Real-Time RAG with Haystack 2.0 and Bytewax

​Come and learn the tools necessary to build efficient, real-time RAG pipelines with AIM community member Laura Funderburk!

Join in to gain the tools necessary to build efficient, real-time RAG pipelines. This event will cover the fundamentals of Retrieval Augmented Generation, data flow mechanics, and directed graphs (DGs), and will include code and material focused on implementing these concepts for real-time data processing and retrieval. Participants will gain a solid understanding of how RAG works as a powerful tool for AI applications, learn the intricacies of DG in processing architectures, and acquire practical skills in building real-time AI pipelines using Haystack and Bytewax. 

​Who Should Attend:

• ​AI and machine learning practitioners interested in advanced model architectures.

• ​Data engineers and architects looking for real-time data processing solutions with LLMs.

• ​Researchers and students in computational fields exploring cutting-edge AI technologies.

​Event Agenda:

• ​Understanding RAG (Retrieval-Augmented Generation)

  • ​Definition and significance in the AI landscape.

  • ​Use cases and benefits for enhancing model responses with external knowledge.

• ​Introduction to Data Flow and Directed Graphs (DGs) 

  • ​Basics of data flow in computing and its critical role in processing pipelines.

  • ​Introduction to DGs and their properties.

  • ​Examples of DGs in various data processing frameworks.

• ​RAG as a DG 

  • ​Explanation of how RAG can be conceptualized and implemented as a DG.

  • ​The interaction between retrieval and generation phases in a RAG model.

  • ​Visualization of RAG workflows as DGs.

• ​Building Real-Time RAG with Bytewax and Haystack

  • ​Introduction to Haystack and Bytewax.

  • ​Setting up RAG with Haystack.

  • ​Introduction to workers, state management and stream processing with Bytewax.

  • ​Mini example of real time RAG implementation.

  • ​Architectural Patterns for real-time RAG Implementations.

​Speaker Bio:

• ​ Laura Funderburk has a B.Sc. Mathematics from Simon Fraser University, and over three years of experience as a professional data scientist. Laura is enthusiastic about using open source for MLOps and DataOps and is passionate about outreach and education. In her day to day, Laura creates written content around building end to end scalable LLM pipelines with streaming data.

​
​Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.