introduction Azure OpenAI by Usama wahab khan

Usama wahab Khan
MVP,MCT, CTO @Evolution Technologies

Usama Wahab Khan
Father, data Scientist, Developer/Nerd, Traveler
Twitter : @usamawahabkhan
LinkedIn : Usamawahabkhan

What is generative AI
Generative AI models are a subset of deep
learning models that can produce new content
based on what is described in the input. The
OpenAI models are a collection of generative AI
models that can produce language, code, and
images.

Power your apps with large-scale AI models with Azure
take advantage of large-scale, generative AI models with deep understandings of language and code to
enable new reasoning and comprehension capabilities for building cutting-edge applications. Apply
these coding and language models to a variety of use cases, such as writing assistance, code generation,
and reasoning over data. Detect and mitigate harmful use with built-in responsible AI and access
enterprise-grade Azure security.
Custom AI models fine-tuned with your data and
hyperparameters
Built-in features to help ensure you’re using AI responsibly
Enterprise-grade security with role-based access control
(RBAC) and private networks
• ISO/IEC
• CSA/CCM
• ITAR
• CJIS
• HIPAA
• IRS 1075

Introduction to Azure OpenAI Service
Pre-trained generative AI models
Customization capabilities; the ability to fine-tune AI models
with your own data
Built-in tools to detect and mitigate harmful use cases so users
can implement AI responsibly
Enterprise-grade security with role-based access control (RBAC)
and private networks
Azure OpenAI Service provides REST API access to OpenAI's powerful language models
including the GPT-3, Codex and Embeddings model series.

Workload azure Open AI Support
Generating Natural Language
Text completion: generate and edit text
Embeddings: search, classify, and compare text
Generating Code: generate, edit, and explain code
Generating Images: generate and edit images

Examples AI
Q&A
Answer questions based on existing knowledge.
Grammar correction
Correct sentences into standard English.
Summarize for a 2nd grader
Translates difficult text into simpler concepts.
Natural language to OpenAI API
Create code to call the OpenAI API using a natural language instruction.
Text to command
Translate text into programmatic commands.
English to other languages
Translates English text into French, Spanish, and Japanese.
Natural language to Stripe API
Create code to call the Stripe API using natural language.
SQL translate
Translate natural language to SQL queries.
Parse unstructured data
Create tables from long-form text
Classification
Classify items into categories via example.

How to use
https://aka.ms/oaiapply

These OpenAI models fall into a few main families:

Models available
Codex
Embeddings
model series
the GPT-3
A series of models that can understand and generate natural
language. This includes the new ChatGPT model.
A series of models that can understand and generate code,
including translating natural language to code.
A set of models that can understand and use embeddings. An embedding is a
special format of data representation that can be easily utilized by machine learning
models and algorithms. The embedding is an information dense representation of the
semantic meaning of a piece of text. Currently, we offer three families of Embeddings
models for different functionalities: similarity, text search, and code search.

Understanding prompts, completions, and tokens
Prompt engineering

Like a person writing an essay, an AI
model takes a prompt and continues
writing based on the text in the prompt.
The new text that the model outputs is
called the completion. An example task
might be to write a Python program to add
two numbers. If you write out the task as a
Python comment like so:
Prompt engineering

def add(a, b):
return a + b
# Write a function that adds two numbers and returns the result.
t

# Load iris data from scikit-learn datasets and plot the training data.

Q & A
Usama Wahab Khan
Twitter : @usamawahabkhan
LinkedIn : Usamawahabkhan

introduction Azure OpenAI by Usama wahab khan

In this document