Tweet
Tweet

Slide 1

Slide 1 text

Generative AI From Zero to Production: Build your own GenAI solution #WISSENTEILEN powered by Lars Röwekamp | Tim Wüllner | open knowledge GmbH Hands-on Workshop

Slide 2

Slide 2 text

(Architecture, Cloud, AI & ML) Lars Röwekamp @mobileLarson CIO New Technologies OPEN KNOWLEDGE

Slide 3

Slide 3 text

Tim Wüllner Machine Learning Engineer OPEN KNOWLEDGE

Slide 4

Slide 4 text

What‘s GenAI? How does „Generative AI“ actually work?

Slide 5

Slide 5 text

No content

Slide 6

Slide 6 text

Is this a cat? Neural Networks aka traditional AI Is this a cat?

Slide 7

Slide 7 text

This is not a cat fit Neural Network Cat Cat Cat Cat Dog Dog Neural Networks aka traditional AI This is a cat

Slide 8

Slide 8 text

infer trained Neural Network with pattern recognition for pictures of cats Neural Networks aka traditional AI Is this a cat?

Slide 9

Slide 9 text

Universal world knowledge Transformer Models aka generative AI Generative AI Model learn

Slide 10

Slide 10 text

Generative AI Model Prompting What is a cat? A cat is* … and looks like this. *based on my world knowledge Transformer Models aka generative AI

Slide 11

Slide 11 text

Generative AI vs traditional Neural Networks Predictive ML Model Generative Model learns / recognises relationships between data and label learns / understands connections in unstructured data Label new Content Label Data unstructured Data

Slide 12

Slide 12 text

Generative AI under the Hood Large Language Model Mary had a … Large Language Model Mary had a little … Next Token red little delicious … Probability 0.2 0.4 0.1 … Next Token mouse lamb kettle … Probability 0.2 0.3 0.2 …

Slide 13

Slide 13 text

Source: http://vectors.nlpl.eu/explore/embeddings/en/MOD_enwiki_upos_skipgram_300_2_2021/cat_NOUN/ Generative AI under the Hood

Slide 14

Slide 14 text

1. queen – woman + man = king 2. doctor – man + woman = nurse Male-Female Verb Tense Country-Capital Generative AI under the Hood

Slide 15

Slide 15 text

Transformer (LLM Layer) John wants his bank to cash the … ? word2vec style Vectors Generative AI under the Hood

Slide 16

Slide 16 text

Transformer (LLM Layer) John wants his bank to cash the … ? John wants his bank to cash the … ? (verb) (verb) word2vec style Vectors context aka hidden state Generative AI under the Hood

Slide 17

Slide 17 text

Transformer (LLM Layer) John wants his bank to cash the … ? John wants his bank to cash the … ? (verb) (verb) word2vec style Vectors context aka hidden state Key-Vector: btw I‘am a noun describing a male person. Query-Vector: btw I‘am seeking for a noun describing a male person. Generative AI under the Hood

Slide 18

Slide 18 text

Transformer (LLM Layer) John wants his bank to cash the … ? word2vec style Vectors Transformer (LLM Layer) context aka hidden state John wants his bank to cash the … ? (verb) (verb) (John‘s) (finance) John wants his bank to cash the … ? (verb) (verb) (male) ( ... ) Generative AI under the Hood

Slide 19

Slide 19 text

Transformer (LLM Layer) John wants his bank to cash the … ? word2vec style Vectors John (main character, male, married to Cheryl, cousin of Donald, from Minnesota, currently in Boise, … ) wants his bank to cash the … ? Generative AI under the Hood

Slide 20

Slide 20 text

Transformer (LLM Layer) John wants his bank to cash the … ? word2vec style Vectors Transformer (LLM Layer) context aka hidden state John wants his bank to cash the … (verb) (verb) (John‘s) (finance) John wants his bank to cash the … ? (verb) (verb) (male) Enough context information to be able to „guess“ the next word. ( ... ) Generative AI under the Hood check

Slide 21

Slide 21 text

Generative AI under the Hood Large Language Model Mary had a … Large Language Model Mary had a little … Next Token red little delicious … Probability 0.2 0.4 0.1 … Next Token mouse lamb kettle … Probability 0.2 0.3 0.2 …

Slide 22

Slide 22 text

GenAI by Example? Where can I realistically use GenAI - and where not?

