Skip to content
ATTEND!
EXHIBIT

WORKSHOP

Building Production-Ready Knowledge Graphs: Hands-On Workshop with Neo4j, Graph RAG, and LangChain

Date: 06-Nov-2025 | Time: 11:30 - 02:00 PM

Venue: Workshop Room 2, NIMHANS Convention Centre, Bangalore

FEES:
• Rs.299 for Pro pass holders
• Rs2699 for Standard Pass holders
• Rs2999 for all others
(Limited seats available)

Book Your Seat

To empower participants with practical skills to build intelligent knowledge graph systems that transform unstructured documents into conversational AI applications. By the end of this workshop, participants will have hands-on experience creating complete Graph RAG implementations using Neo4j and LangChain, enabling them to solve complex data retrieval and analysis challenges in their organizations

Speaker /Instructor

Manjunath Janardhan

Principal AI Engineer, MSG Global Solutions

Who can attend this workshop?​
  • Software Developers and Engineers looking to implement advanced RAG systems
  • Data Scientists and ML Engineers wanting to enhance their retrieval architectures
  • AI/ML Practitioners seeking to move beyond traditional vector search approaches
  • Technical Architects designing knowledge management and document intelligence systems
  • Product Managers with technical backgrounds overseeing AI product development
  • Research Engineers working on information extraction and knowledge representation
  • Technical Consultants advising clients on AI and data strategy implementations
  • Note: Basic programming experience required; suitable for intermediate to advanced technical professionals
What all will be covered in the workshop?


Module 1: Foundation Setup 
1. Neo4j installation and database setup
2. Python environment configuration with LangChain dependencies
3. Workshop dataset overview and project architecture
4. Basic graph concepts and Cypher query introduction 

Module 2: Document Ingestion Pipeline
1. Document preprocessing and text extraction techniques
2. Entity recognition and relationship extraction methods
3. Building your first knowledge graph from documents
4. Data validation and quality assurance practices
5. Handling different document formats (PDF, Word, HTML)

Module 3: Advanced Graph Modeling
1. Designing optimal graph schemas for complex data
2. Implementing hierarchical and temporal relationships
3. Working with metadata and document provenance
4. Graph indexing strategies for performance optimization
5. Schema evolution and versioning best practices

Module 4: Graph RAG Implementation
1. Retrieval strategy design: traversal patterns and query optimization
2. LangChain integration with Neo4j for seamless data access
3. Building conversational interfaces for graph querying
4. Context-aware response generation using graph structure
5. Implementing hybrid search (graph + vector) approaches

Module 5: Chat Interface Development
1. Creating interactive chat applications with Streamlit/Gradio
2. Natural language to Cypher query translation
3. Response formatting and citation generation
4. Real-time query processing and caching strategies
5. User experience optimization for graph-based conversations

Module 6: Production Deployment
1. Error handling and system resilience patterns
2. Performance monitoring and query optimization
3. Scaling strategies for large knowledge graphs
4. Integration with existing data pipelines and APIs
5. Security considerations and access control implementation

Module 7: Testing and Evaluation
1. Comparing Graph RAG vs. traditional vector search results
2. Quality metrics for knowledge graph systems
3. Debugging common issues and troubleshooting techniques”

Prerequisites to attend the workshop

Technical Requirements:

1. Programming Experience: Intermediate Python skills (functions, classes, libraries)
2. Database Familiarity: Basic understanding of databases and query concepts
3. Command Line Comfort: Ability to navigate terminal/command prompt

Hardware/Software Requirements:

1. Laptop: Any laptop capable of running a web browser
2. Operating System: Any OS (Windows, macOS, Linux) – no specific requirements
3. Internet Connection: Stable connection for accessing cloud services and development environments
4. Web Browser: Modern browser (Chrome, Firefox, Safari, Edge) for accessing development tools

Cloud Development Environment.

