API Server

Overview

The Olis API Server is a FastAPI-based backend service that provides the core intelligence behind Olis. It includes a sophisticated RAG (Retrieval-Augmented Generation) pipeline for document understanding and intelligent responses.

Technology Stack

FastAPI

Modern, fast Python web framework

Uvicorn

Lightning-fast ASGI server

RAG Pipeline

Document retrieval and generation system

Vector Database

Semantic search capabilities

Project Structure

apps/api-server/
├── src/
│   └── backend/
│       ├── routers/          # API route handlers
│       ├── utils/
│       │   └── retrievers/   # RAG components
│       │       └── document_db/
│       │           ├── reranker.py
│       │           └── retriever.py
│       ├── models/           # Pydantic models
│       └── middleware/       # Custom middleware
├── tests/
│   └── integration_tests/    # Integration tests
├── scripts/
│   ├── preflight_rag.sh     # Unix RAG preflight
│   └── preflight_rag.ps1    # Windows RAG preflight
├── requirements.txt          # Python dependencies
└── main.py                   # Application entry point

Development Setup

Prerequisites

Python 3.9+
pip or poetry
Redis (optional, for caching)
Vector database (optional, for RAG)

Installation

Navigate to the API server directory

cd apps/api-server

Create a virtual environment (recommended)

# Create virtual environment
python -m venv venv

# Activate it
# Windows
.\venv\Scripts\activate

# macOS/Linux
source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Set up environment variables

Create a .env file:

# API Configuration
API_HOST=0.0.0.0
API_PORT=8000
DEBUG=True

# Database
DATABASE_URL=postgresql://user:pass@localhost/olis

# Redis Cache
REDIS_URL=redis://localhost:6379

# RAG Configuration
VECTOR_DB_URL=http://localhost:8080
EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

Run the server

uvicorn main:app --reload --host 0.0.0.0 --port 8000

The API will be available at http://localhost:8000.

API Endpoints

Core Endpoints

GET /health

Health check endpointResponse:

{
  "status": "healthy",
  "timestamp": "2024-01-01T00:00:00Z",
  "version": "0.1.0"
}

POST /api/chat

Send a chat message and receive AI responseRequest:

{
  "message": "What is Olis?",
  "context": [],
  "sessionId": "uuid-string"
}

Response:

{
  "response": "Olis is an AI assistant...",
  "sources": ["doc1.pdf", "doc2.md"],
  "confidence": 0.95
}

POST /api/search

Search documents semanticallyRequest:

{
  "query": "machine learning basics",
  "limit": 10,
  "filters": {
    "type": "pdf"
  }
}

Response:

{
  "results": [
    {
      "id": "doc1",
      "content": "...",
      "score": 0.92,
      "metadata": {...}
    }
  ],
  "total": 42
}

POST /api/ingest

Ingest documents into the RAG systemRequest: Multipart form data with file uploadsResponse:

{
  "success": true,
  "documentsProcessed": 5,
  "jobId": "job-uuid"
}

Interactive API Documentation

FastAPI automatically generates interactive API documentation:

Swagger UI: http://localhost:8000/docs
ReDoc: http://localhost:8000/redoc

RAG Pipeline

Architecture

Components

Document Ingestion
Retrieval
Reranking
Generation

Process:

Document upload via API
Text extraction (PDF, DOCX, etc.)
Chunking into manageable pieces
Embedding generation
Storage in vector database

Supported Formats:

PDF
DOCX
TXT
MD (Markdown)
JSON
CSV

Process:

Query embedding generation
Semantic similarity search
Top-k document retrieval
Metadata filtering

Configuration:

# src/backend/utils/retrievers/document_db/retriever.py
class DocumentRetriever:
    def __init__(
        self,
        top_k: int = 10,
        similarity_threshold: float = 0.7
    ):
        self.top_k = top_k
        self.threshold = similarity_threshold

Purpose: Improve retrieval quality by reordering resultsReranker Types:

Cross-encoder: Deep semantic understanding
BM25: Traditional keyword-based
Hybrid: Combine multiple signals

Implementation:

# src/backend/utils/retrievers/document_db/reranker.py
class Reranker:
    def rerank(
        self,
        query: str,
        documents: List[Document]
    ) -> List[Document]:
        # Reranking logic
        pass

RAG Preflight Testing

Before deploying, run the RAG preflight check to catch issues early:

cd apps/api-server
./scripts/preflight_rag.sh

Environment Overrides

# Set custom timeout (default: 300 seconds)
PREFLIGHT_TIMEOUT_SECONDS=600 ./scripts/preflight_rag.sh

# Keep containers running for debugging
KEEP_PREFLIGHT_RUNNING=1 ./scripts/preflight_rag.sh

What It Tests

Import Checks

All Python modules import successfully
No missing dependencies
Correct Python version

Runtime Checks

API server starts without errors
Database connections work
Redis cache is accessible
Vector database is reachable

Integration Tests

Document ingestion pipeline
Query retrieval
Reranking functionality
End-to-end RAG flow