Slide 23

Slide 23 text

Generative AI by Example

Slide 24

Slide 24 text

Generative AI by Example Health Care Enhancing medical images Discovering new drugs* Simplifying medical tasks Persionalized treatment *via Generative Design

Slide 25

Slide 25 text

Generative AI by Example Advertising & Marketing Generate marketing content Personalized recommendations Create product descriptions Enhance SEO

Slide 26

Slide 26 text

Generative AI by Example Manufactoring Accelerate design process Provide smart maintenance Improve supply chain

Slide 27

Slide 27 text

Generative AI by Example Media & Entertainment Create audio & video content Generate highlights for events Manage tags for better CM

Slide 28

Slide 28 text

Generative AI by Example Financial Services Create investment strategies Communicate & educate clients Quickly draft information Monitor regulatory activities

Slide 29

Slide 29 text

Generative AI by Example Software Development Generate code Automate testing Translate prog. Language Explain software soultions

Slide 30

Slide 30 text

GenAI by Example „Know Your Business!“ *if you want to succeed in the end.

Slide 31

Slide 31 text

GenAI Basics How to build a first, simple GenAI system?

Slide 32

Slide 32 text

GenAI- Model Prompt „What is the most beautiful holiday destination?“ GenAI Basics

Slide 33

Slide 33 text

GenAI- Model Prompt GenAI Basics Model Selection Prompt Engineering 2 1 „What is the most beautiful holiday destination?“

Slide 34

Slide 34 text

GenAI Hands-on „Hello IPYNB*, hello GenAI“ *IPython Notebook aka Jupyter Notebook

Slide 35

Slide 35 text

GenAI Hands-on What are you going to learn during this lesson: • Create your first Jupyter Notebook in Google Colab cloud environment. • Access a GenAI model with customised prompts via provider-specific API.

Slide 36

Slide 36 text

Hands-on Hello Jupyter Notebook https://colab.research.google.com/

Slide 37

Slide 37 text

Hands-on Hello Jupyter Notebook https://github.com/openknowledge/workshop-genai-student

Slide 38

Slide 38 text

Hands-on Hello GenAI World

Slide 39

Slide 39 text

GenAI explained MODELS

Slide 40

Slide 40 text

GenAI- Model Prompt GenAI Basics Model Selection Prompt Engineering 2 Model Selection 1 Which MODEL? Which PARAMETERS? Which INFRASTRUCTURE? Which LICENCE? Which COST MODEL? Which GOVERNANCE? „What is the most beautiful holiday destination?“

Slide 41

Slide 41 text

GenAI Basics Model Selection aka „How do I find the right model?“

Slide 42

Slide 42 text

Source: https://lifearchitect.ai/ look for „LLM Billboard Charts“

Slide 43

Slide 43 text

GenAI Basics Model Selection „ What does an AI benchmark measure?“ • General Kowledge • Programming • Mathematics • ... Official benchmarks ars often part of the training data! • Creativity • Factual Knowledge • Logic Thinking

Slide 44

Slide 44 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ • for my PROBLEM • for my DATA • for my CONTEXT • for my BUDGET

Slide 45

Slide 45 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ Public, Private, Sizes, Purpose Availability

Slide 46

Slide 46 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ Public, Private, Sizes, Purpose Data Privacy, Security, Explainability Availability Governance

Slide 47

Slide 47 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ Public, Private, Sizes, Purpose Data Privacy, Security, Explainability Complexity, Business Area Availability Governance Use Case

Slide 48

Slide 48 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ Public, Private, Sizes, Purpose Data Privacy, Security, Explainability Complexity, Business Area Latency, Cost, Customizeability Availability Governance Use Case Performance

Slide 49

Slide 49 text

GenAI Basics Model Selection aka „How do I find the right model for me?“ Public, Private, Sizes, Purpose Data Privacy, Security, Explainability Complexity, Business Area Latency, Cost, Customizeability Traininig, Runtime, Availability Team Skills, Computational Power Availability Governance Use Case Performance Data Resources „Know Your Use-Case!“ *if you want to be successful.

