✨ Add text extraction dependencies and integrate extraction in document creation

Author: monicasmith463

backend/app/api/routes/documents.py

@@ -1,5 +1,6 @@
 from typing import Any
 from app.api.deps import CurrentUser, SessionDep
+from app.core.extractors import extract_text_and_save_to_db
 from app.models import Document, DocumentCreate, DocumentPublic
 from fastapi import APIRouter, BackgroundTasks, File, UploadFile, HTTPException
 from app.s3 import upload_file_to_s3, generate_s3_url
@@ -40,6 +41,5 @@ def create_document(
 
     # 3. Kick off background job
     print("Document created, starting background task...")
-    # background_tasks.add_task(generate_questions, document.id)
-
+    background_tasks.add_task(extract_text_and_save_to_db, url, document.id)
     return document

backend/app/tests/api/routes/test_documents.py

@@ -6,9 +6,10 @@
 from app.core.config import settings
 from app.tests.utils.document import create_random_document
 import io
+import time
 
 
-def skip_test_create_document(
+def skip_test_create_document_real_s3(
     client: TestClient, superuser_token_headers: dict[str, str]
 ) -> None:
     '''Test creating a document with a file upload with the real S3 service.'''
@@ -25,10 +26,6 @@ def skip_test_create_document(
     assert response.status_code == 200
     content = response.json()
     assert "id" in content, "actual response: " + str(content)
-    # assert content["title"] == metadata["title"]
-    # assert content["description"] == metadata["description"]
-    # assert "id" in content
-    # assert "owner_id" in content
 
 def test_create_document(
     client: TestClient, superuser_token_headers: dict[str, str]

backend/pyproject.toml

@@ -22,6 +22,8 @@ dependencies = [
     "pydantic-settings<3.0.0,>=2.2.1",
     "sentry-sdk[fastapi]<2.0.0,>=1.40.6",
     "pyjwt<3.0.0,>=2.8.0",
+    "pymupdf>=1.26.3",
+    "textract>=1.6.5",
 ]
 
 [tool.uv]