LAB331: Deep Research with LangChain and DeepSeek R1
Introduction
Welcome to Lab 331! In this hands-on workshop, you'll learn how Reasoning Models, like DeepSeek R1 work and how to use them for deep research.
What You'll Build
We'll walk through how to build a research assistant that can conduct comprehensive web research, analyze and synthesize information, and present it's findings.
The complete iterative deep research process includes:
- Query Generation: Query generation based on the users research topic input
- Web Search: Searching the web based on the generated query
- Summarization: Summarization of the web search results into a report
- Knowledge Gap Identification: Reflection on the summary and identification of specific knowledge gaps to fill
- Follow-up search cycles: Iterative search and reflection cycles based on identified gaps
- Final Report: Synthesis of all findings into a comprehensive report
What You'll Learn
This workshop has been built to teach you foundational concepts for using reasoning models. To view the full application code see the Deep Research Azure Sample. For a more in depth understanding of how reasoning models work read this article.
By the end of this workshop, you'll have learnt:
- What a reasoning model is and how to use DeepSeek R1
- How to use reasoning models with tools like Tavily web search for optimum search results
- What LangGraph is and how to implement reflection style archictecture with it
- How to use LangGraph to perform iterative research cycles to build comprehensive knowledge
- How to deploy the final application
Workshop Structure
The workshop is organized into four labs:
- Introduction to Reasoning Models
- Web Research Integration
- Research Reflection
- Launching Your Researcher
Getting Started
To begin the workshop, proceed to the Getting Started section to set up your environment and install the necessary dependencies.