[NOTICKET]: adjusted pyproject.toml for OCR PDF

.gitignore

@@ -35,4 +35,5 @@ playground_chat.py
 playground_flush_cache.py
 playground_create_user.py
 API_CONTRACT.md
-context_engineering/
+context_engineering/
+sample_file/

pyproject.toml

@@ -84,6 +84,10 @@ dependencies = [
     "pymssql>=2.3.0",
     "sqlalchemy-bigquery>=1.11.0",
     "snowflake-sqlalchemy>=1.7.0",
+    # --- OCR (pdf processing) ---
+    "pdf2image>=1.17.0",
+    "pytesseract>=0.3.13",
+    "pypdf2>=3.0.1",
 ]
 
 [project.optional-dependencies]

src/knowledge/processing_service.py

@@ -5,12 +5,10 @@ from langchain_core.documents import Document as LangChainDocument
 from src.db.postgres.vector_store import get_vector_store
 from src.storage.az_blob.az_blob import blob_storage
 from src.db.postgres.models import Document as DBDocument
-from src.config.settings import settings
 from sqlalchemy.ext.asyncio import AsyncSession
 from src.middlewares.logging import get_logger
 from typing import List
 import sys
-import pypdf
 import docx
 import pandas as pd
 import pytesseract