← back
Forget RAG Pipelines—Build Production Ready Agents in 15 Mins: Nina Lopatina, Rajiv Shah, Contextual
Takeaway
Treat RAG like a managed service with modular components rather than hand-assembling extractor/embedder/reranker/vector-DB pipelines.
Summary
- Contextual.ai pitches RAG-as-managed-service: founders Douwe Kiela (original RAG paper) and Aman Verma make RAG modular so you can replace just extraction or reranker without rebuilding.
- Workshop walks through ingesting NVIDIA financial docs plus spurious-correlation data, then querying with quantitative reasoning over tables.
- Single API key handles ingestion, extraction, retrieval, reranking, and generation — explicitly contrasts with 'API scavenger hunts' of self-hosted stacks.
- Covers advanced settings (extraction tuning, reranking) and evaluation; integrates with Claude Desktop via MCP at the end.
- Targets enterprises hitting scale issues when their POC moves from 10 to thousands of diverse documents.
ragcontextual-aimanaged-service
Original description
Want to take advantage of your data, but don't want to reinvent RAG infrastructure? Join our workshop and see how you can deploy Agentic RAG in minutes using Contextual AI's managed RAG solution. We'll explore how Contextual handles intelligent parsing and chunking of your data, retrieves information with state of the art accuracy, and generates responses with a multi layered set of guardrails against hallucinations. Together, we'll build an end-to-end Agentic RAG pipeline and demonstrate its integration with Claude Desktop via MCP, so you can see how this could plug into your existing ecosystem. By the end of this session, you'll have a functioning Agentic RAG prototype that you can easily customize and deploy to production for your specific use cases, even with complex, unstructured documents. About Nina Lopatina Nina Lopatina is Lead Developer Advocate at Contextual AI, the fastest way for developers to build accurate, scalable RAG agents. She focuses on enabling developers to transform unstructured data into applications by connecting product, content, and community. Nina has worked as a developer and leader in the NLP and language for the last 7 years. She began her tech career after applying machine learning techniques to neural data throughout her PhD and postdoctoral research focused on reinforcement learning and decision-making. When she is not working, Nina is likely chasing fresh snow on the slopes or camping and hiking with her family. About Rajiv Shah Rajiv Shah is the Chief Evangelist at Contextual AI with a passion and expertise in Practical AI. He focuses on enabling enterprise teams to succeed with AI. Rajiv has worked on GTM teams at leading AI companies, including Hugging Face in open-source AI, Snorkel in data-centric AI, Snowflake in cloud computing, and DataRobot in AutoML. He started his career in data science at State Farm and Caterpillar. Rajiv is a widely recognized speaker on AI, published over 20 research papers, been cited over 1000 times, and received over 20 patents. He holds a PhD in Communications and a Juris Doctor from the University of Illinois at Urbana Champaign. You find him on social media with his short videos, @rajistics, that have received over ten million views. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter