Digestly

Mar 27, 2025

AI Dev 25 | Bilge Yücel: Building and Deploying Agentic Workflows with Haystack

DeepLearningAI - AI Dev 25 | Bilge Yücel: Building and Deploying Agentic Workflows with Haystack

The presentation introduces Haystack, an open-source LLM orchestration framework by Deepset, which helps Python developers build real-world agentic AI systems. Haystack's modular components and directed acyclic graph pipelines allow for flexible data flow and agent behavior. The speaker demonstrates building a GitHub issue resolver agent that reads issue comments, navigates the repository, and suggests solutions. This agent uses Haystack's components like GitHub issue viewer, repository viewer, and comment writer, integrated into a pipeline. The agent is deployed using Hay Hooks, which turns pipelines into REST APIs, simplifying deployment and integration with user interfaces. The speaker also introduces Deepset Studio, a visual development environment for Haystack, allowing users to create and deploy pipelines without extensive coding.

Key Points:

  • Haystack provides modular components and pipelines for building AI systems, offering flexibility and control over data flow.
  • The GitHub issue resolver agent uses Haystack components to read issues, navigate repositories, and suggest solutions.
  • Hay Hooks deploys Haystack pipelines as REST APIs, facilitating integration with user interfaces.
  • Deepset Studio allows visual pipeline creation and deployment, reducing the need for extensive coding.
  • The agent's effectiveness depends on repository size and complexity, suggesting modular approaches for large codebases.

Details:

1. 🎤 Introduction and Agenda

  • The session will focus on building and deploying agenting workflows using Haststack, providing a practical approach to enhancing development processes.
  • Vil, the speaker, is a Developer Relations Engineer at Deep, ensuring the session is led by someone with specialized knowledge and experience in the field.

2. 🧠 Understanding Agents and Haststack

  • Deepset is the developer of Haststack, an open-source LM orchestration framework designed to streamline the deployment and management of language models.
  • Haststack facilitates efficient orchestration, reducing the complexity of integrating multiple language models in applications.
  • The framework supports scalability and flexibility, enabling users to tailor deployments to specific needs.
  • Haststack's design emphasizes ease of use, allowing even those with limited technical expertise to effectively manage complex language model environments.
  • Key benefits include improved deployment speed and resource optimization, crucial for organizations leveraging AI in business operations.

3. 🔧 Building an Agent with Haststack

3.1. Introduction to Haststack and its Framework

3.2. Building an LLM Agent and Practical Application

4. 🚀 Live Demo: GitHub Issue Resolver Agent

4.1. Introduction and Setup

4.2. Components and Functionality

4.3. Pipeline Creation

4.4. Pipeline Execution

4.5. Testing and Improvements

4.6. Deployment using Hay Hooks

5. 🌐 Deployment and Further Exploration

5.1. Deployment Insights

5.2. Further Exploration

6. 🎵 Conclusion and Questions

  • Visit booth nine for more information.
  • Recap of key topics discussed: AI-driven customer segmentation, product development cycle optimization, and personalized engagement strategies.
  • Encouragement to implement actionable insights shared during the video for business growth.
View Full Content
Upgrade to Plus to unlock complete episodes, key insights, and in-depth analysis
Starting at $5/month. Cancel anytime.