1. GitHub Account: Free account required for accessing GitHub Codespaces
2. Neo4j AuraDB: We’ll use cloud instance (setup instructions provided during workshop)
3. GitHub Codespaces: Pre-configured development environment with all dependencies
4. No Local Installation Required: All tools and libraries accessible through browser

Recommended Background:

Basic understanding of natural language processing

Optional but Helpful:

1. Knowledge of retrieval-augmented generation (RAG) concepts
2. Familiarity with LangChain or similar LLM frameworks

Workshop Setup:

1. Pre-configured GitHub Codespaces environment with all required libraries
2. Neo4j AuraDB cloud instances provisioned for each participant
3. All sample datasets and starter code are available in the workshop repository

Note: For hands-on workshop, attendees should bring their own laptop with tools installed

Benefits/Takeaways of this workshop for the attendees (What will attendees do after attending the workshop which they were not able to do before attending this)

Technical Requirements:

  1. Programming Experience: Intermediate Python skills (functions, classes, libraries)
  2. Database Familiarity: Basic understanding of databases and query concepts
  3. Command Line Comfort: Ability to navigate terminal/command prompt

Hardware/Software Requirements:

  1. Laptop: Any laptop capable of running a web browser
  2. Operating System: Any OS (Windows, macOS, Linux) – no specific requirements
  3. Internet Connection: Stable connection for accessing cloud services and development environments
  4. Web Browser: Modern browser (Chrome, Firefox, Safari, Edge) for accessing development tools

Cloud Development Environment. 

  1. GitHub Account: Free account required for accessing GitHub Codespaces
  2. Neo4j AuraDB: We’ll use cloud instance (setup instructions provided during workshop)
  3. GitHub Codespaces: Pre-configured development environment with all dependencies
  4. No Local Installation Required: All tools and libraries accessible through browser

Recommended Background:

Basic understanding of natural language processing

Optional but Helpful:

  1. Knowledge of retrieval-augmented generation (RAG) concepts
  2. Familiarity with LangChain or similar LLM frameworks

Workshop Setup:

  1. Pre-configured GitHub Codespaces environment with all required libraries
  2. Neo4j AuraDB cloud instances provisioned for each participant
  3. All sample datasets and starter code are available in the workshop repository

1. Complete working knowledge graph system ready for production deployment
2. Proficiency in Neo4j database operations and Cypher query language
3. Advanced LangChain integration patterns for Graph RAG implementations
4. Document processing pipelines for automated knowledge extraction

Practical Assets:

1. Production-ready codebase with modular, reusable components
2. Deployment scripts and configuration templates
3. Performance optimization techniques and monitoring solutions
4. Integration patterns for existing enterprise systems

Strategic Knowledge:

1. Understanding when to choose Graph RAG over traditional vector approaches
2. Cost-benefit analysis framework for knowledge graph implementations
3. Architectural patterns for scalable document intelligence systems
4. Best practices for maintaining and evolving knowledge graphs

Professional Development:

1. Hands-on experience with cutting-edge AI retrieval technologies
2. Portfolio project demonstrating advanced RAG capabilities
3. Network connections with peers working on similar challenges
4. Continued learning resources and community access

Book Your Seat

About Speakers

Manjunath Janardhan is a seasoned Senior Software Engineer with over 20 years of experience transforming healthcare through innovative technology. A patented innovator and advocate of open-source AI, he specializes in developing accessible, scalable, and cost-effective solutions that drive real-world impact. At GE Healthcare, he leads efforts to design and deploy generative AI applications using open-source models, enhancing developer productivity and accelerating innovation across global teams in the US, China, and Japan.

Manjunath is deeply passionate about democratizing AI and has hands-on expertise with LLMs, LangChain, LlamaIndex, RAG frameworks, and agentic systems. He has spearheaded the creation of solutions such as MICT GPT, Code GPT, Service GPT, and a Unit Test Case Generator to optimize developer workflows. A strong communicator and mentor, he contributes actively to open-source communities and champions strategic technology adoption to advance healthcare innovation worldwide.