AI APIs and Standalone AI Applications

Objective

The course is part of AI Tools and applications module

During this course you will learn:

- how to use APIs provided by major AI companies, such as OpenAI (ChatGPT and Dall-E 3) and integrate AI as part of your web site or other applications.
- how to use AI to automate tasks, including running programs on your computer. Learn how to utilize AI to scrape information from the web and social media sites.
- how to create your own custom bots and use AI APIs in a multimodal way e.g. combine text and image in creative ways.
- how to install and use AI tools on your local computer. NOTE: this will require quite powerful PC and preferably at least 8 Gigabytes on video memory (VRAM) and NVIDIA display adapter. The more VRAM, the better.

Content

Training your own AI models can be prohibitely expensive and time consuming. The use of AI APIs and existing open source LLMs and image generators (such as Stable Diffusion) are the most efficient ways to bring AI as part of your own tool chain and integrate as part your own applications.

The main objective is to find how to utilize existing AI APIs and how to install AI tools on your local computer or on the cloud. Lots of practical examples and services.

There will be several programming assignments and some of them might require the student to pay for the use of AI APIs.

Most programming will happen in Python, but other programming languages (such as JavaScript) might be used.

Many APIs will be pay to use, but the cost are likely to be moderate (e.g. with about 10 euros you can by enough credits for short experimentation). The student pays for the use of the APIs.

Disclaimer: This is rapidly changing field and the actual content can be subject to change.

Schedule

The schedule can be found from Moodle and calendar. Most likely just one 2x45 minute online session per week. All online sessions will be recorded and uploaded to YouTube,

Teaching methods

The aim is to learn how to build AI applications using existing AI APIs, libraries and standalone programs.

The course contains lots of practical examples and assignments, which harness the power of existing AI-related APIs. The students will also learn how to install and run open source large language models (LLMs) and image generators on their own computer.

We will also cover system prompting and students will build their own custom bots, which will be released in the Internet.

We will also cover topics, like retrieval augmented generation (RAG) and reading and generating popular formats, such as PDF,
Word, Excel, CSV and JSON related to use of AI.

Many of the APIs use require the student to purchase credits to services themselves.

DISCLAIMER: This is the pilot of this course, so not everything will be ready. You will however be well set to become one of the front-runners in the use AI in this country.

Learning material

Study materials and assignments are found from Moodle.

Cooperation with the business sector

-

Additional info

Giving Spark study feedback is possible no earlier than 7 days before the end date of the implementation plan and it continues 14 days after the end of the implementation. Study feedback can be found on the Pakki student's desktop, where a notification appears about the studies/modules you have registered for and feedback can be given. You will receive a reminder message in HAMK's e-mail about giving feedback on the day the implementation ends, if you have not already given feedback before then. You can get more information about study/module feedback from the student feedback page.

Evaluation criteria

1-5