11de850054
PDF uploads were stored in S3 and had text extracted during upload, but fetch_upload_images() filtered exclusively for image MIME types, so document content never reached the AI. - Add fetch_upload_documents() in storage_service.py to retrieve extracted_content for PDFs and text files - Update ai_sessions.py chat endpoint to call both fetch_upload_images and fetch_upload_documents, injecting document text as context - Add PDF text extraction in _generate_ai_description (pypdf) - Add pypdf>=4.0.0 to requirements.txt - Fix test_db teardown to avoid connection pool issues - Add 5 tests for fetch_upload_documents Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
63 lines
926 B
Plaintext
63 lines
926 B
Plaintext
# FastAPI and server
|
|
fastapi==0.128.5
|
|
uvicorn[standard]==0.40.0
|
|
|
|
# Database
|
|
sqlalchemy==2.0.46
|
|
asyncpg==0.31.0
|
|
psycopg2-binary==2.9.9
|
|
alembic==1.18.3
|
|
|
|
# Authentication
|
|
python-jose[cryptography]==3.5.0
|
|
passlib[bcrypt]==1.7.4
|
|
bcrypt==4.1.2
|
|
python-multipart==0.0.22
|
|
|
|
# Validation and settings
|
|
pydantic==2.12.5
|
|
pydantic-settings==2.12.0
|
|
email-validator==2.1.0
|
|
|
|
# Rate Limiting
|
|
slowapi==0.1.9
|
|
|
|
# Payments
|
|
stripe==14.3.0
|
|
|
|
# Email
|
|
resend==2.21.0
|
|
|
|
# HTTP client (seed scripts, internal API calls)
|
|
httpx>=0.27.0
|
|
|
|
# AI Flow Builder
|
|
anthropic>=0.40.0
|
|
google-genai>=1.0.0
|
|
|
|
# RAG / Embeddings
|
|
pgvector>=0.3.6
|
|
voyageai>=0.3.0
|
|
|
|
# Monitoring
|
|
sentry-sdk[fastapi]>=2.54.0
|
|
|
|
# PDF Export
|
|
weasyprint>=62.0
|
|
jinja2>=3.1.0
|
|
|
|
# Utilities
|
|
python-dotenv==1.0.1
|
|
croniter>=2.0.0
|
|
pytz>=2024.1
|
|
apscheduler>=3.10.4
|
|
|
|
# Object Storage
|
|
boto3>=1.34.0
|
|
|
|
# Image processing (vision upload resize)
|
|
Pillow>=10.0.0
|
|
|
|
# PDF text extraction (upload analysis)
|
|
pypdf>=4.0.0
|