DSPy GEPA Example: Listwise Reranker

Weaviate vector database · Beginner ·🧠 Large Language Models ·10mo ago

Skills: Vector Stores80%Paper Reproduction60%

Key Takeaways

Trains a Listwise Reranker using DSPy's GEPA optimizer and Weaviate vector database

Original Description

Hey everyone! Thanks so much for watching this video exploring DSPy's GEPA optimizer to train a Listwise Reranker! Here is the link to the notebook from the video to follow along with: https://github.com/weaviate/recipes/blob/main/integrations/llm-agent-frameworks/dspy/GEPA-Hands-On-Reranker.ipynb Introduction to DSPy and Weaviate: https://www.youtube.com/watch?v=ickqCzFxWj0 Thanks so much for watching! ▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT WITH US ▬▬▬▬▬▬▬▬▬▬▬▬ • Visit weaviate.io • Star us on GitHub https://github.com/weaviate/weaviate • Stay updated and subscribe to our newsletter: https://newsletter.weaviate.io/ • Try out Weaviate Cloud Services for free here: https://console.weaviate.cloud/ Have questions? • Forum: https://forum.weaviate.io/ • Slack: https://weaviate.io/slack Connect with us on: • Twitter: https://twitter.com/weaviate_io • LinkedIn: https://www.linkedin.com/company/weaviate-io/ Chapters 0:00 GEPA! 4:40 Step 1: DSPy Program 7:45 Step 2: Load Dataset 11:45 Step 3: Metric with Feedback 13:00 Step 4: Run Unoptimized Eval 13:40 Step 5: GEPA Optimization 23:16 Step 6: Run Optimized Eval

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Vector Stores

View skill →

FULLY LOCAL Mistral AI PDF Processing [Hands-on Tutorial]

FULLY LOCAL Mistral AI PDF Processing [Hands-on Tutorial]

🚀 Deploy a PRIVATE Chroma Vector DB to AWS | Step by step 🚀

🚀 Deploy a PRIVATE Chroma Vector DB to AWS | Step by step 🚀

AI-Powered Resumes with Super People & Weaviate

AI-Powered Resumes with Super People & Weaviate

Weaviate vector database

Build Advanced Retrieval-Augmented Generation (RAG) with MongoDB Vector Search

Build Advanced Retrieval-Augmented Generation (RAG) with MongoDB Vector Search

Creating & Ingesting Your Own Embeddings in Weaviate | Vector Databases for Beginners | Part 7

Creating & Ingesting Your Own Embeddings in Weaviate | Vector Databases for Beginners | Part 7

Data Science Dojo

Configuring Vector Search in AlloyDB

Related Reads

Building an AI Study Buddy with Persistent Memory Using Cognee

Learn to build an AI study buddy with persistent memory using Cognee, enabling it to remember, recall, and improve knowledge over time.

WHAT AI ACTUALLY KNOWS: A Series Introduction

Understand the gap between AI's appearance and actual capabilities through 7 architectural properties

Prompting, RAG, Fine-Tuning, ICL

Identify the failing layer to fix AI failures, rather than switching techniques

Medium · Machine Learning

WHAT AI ACTUALLY KNOWS: A Series Introduction

Understand the gap between AI's appearance and actual capabilities through 7 architectural properties

Chapters (7)

GEPA!

4:40 Step 1: DSPy Program

7:45 Step 2: Load Dataset

11:45 Step 3: Metric with Feedback

13:00 Step 4: Run Unoptimized Eval

13:40 Step 5: GEPA Optimization

23:16 Step 6: Run Optimized Eval

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems

Dave Ebbelaar (LLM Eng)