AI-DRIVEN SOFTWARE DEVELOPMENT
WITH AZURE AI
Jörg Neumann
Slide 2
Slide 2 text
TOPICS
AI
Frontend Technologies
Mobile Development
Consulting, Coaching, Training
CONTACT
Mail: [email protected]
Twitter: @JoergNeumann
Web: www.neogeeks.de
JÖRG NEUMANN
Founder & CEO NeoGeeks GmbH
Azure OpenAI Service,
Azure Machine Learning Platform
Slide 3
Slide 3 text
AI-SCENARIOS
POPULAR CASES
Chat with own data
Customer support
Call centers
…
Slide 4
Slide 4 text
RETRIEVAL AUGMENTED GENERATION (RAG)
GOAL
Extend the model with external data sources
Integrate domain-specific knowledge
Model doesn’t need to be trained
Slide 5
Slide 5 text
RETRIEVAL AUGMENTED GENERATION
question
query own
data
add results to
the prompt
query model answer
PROMPT ENGINEERING
Answer the question based on the context provided below. If the question
cannot be answered with the provided information, respond with 'I don't know’.
context:
Large Language Models (LLMs) are the latest models used in NLP. Their superior
performance over smaller models has made them incredibly useful for
developers. These models can be accessed via the 'transformers' library by
Hugging Face, via OpenAI with the 'openai' library, and via Cohere with the
'cohere' library.
question:
Which libraries and model providers offer LLMs?“
instructions
prompt
external
information
Which libraries and model providers offer LLMs?
Slide 8
Slide 8 text
IMPLEMENTATION
CHALLENGES
Tables and illustrations in documents
Answers have no source citations
Answers can be outdated
The model can hallucinate
Limit context to specific data
Content filters
AI IN AZURE
AZURE OPENAI SERVICE
Models from OpenAI
Endpoint for API access
Available models depend on region
AZURE OPENAI STUDIO
Deployment and configuration
of the models
Slide 11
Slide 11 text
Documents
Table Storage
Blob Storage AI Search
OpenAI Service
Database Data
App
ARCHITECTURE
Slide 12
Slide 12 text
DEMO
Azure OpenAI Studio
Source: https://oai.azure.com
Slide 13
Slide 13 text
AI IN AZURE
AZURE AI STUDIO
Development of
complex AI solutions
Multi-Model Support
Prompt Flow
Debugging & Metrics
https://ai.azure.com
Slide 14
Slide 14 text
DEMO
Azure AI
Source: https://oai.azure.com
Slide 15
Slide 15 text
CONCLUSION
RAG is a complex pattern
Numerous frameworks and tools are required
Azure OpenAI and Azure AI Search offers an easy low-code solution for RAG scenarios
Complex scenarios can be implemented with Azure AI Studio