production-agentic-rag-course
Learn to implement async Telegram bot operations with robust error handling using python-telegram-bot. Explore exception handling and lifecycle management.
Performance of Hybrid Search vs BM25‑only Search: Latency Benchmarks and Trade‑offsCompare hybrid search with BM25-only search. Discover latency benchmarks and trade-offs for production RAG systems. Optimize your semantic search performance.
How the ArXiv Client Handles Rate Limiting and Retries: A Production-Grade ImplementationDiscover how the ArXiv client manages rate limiting with a 3-second delay and implements linear back-off retries for robust PDF downloads. Learn about production-grade handling of API requests and network failures.
Best Practices for Deploying a RAG System with Docker Compose: Production-Ready PatternsDeploy a production-ready RAG system using Docker Compose. Learn best practices for loosely-coupled services, health checks, and environment configuration for seamless deployment.
How to Add a Custom Tool to a LangGraph Agent Workflow: Complete Implementation GuideLearn to add custom tools to your LangGraph agent workflow. This guide covers defining functions, registering them in ToolNode, and handling tool calls for seamless integration.
Data Flow from arXiv to OpenSearch Indexing: A Production RAG Pipeline Deep DiveUnderstand the data flow from arXiv to OpenSearch indexing in a production RAG pipeline. Learn about PDF parsing, chunking, embedding generation with Jina AI, and OpenSearch hybrid indexing.
How to Debug and Trace LangGraph Workflow Execution in Production RAG SystemsDebug and trace LangGraph workflow execution in production RAG systems. Visualize graphs, use Langfuse, inspect states, and leverage structured logging for seamless observability. Improve your AI agent performance.
Environment Variables Required for Each Service in the Production Agentic RAG CourseDiscover the essential environment variables needed for each service in the production Agentic RAG course. Learn how Pydantic settings manage your configurations effectively.
How to Configure an RRF Search Pipeline in OpenSearch for Hybrid SearchLearn to configure an RRF search pipeline in OpenSearch for hybrid search. Fuse BM25 and vector results effectively using the score ranker processor and the search pipeline API.
Streaming vs Non-Streaming RAG Response Modes: A Production Implementation GuideUnderstand streaming vs non-streaming RAG response modes for production. Learn how to implement RAG effectively with incremental text or complete JSON payloads for better user experiences.
How Document Grading Evaluates Semantic Relevance in Agentic RAGDiscover how document grading in agentic RAG uses structured LLM prompts for binary relevance scoring, optimizing your workflow for accurate answers or query refinement.
Guardrail Node Out-of-Domain Detection Mechanism in Production RAGLearn how the Guardrail node detects out-of-domain queries in production RAG. It uses an LLM to score relevance against a configurable threshold for AI research domain adherence.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →