|
||
|
|
|
||
|
|
id = Column(Integer, primary_key=True, index=True)
|
||
|
|
message_id = Column(String, unique=True, index=True)
|
||
|
|
subject = Column(Text)
|
||
|
|
sender = Column(String)
|
||
|
|
date = Column(DateTime)
|
||
|
|
content = Column(Text)
|
||
|
|
embedding = Column(Vector(EMBEDDING_DIMENSIONS))
|
||
|
|
|
||
|
|
def init_db():
|
||
|
|
# Install pgvector extension if not exists
|
||
|
|
with engine.connect() as conn:
|
||
|
|
conn.execute(text("CREATE EXTENSION IF NOT EXISTS vector"))
|
||
|
|
conn.commit()
|
||
|
|
Base.metadata.create_all(bind=engine)
|
||
|
|
|
||
|
|
def get_db():
|
||
|
|
db = SessionLocal()
|
||
|
|
try:
|
||
|
|
yield db
|
||
|
|
finally:
|
||
|
|
db.close()
|