OCR Text Extraction

This commit is contained in:
2026-01-24 21:24:07 +05:30
parent c76d533783
commit 71d8f0fab5
41 changed files with 1414 additions and 33 deletions

View File

@@ -1,5 +1,7 @@
import os
from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary
import urllib.parse
from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary, Enum as SqlEnum
from sqlalchemy.dialects.postgresql import JSONB
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker, relationship
from dotenv import load_dotenv
@@ -7,22 +9,11 @@ from dotenv import load_dotenv
# Load environment variables
load_dotenv()
DB_USER = os.getenv("DB_USER")
DB_PASSWORD = os.getenv("DB_PASSWORD")
DB_HOST = os.getenv("DB_HOST")
DB_PORT = os.getenv("DB_PORT")
import urllib.parse
# ... (imports)
# Load environment variables
load_dotenv()
DB_USER = os.getenv("DB_USER")
DB_PASSWORD = os.getenv("DB_PASSWORD")
DB_HOST = os.getenv("DB_HOST")
DB_PORT = os.getenv("DB_PORT")
DB_NAME = os.getenv("DB_NAME")
DB_USER = os.getenv("DB_USER", "postgres")
DB_PASSWORD = os.getenv("DB_PASSWORD", "password")
DB_HOST = os.getenv("DB_HOST", "localhost")
DB_PORT = os.getenv("DB_PORT", "5432")
DB_NAME = os.getenv("DB_NAME", "ocr_db")
encoded_user = urllib.parse.quote_plus(DB_USER)
encoded_password = urllib.parse.quote_plus(DB_PASSWORD)
@@ -35,6 +26,26 @@ SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
Base = declarative_base()
class Vendor(Base):
__tablename__ = "vendors"
id = Column(Integer, primary_key=True, index=True)
name = Column(String, unique=True, index=True)
default_model = Column(String) # 'text' or 'vision'
created_at = Column(DateTime)
class Document(Base):
__tablename__ = "documents"
id = Column(Integer, primary_key=True, index=True)
vendor_id = Column(Integer, ForeignKey("vendors.id"), nullable=True)
filename = Column(String)
upload_date = Column(DateTime)
status = Column(String) # 'pending', 'verified'
processed_data = Column(JSONB) # Store the verified extraction results
vendor = relationship("Vendor")
class Email(Base):
__tablename__ = "emails"
@@ -54,7 +65,7 @@ class Attachment(Base):
email_id = Column(Integer, ForeignKey("emails.id"))
filename = Column(String)
content_type = Column(String)
file_content = Column(LargeBinary) # Storing content directly in DB as requested
file_content = Column(LargeBinary)
email = relationship("Email", back_populates="attachments")

View File

@@ -85,6 +85,12 @@ class LoginResponse(BaseModel):
token: str
message: str
@app.post("/api/login", response_model=LoginResponse)
def login(request: LoginRequest):
if request.username == "admin" and request.password == "admin":
return LoginResponse(token="fake-super-secret-token", message="Success")
raise HTTPException(status_code=401, detail="Invalid username or password")
class NERResponse(BaseModel):
text: str