All Things Open AI 2025
2025-03-17..2025-03-18
Durham, United States
who it's for
machine learning engineers, ai engineers, platform engineers, devops engineers, data engineers, engineering managers, product managers
topics
retrieval augmented generation with ChromaDB; vector databases and pgvector; knowledge graphs with Neo4j; local Llama model deployments; declarative ML orchestration with Flyte; fine-tuning with LoRA and QLoRA; Model Context Protocol and mCP servers; agentic workflows with LangChain and Bee; sentence-transformers embeddings; Docker containerized model serving; Kubernetes deployment and observability; tool calling and non-deterministic agents
| title | author | length |
|---|---|---|
| A Developer’s Adventures in AI Wonderland | Burr Sutter | 40m |
A demo built for enterprise shows a working mCP server integration that spins up a cheetah tracking Postgres schema, ingests messages through a Kafka-based… | ||
| Leveraging Knowledge Graphs for RAG: A Smarter Approach to Contextual AI Applications | David vonThenen | 38m |
Concrete claim: knowledge graphs cut hallucinations by scoping and returning the exact evidence used to answer queries. Demo uses Neo4j with named entity… | ||
| Unleashing the Power of Vector Databases for AI-Driven Applications | Venkat Venkatakrishnan | 36m |
Claims a vector database lets apps search by meaning not exact match and power RAG workflows; demonstrates ingesting a CSV into Chroma with a… | ||
| The Future is Non-Deterministic | Michael Donovan | 27m |
Claims that non‑deterministic problem solving is practical now through agentic workflows using tool calling and shows how that works end to end: a standard… | ||
| Rolling out Enterprise AI: Tools, Insights, & Team Empowerment | Calvin Hendryx-Parker | 40m |
Live demos show a working retrieval‑augmented system built with RAG with ChromaDB and PGVector, ingestion that OCRs conference images and enriches metadata via… | ||
| Fine-Tuning Large Language Models with Declarative ML Orchestration | Shivay Lamba | 33m |
Claims that declarative ML orchestration makes LLM fine-tuning practical for smaller teams by assigning resources per task and cutting cloud waste… | ||
| Building AI Agents and Assistants for DevOps Workflows | Lee Faus | 38m |
Shows an actual assistant integrated into continue.dev with Ollama, runs local models (Mistral, Granite), installs LangChain and edits files automatically… | ||
| DON’T PANIC: AI IS COMING – The Hitchhiker’s Guide to AI | Mark Hinkle | 08m |
Claims that AI need not be apocalyptic, backed by concrete community work: a meetup that grows to 2,000 members, training programs that have trained almost 800… | ||
| Open source GenAI vs. enterprise GenAI: Navigating the future of AI innovation | Ruth Akintunde | 11m |
Claims that a hybrid strategy wins: fine-tune open models for control while using enterprise services for scale, compliance, and uptime. Cites concrete… | ||
| Don't just talk to AI, do more with AI: how to improve productivity with AI agents | Sheng Liang | 16m |
Claims an open source system called obot plus a SaaS obot.ai actually wires LLMs to real apps: Outlook email integration, a small knowledge base of job… | ||
| The Death of the Browser | Rachel Nabors | 15m |
Claim: browsers become nostalgic within ten years as agents replace them. Concrete evidence: AgentQL demonstrates how to turn any web page into an API endpoint… | ||
| Artificial Intelligence Needs Community Intelligence | Sriram Raghavan | 15m |
Claims rapid open AI progress in two years and says open models and tooling are already usable not just vapor; names granite models released in families… | ||
| nothing matches | ||