HomeProjectsArticlesPK BoardAbout
Explore Projects

Production Agentic RAG Course

Normal
GitHub Python MIT

Description

A production-focused Agentic RAG course teaching how to build scalable, reliable RAG agent systems with indexing strategies, retrieval optimization, and monitoring.

Key Features

  • 7-week progressive course covering infrastructure to Agentic RAG
  • Production-grade hybrid search: BM25 keyword + vector semantic retrieval
  • LangGraph integration for intelligent decision-making and query rewriting
  • Production monitoring with Langfuse tracing and Redis caching
  • Telegram Bot integration for mobile conversational access
  • One-click deployment with Docker Compose

Use Cases

💡 Learn end-to-end production-grade RAG system development
💡 Build automated academic paper retrieval and Q&A assistants
💡 Master Agentic RAG with intelligent routing and adaptive retrieval
💡 Deploy reliable AI systems with monitoring and caching

Strengths & Limitations

✅ Strengths

  • • High community interest (8.3k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

rag production course agent scaling

Categories

📚 RAG Tools 📊 Observability

Quick Start

1. Clone the repository and navigate to the project directory
2. Copy `.env.example` to `.env` and configure API keys
3. Install dependencies: `uv sync`
4. Start services: `docker compose up --build -d`
5. Access `http://localhost:7861` for the Gradio interface
Visit GitHub

Related Projects

Ragas

15.3k · Python
Stale B

Ragas is a framework for evaluating RAG (Retrieval Augmented Generation) systems. It provides various evaluation metrics including faithfulness, answer relevance, context precision, helping developers optimize RAG application performance.

ragevaluationllm +1
  • · Objective evaluation metrics using both LLM-based and traditional approaches for precise LLM app assessment
  • · Automatic test data generation covering a wide range of scenarios for RAG systems
  • · Seamless integrations with LangChain, major observability tools, and popular LLM frameworks
View full details → View on GitHub

TruLens

3.5k · Python
Active A

TruLens is an open-source tool for evaluating and tracking LLM apps. It provides specialized evaluation for RAG applications including context relevance, groundedness, and answer relevance.

llmevaluationobservability +1
  • · OpenTelemetry-based tracing with structured OTEL spans
  • · 7 agentic evaluators: consistency, efficiency, plan adherence, quality, tool selection, tool calling, tool quality
  • · Batch and inline evaluation with configurable workers
View full details → View on GitHub