Connor Shorten

The codebase for the book "AI-Powered Search" (Manning Publications, 2025)

A curated list of all Henry AI Labs videos on Deep Learning and AI organized by category!

Personal educational journey.

Python code to study how HNSW works

This is the repo for the survey of LLM4IR.

Python SDK for Modaic

Extend the capabilities of your CrewAI agents with Tools

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Verdict is a library for scaling judge-time compute.

Minimal golang implementation of HNSW

MCP (Model Context Protocol) server for Weaviate Serverless using Weaviate Agents

A collection of MCP servers.

Content Links for AI Weekly Update Series on Henry AI Labs

Composio equip's your AI agents & LLMs with 100+ high-quality integrations via function calling

This tutorial covers how to deploy a FastAPI application to Kubernetes with Prometheus monitoring and Grafana dashboards.

No description provided.

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

A python native client for easy interaction with a Weaviate instance.

Letta (fka MemGPT) is a framework for creating stateful LLM services.

AdalFlow: The library to build & auto-optimize any LLM task.

An Awesome list of curated DSPy resources.

🤖 Build AI applications with confidence ✅ DSPy Visualizer ✅ Understand how your users are using your LLM-app ✅ Get a full picture of the quality performance of your LLM-app ✅ Collaborate with your stakeholders in ONE platform ✅ Iterate towards the most valuable & reliable LLM-app.

Implementing DCGANs to generate 45 x 45 x 3 images of Basketball Shoes. Keras code with Tensorflow Backend

AugmentationLab explores the role of Data Augmentation in Robustness, Class Imbalance, Distribution Shift and Generalization.

MATLAB project, transfer learning w/ alexnet + naive bayes classifier

Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.

Quick test with the natural questions dataset

Stanford DSPy: The framework for programming—not prompting—foundation models

Slides for ODSC talk - "Vector Search for Data Scientists"

Code to generate simulated ANN datasets