Docker Deployment

Local Development

Use Docker Compose for local development:

# docker-compose.local.yml
version: '3.8'

services:
  api:
    build: ./apps/api-server
    ports:
      - "8000:8000"
    environment:
      - DATABASE_URL=${DATABASE_URL}
      - REDIS_URL=redis://redis:6379
    depends_on:
      - redis
      - vector-db

  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"

  vector-db:
    image: qdrant/qdrant
    ports:
      - "6333:6333"

Start services:

docker-compose -f docker-compose.local.yml up

Production Build

# Dockerfile
FROM python:3.11-slim

WORKDIR /app

# Install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY . .

# Run with uvicorn
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

Build and run:

docker build -t olis-api:latest .
docker run -p 8000:8000 olis-api:latest

Testing

Running Tests

cd apps/api-server
pytest

Test Structure

# tests/integration_tests/test_fastapi.py
import pytest
from fastapi.testclient import TestClient
from main import app

client = TestClient(app)

def test_health_endpoint():
    response = client.get("/health")
    assert response.status_code == 200
    assert response.json()["status"] == "healthy"

def test_chat_endpoint():
    response = client.post(
        "/api/chat",
        json={"message": "Hello", "sessionId": "test"}
    )
    assert response.status_code == 200
    assert "response" in response.json()

Configuration

Environment Variables

API Settings

API_HOST=0.0.0.0
API_PORT=8000
DEBUG=False
LOG_LEVEL=INFO
CORS_ORIGINS=["http://localhost:3000"]

Database Settings

DATABASE_URL=postgresql://user:pass@localhost/olis
DATABASE_POOL_SIZE=20
DATABASE_MAX_OVERFLOW=10

Redis Settings

REDIS_URL=redis://localhost:6379
REDIS_CACHE_TTL=3600
REDIS_MAX_CONNECTIONS=50

RAG Settings

VECTOR_DB_URL=http://localhost:6333
EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
CHUNK_SIZE=512
CHUNK_OVERLAP=50
TOP_K_DOCUMENTS=10
RERANK_ENABLED=True

Performance Optimization

Caching

Redis for query results
Embedding cache
Response caching
Connection pooling

Async Operations

Async/await throughout
Non-blocking I/O
Background tasks
Parallel processing

Database Optimization

Connection pooling
Query optimization
Index management
Batch operations

Monitoring

Prometheus metrics
Request logging
Error tracking
Performance profiling

Troubleshooting

Server Won't Start

Problem: uvicorn fails to startSolution:

# Check port availability
netstat -an | grep 8000

# Try different port
uvicorn main:app --port 8001

# Check Python version
python --version  # Should be 3.9+

Import Errors

Problem: Module import failuresSolution:

# Verify virtual environment is activated
which python

# Reinstall dependencies
pip install --force-reinstall -r requirements.txt

# Check for missing packages
pip list

Database Connection Issues

Problem: Cannot connect to databaseSolution:

# Verify DATABASE_URL format
# postgresql://user:password@host:port/database

# Test connection directly
psql $DATABASE_URL

# Check firewall/network settings
telnet host port

RAG Pipeline Failures

Problem: Document ingestion or retrieval failsSolution:

Run preflight check: ./scripts/preflight_rag.sh
Check vector database is running
Verify embedding model is downloaded
Check logs for specific errors
Test with simple document first

Overview

Technology Stack

FastAPI

Uvicorn

RAG Pipeline

Vector Database

Project Structure

Development Setup

Prerequisites

Installation

API Endpoints

Core Endpoints

Interactive API Documentation

RAG Pipeline

Architecture

Components

RAG Preflight Testing

Environment Overrides

What It Tests

Docker Deployment

Local Development

Production Build

Testing

Running Tests

Test Structure

Configuration

Environment Variables

Performance Optimization

Caching

Async Operations

Database Optimization

Monitoring

Troubleshooting

Next Steps

API Reference

Electron Client

​Overview

​Technology Stack

FastAPI

Uvicorn

RAG Pipeline

Vector Database

​Project Structure

​Development Setup

​Prerequisites

​Installation

​API Endpoints

​Core Endpoints

​Interactive API Documentation

​RAG Pipeline

​Architecture

​Components

​RAG Preflight Testing

​Environment Overrides

​What It Tests

​Docker Deployment

​Local Development

​Production Build

​Testing

​Running Tests

​Test Structure

​Configuration

​Environment Variables

​Performance Optimization

Caching

Async Operations

Database Optimization

Monitoring

​Troubleshooting

​Next Steps

API Reference

Electron Client

Overview

Technology Stack

Project Structure

Development Setup

Prerequisites

Installation

API Endpoints

Core Endpoints

Interactive API Documentation

RAG Pipeline

Architecture

Components

RAG Preflight Testing

Environment Overrides

What It Tests

Docker Deployment

Local Development

Production Build

Testing

Running Tests

Test Structure

Configuration

Environment Variables

Performance Optimization

Troubleshooting

Next Steps