Session Content

• Quiz

• Homework presentation

• Short recap on intro to LLMs & prompt engineering

• Breakout session on prompt hubs

• Anatomy of an app

• Breakout session on project ideas

• Presentation of project ideas and default projects

• Homework for next week

Session Slides

Todo until next session

• Watch the short course "LangChain for LLM Application Development" (~1h 40min)

• If the videos "Question and Answer" and "Evaluation" are too confusing for you right now, as they introduce a lot of concepts in a short amount of time, you can skip these videos as this content will also be part of later sessions.

• Work through the Jupyter notebook "HomeworkLangChain" and complete the tasks at the bottom of the notebook.

"Colab Link HomeworkLangChain" (Copy the notebook to your Google Drive before working on it.)

today's schedule

• Quiz

• Short Recap

• Short presentation of current status

• Breakout Session ‘Next Steps’

• Homework for next week

resources

homework

• Take a look at this article: https://blog.n8n.io/open-source-llm/

• Take a look at some open-source / open-access LLM frameworks:

• • Ollama (Mac, Linux):

    • https://www.youtube.com/watch?v=Ox8hhpgrUi0

    • https://www.youtube.com/watch?v=k_1pOF1mj8k

  • LM Studio (Windows, Mac, Linux): - --https://medium.com/@genebernardin/running-llms-locally-using-lm-studio-38070f286413

  • GPT4All

• Test some open-source/open-access LLMs either locally downloaded or in HuggingFace spaces or any other test environment (e.g. HuggingChat, H2O.ai, etc.)

  • Do you see significant differences in the output of proprietary and open-source/open-access LLMs?

This sessions schedule

• Quiz

• Homework presentation

• Short Recap

• Projects

• Homework for next week

Ressources

Homework

1. Watch the course “”

2. Prepare a short presentation (max 5 min per group) with 2 parts:

• Present your project outline using the template (or improvise)

• Present a rough prototype (or mockup) using LangFlow

Use one of the available no-code tools (or, if you prefer, LangChain) to test the feasibility of your idea by creating a first small prototype.

Session content

• Getting to know each other

• What can you expect

• Requirements for credits

• Course outline

• Demos

• Breakout session

• Content and homework

Todo until next session

Watch and read the course content

• Register on learn.deeplearning.ai

• Watch "Language Models, the Chat Format and Tokens" (20 min)

• Watch the short course "ChatGPT Prompt Engineering for Developers" and work through the Jupyter notebooks (~1h 30min)

• Watch "Chain-of-Thought Reasoning" (10 min)

• Read "Contructing prompts" and "Prompt Engineering for Generative AI"

Tasks

1. Watch the provided videos and review the text to identify various tactics and techniques used in Prompt Engineering. List these tactics and techniques with clear examples.

2. Handling Ambiguity

   The word “Java” has at least three meanings (programming language, island in Indonesia, or coffee).

   Task:

   Try out the following prompt:

   Can you tell me about Java?

   Task:

   Suppose you are developing an app and do not know beforehand what your app's user means. Can you improve the prompt to help the model to clarify what the user represents and generate an answer?

3. Generate three potential course project ideas that you could work on. Be prepared to discuss these ideas in the next session. Feel free to consider alternative projects if needed.

4. Select one of the potential project ideas from Task 3 and create prompts for the language model to solve the problem. Use different prompting tactics and techniques to see which one produces the best results in addressing the chosen project idea.

Additional resources

• Slides of Session 1:

Readings on simple prompting techniques

• Instruction prompting

• Role prompting

• Priming prompt

• To be continued...

Sessions schedule

• Quiz

• Short Recap

• Impulses on Sparse Priming Representations (SPRs) and HyDE (Hypothetical Document Embeddings)

• Project Prototype Presentations

• Homework for next week

Resources

Homework for next week

• Watch the course “Building Generative AI Applications with Gradio”

• Install Gradio and explore the examples from the Gradio playground locally (https://www.gradio.app/playground)

• Think about the elements your application user interface should contain, create a sketch or wireframe of your app and implement it with Gradio

• (If possible connect your prototype to the user interface)

content

• Quiz

• Homework presentation

• short recab on LangChain

• overview of project ideas & pitches

• building project groups

this sessions presentation

homework

• Watch and work through the course “LangChain: Chat with your Data” on Deeplearning.AI

• Work through the tutorial HomeworkRAG, understand the code and do the tasks

today's topics

• Project Prototype Presentations

• Gradio

• Self-hosted models with LM Studio

• Breakout Session ‘Concrete Planning’

• Homework for next week

resources

homework

• Watch the videos “Evaluation Part I” and “Evaluation Part II” from the course “Building Systems with the ChatGPT API”

• Watch the video “Evaluation” from the course “LangChain for LLM Application Development”

Watch the video “Using LangChain Output Parsers to get what you want out of LLMs” from Sam Witteveen

today's schedule

• special guest: Jan Monika

• Tips 'n Tricks on Open Source LLMs

• Questions

• The Template for Code Submission

• Guidelines for the Final Presentation

Slides