Document Q&A System

AI-based intelligent document question answering system built with FastAPI, supporting multiple document formats and AI providers.

Features

• Document Management: Upload, parse, and store documents (TXT, Markdown, PDF, DOCX)
• Intelligent Q&A: RAG-based question answering using semantic search
• Multi-turn Conversations: Context-aware chat with conversation history
• Multiple AI Providers: Support for OpenAI, Anthropic (Claude), and local models
• Vector Search: ChromaDB for efficient document chunk retrieval

Tech Stack

• Backend: FastAPI, Async SQLAlchemy, Pydantic v2
• Database: PostgreSQL, Redis
• Vector Store: ChromaDB
• AI: OpenAI, Anthropic, Sentence Transformers
• Document Parsing: pypdf, python-docx, markdown

Quick Start

Prerequisites

• Python 3.11+
• Docker and Docker Compose
• OpenAI or Anthropic API key

1. Clone and Setup

cd python-proj

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
make dev

2. Configure Environment

cp .env.example .env
# Edit .env with your settings (especially API keys)

3. Start Services

# Start PostgreSQL and Redis
make docker-up

# Run database migrations
make migrate

4. Run the Application

make run

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

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

API Endpoints

Documents

Method	Endpoint	Description
POST	/api/v1/documents	Upload a document
GET	/api/v1/documents	List all documents
GET	/api/v1/documents/{id}	Get document details
DELETE	/api/v1/documents/{id}	Delete a document

Q&A

Method	Endpoint	Description
POST	/api/v1/qa/ask	Ask a question

Conversations

Method	Endpoint	Description
POST	/api/v1/conversations	Create a conversation
GET	/api/v1/conversations	List conversations
GET	/api/v1/conversations/{id}	Get conversation details
PUT	/api/v1/conversations/{id}	Update a conversation
DELETE	/api/v1/conversations/{id}	Delete a conversation
POST	/api/v1/conversations/{id}/messages	Send a message

AI Settings

Method	Endpoint	Description
GET	/api/v1/settings/ai-providers	List AI providers
POST	/api/v1/settings/ai-providers	Add AI provider
PUT	/api/v1/settings/ai-providers/{id}	Update AI provider
DELETE	/api/v1/settings/ai-providers/{id}	Delete AI provider
POST	/api/v1/settings/ai-providers/{id}/test	Test AI connection

Usage Examples

Upload a Document

curl -X POST "http://localhost:8000/api/v1/documents" \
  -F "file=@document.pdf" \
  -F "title=My Document"

Ask a Question

curl -X POST "http://localhost:8000/api/v1/qa/ask" \
  -H "Content-Type: application/json" \
  -d '{"question": "What is the main topic of the document?"}'

Create a Conversation

curl -X POST "http://localhost:8000/api/v1/conversations" \
  -H "Content-Type: application/json" \
  -d '{"title": "My Chat", "document_ids": ["doc-uuid-here"]}'

Send a Message

curl -X POST "http://localhost:8000/api/v1/conversations/{id}/messages" \
  -H "Content-Type: application/json" \
  -d '{"message": "Tell me more about section 2"}'

Project Structure

python-proj/
├── app/
│   ├── api/routers/     # API route handlers
│   ├── services/        # Business logic
│   ├── daos/            # Data access layer
│   ├── models/          # SQLAlchemy models
│   ├── schemas/         # Pydantic schemas
│   ├── core/            # Config, exceptions, middleware
│   └── infra/           # Database, Redis, Vector store
├── migrations/          # Alembic migrations
├── tests/               # Test suite
├── docker/              # Docker configuration
└── docs/                # Documentation

Development

# Run tests
make test

# Run linters
make lint

# Format code
make format

# Create a migration
make migration msg="add new table"

Docker Deployment

# Build the image
make docker-build

# Run with Docker Compose
make docker-run

Configuration

Key environment variables:

Variable	Description	Default
ENV	Environment (dev/test/prod)	dev
DB_HOST	PostgreSQL host	localhost
REDIS_HOST	Redis host	localhost
OPENAI_API_KEY	OpenAI API key	-
ANTHROPIC_API_KEY	Anthropic API key	-
DEFAULT_AI_PROVIDER	Default AI provider	openai

See .env.example for all options.

License

MIT