13:09

Building Better AI: Improving Safety and Reliability of LLM Applications

53:27

AI Agent Mastery: Is Your Agent Stuck in a Loop?

04:52

Which Eval Model should you use?

46:58

Exploring OpenAI's o1-preview and o1-mini

01:01:07

AI Agent Mastery: Evaluating Agents

04:17

Debug your AI with AI - Arize's AI Agent Search

01:00:53

AI Agent Mastery: Comparing Agent Frameworks

01:01:28

AI Agent Mastery: Agent Architectures

29:56

Breaking Down Reflection Tuning: Enhancing LLM Performance with Self-Learning

05:23

How to Trace a Groq Application in Phoenix

10:51

How To Set Up CrewAI Observability

15:40

Trace a Vercel AI powered Chat App

10:50

Build and Evaluate an Image Classifier

03:28

How Bazaarvoice Navigated the Challenges of Deploying an LLM App

09:03

Trace and Evaluate Haystack Pipelines with Phoenix

15:36

Prompt Optimization Using Datasets and Experiments

09:06

Phoenix: Use Annotations to collect Human Feedback from your LLM App

41:04

Community Paper Reading: Judging the Judges

02:05

How Atropos Health Accelerates Research with LLM Observability

51:26

AI with Assurance: Combining Guardrails and LLM Evaluations

04:27

How Flipkart Leverages Generative AI for 600 Million Users

14:59

LlamaIndex Workflows: Everything You Need To Get Started and Trace and Evaluate Your Agent

18:18

Embeddings (Vectors) Explained: The Core Concepts for Developers

05:18

Arize ML & LLM demo

47:29

Breaking Down Meta's Llama 3 Herd of Models

12:21

How To: Host Phoenix | Persistence

25:37

Automating Prompt Engineering with DSPy

12:57

Evaluating LLM Changes with Phoenix

02:21

How To Effectively Instrument Your LLM Application

29:09

How Microsoft Optimizes RAG and Agentic Workflows

15:10

Building and Deploying Cloud Native Gen AI Apps at Microsoft

25:53

Using the Microsoft Azure AI Model Catalog to Deploy the Right Model

32:10

Microsoft AutoGen: A Programming Framework for Agentic AI

05:26

Prompt Playground

10:56

How Naologic Built Multi-Agent RAG

28:27

NATO: Gen AI in the Defense Sector

29:34

How Fireworks AI Makes Open Models Faster

18:24

Cohere AI on Building Gen AI Models for Enterprise Use Cases

28:37

Building LLM Evals From Scratch

19:06

How Atropos Health Evaluates Automated Summaries for Medical Research

12:22

How Modelbit Runs a Two Tiered LLM System in Production

15:56

How Upstage AI Deploys Full Stack LLM for Enterprise

16:56

Mindsdb on Turning Demos into Robust AI Solutions

19:34

Yujian Tang on 1001 Ways to Build an LLM App

38:31

How to Efficiently Fine-Tune and Serve OSS LLMs

25:43

How PromptLayer Adapts LLM Evaluation Strategies

14:15

Lessons Learned from Building LLM Apps at Voiceflow

22:30

Evaluating and Tracing a Multi Modal RAG Application

14:00

MLOps for Generative AI: Lessons from Deploying Google Gemini Fine Tuned Models

07:55

Evaluating your RAG Pipeline in Real Time

17:34

Gorilla LLM: Teach LLMs to Use Tools at Scale

18:05

RAFT: Adapting Language Models To RAG

09:02

Custom AI Models Research at OpenAI

19:40

AGI House: Lessons from Hundreds of Launched AI Projects

30:24

Zapier Founder Mike Knoop on Automation to AGI

30:00

How To Build AI Knowledge Assistants with LlamaIndex

30:30

Arize:Observe 2024 Keynote: Introducing Arize Copilot and Hosted Phoenix

03:45

Enabling Ongoing LLM Evaluations

58:05

Phoenix 2.0 Launch Week Town Hall

35:35

Community Paper Reading: DSPy Assertions