Frequently Asked Questions (FAQ)¶

General¶

What is RAG Modulo?¶

RAG Modulo is a production-ready Retrieval-Augmented Generation platform that provides enterprise-grade document processing, intelligent search, and AI-powered question answering with advanced Chain of Thought (CoT) reasoning.

What LLM providers are supported?¶

WatsonX (IBM)
OpenAI
Anthropic

See API Documentation for configuration details.

What vector databases are supported?¶

Milvus (default)
Elasticsearch
Pinecone
Weaviate
ChromaDB

See Getting Started for setup instructions.

Installation & Setup¶

How do I install RAG Modulo?¶

See the Installation Guide for detailed instructions.

What are the system requirements?¶

Python 3.12+
Docker & Docker Compose
PostgreSQL
Vector database (Milvus recommended)

See Installation for full requirements.

How do I run locally without Docker?¶

Use the local development mode:

make local-dev-setup
make local-dev-infra
make local-dev-backend
make local-dev-frontend

See Development Workflow for details.

Usage¶

How do I upload documents?¶

Documents can be uploaded via: - Web interface (drag & drop) - CLI: rag-cli documents upload - REST API: POST /api/documents

See Getting Started.

What document formats are supported?¶

PDF
Word (DOCX)
Text (TXT, MD)
HTML
CSV/Excel (via IBM Docling)
Images (with OCR via Docling)

How does Chain of Thought reasoning work?¶

CoT reasoning breaks complex questions into smaller sub-questions, answers each step, and synthesizes a comprehensive final answer with source attribution.

See Chain of Thought Guide.

Development¶

How do I run tests?¶

make test-atomic      # Fast schema tests (~5 sec)
make test-unit-fast   # Unit tests (~30 sec)
make test-integration # Integration tests (~2 min)
make test-all         # All tests