Skip to main content

​
Core Technologies

​
FastAPI

Modern, high-performance Python web framework. Why FastAPI:
  • Automatic OpenAPI documentation
  • Built-in validation with Pydantic
  • Async/await support
  • High performance (comparable to Node.js)
  • Type hints throughout

​
Python 3.8+

Language runtime with extensive library ecosystem.

​
Uvicorn

ASGI server for production deployment. 
import uvicorn

uvicorn.run(
    "app.main:app",
    host="0.0.0.0",
    port=8000,
    reload=True  # Development only
)

​
AI & ML Libraries

Purpose: Claude AI integrationModels Used:
  • claude-3-opus (highest quality)
  • claude-3-sonnet (balanced)
  • claude-3-haiku (fast)
Use Cases: Report generation, document analysis, CRM queries
Purpose: Alternative AI providerModels: GPT-4, GPT-3.5-turboUse Cases: Embeddings, fallback AI
Purpose: Multi-agent orchestrationFeatures: Agent teams, tool use, conversation management
Purpose: Local model inferenceUse Cases: Embeddings, classification

​
Document Processing

Purpose: Primary document extractionSupports: PDF, DOCX, PPTX, HTML Features: Layout analysis, table extraction, image extraction
Purpose: PDF text and table extractionAdvantages: Better table detection than PyPDF2
Purpose: Optical Character RecognitionLanguages: 80+ Features: GPU support, high accuracy

​
Database & Storage

Purpose: PostgreSQL database accessFeatures:
  • Database queries
  • Auth management
  • File storage
  • Real-time subscriptions
Purpose: ORM for complex queriesUse Cases: Advanced joins, aggregations

​
External Integrations

Purpose: Unified OAuth and API accessIntegrations: Gmail, Outlook, Drive, Calendar, 100+ more
Purpose: AI-powered web searchUse Case: Company sourcing and research

​
Data Processing

Purpose: Data manipulation and analysisUse Cases: Excel processing, data transformation
Purpose: Numerical computationsUse Cases: Financial calculations, analytics

​
Development Tools

  • Black: Code formatting
  • pytest: Testing framework
  • mypy: Type checking
  • pylint: Code linting

​
Dependencies

Total: 145+ Python packages in requirements.txt Key Packages: 
fastapi==0.109.0
uvicorn[standard]==0.27.0
pydantic==2.5.0
python-jose[cryptography]==3.3.0
python-multipart==0.0.6
supabase==2.3.0
anthropic==0.8.0
openai==1.6.0
autogen==0.2.0
docling==1.0.0
easyocr==1.7.0
pdfplumber==0.10.0
pandas==2.1.0
numpy==1.24.0

​
Performance

  • Requests/sec: 1,000+ on single instance
  • Async I/O: Non-blocking operations
  • Connection pooling: Reuse database connections
  • Agent pools: Eliminate 5-11s cold start

​
Next Steps

Backend Overview

Architecture overview

Services

Core services

API Reference

API endpoints