Slide 50

Slide 50 text

GenAI- Model Prompt GenAI Basics Model Integration Prompt Engineering 2 Model Selection 1 Suitable model found: But how do I address it from my application? „What is the most beautiful holiday destination?“

Slide 51

Slide 51 text

Model A-small Model Provider model-name model-parameter provider-parameter prompt Model A-big Model B e.g. openAI, Google, … Provider Client API GenAI Basics Model Integration „What is the most beautiful holiday destination?“ Reminder: 00-hello-genai.ipynb

Slide 52

Slide 52 text

Model X mini Model Provider II model-name model-parameter provider-parameter prompt Model Y Model Y ++ e.g. openAI, Google, … Provider Client API GenAI Basics Model Integration „What is the most beautiful holiday destination?“

Slide 53

Slide 53 text

Model X mini Model Provider II Provider II Client API model-name model-parameter provider-parameter prompt Model Y Model Y ++ e.g. openAI, Google, … GenAI Basics Model Integration „What is the most beautiful holiday destination?“

Slide 54

Slide 54 text

Hub-Provider Client API model-name model-parameter hub-provider-parameter prompt e.g. Hugging-Face Provider-II hosted Models Provider-I hosted Models Hub-hosted Models* Hub-Provider Dispatcher *Provider X, fine-tuned or adapted, own GenAI Basics Model Integration „What is the most beautiful holiday destination?“ Cloud based Resources

Slide 55

Slide 55 text

Hub-Provider Client API model-name model-parameter hub-provider-parameter prompt e.g. Hugging-Face Provider-II hosted Models Provider-I hosted Models Hub-hosted Models* Hub-Provider Dispatcher *Provider X, fine-tuned or adapted, own GenAI Basics Model Integration „What is the most beautiful holiday destination?“ cloud-not-allowed exception

Slide 56

Slide 56 text

Local-Hub Provider Client API model-name model-parameter hub-provider-parameter prompt e.g. GPT4all, ollama Local hosted Models (Provider III) Local hosted Models (Provider II) Local hosted Models (own or adaptedI) Local-Hub Provider Dispatcher Local Machine GenAI Basics Model Integration „What is the most beautiful holiday destination?“

Slide 57

Slide 57 text

GenAI Basics Model Adaption „ What additional levers do I have?“ • Temperature degree of ‘fantasy‘ • Max Tokens length of answer • Top K selection of hits from the top K hits • Top P selection of hits from the top P per cent • Presence Penalty avoid repetition • Frequence Penalty avoid repetition (weighted edition)

Slide 58

Slide 58 text

GenAI Basics Model Selection Source: https://promptengineering.org/prompt-engineering-with-temperature-and-top-p/

Slide 59

Slide 59 text

Hands-on GenAI Models

Slide 60

Slide 60 text

Source: https://lifearchitect.ai/ look for „Models Table“

Slide 61

Slide 61 text

GenAI explained PROMPTING

Slide 62

Slide 62 text

GenAI- Model Prompt Model Selection Prompt Engineering 2 1 GenAI Basics Prompt Engineering „What is the most beautiful holiday destination?“

Slide 63

Slide 63 text

GenAI- Model Prompt Model Selection Prompt Engineering 2 1 Parts of a Prompt System vs User Prompt Principles of Prompting Chain-of-Thought Prompts Few-Shot Learning GenAI Basics Prompt Engineering „What is the most beautiful holiday destination?“

Slide 64

Slide 64 text

GenAI Basics Prompt Engineering Role Instruction Example 1 Context Example n Question Who am I? What is my intention? What are helpful examples? Are there any additional information? BTW: what is the task I ask for? What should a good prompt should look like?

Slide 65

Slide 65 text

GenAI Basics Prompt Engineering Role Instruction Example 1 Context Example n Question What is your role as an assistant? What is my intention? What are helpful examples? Are there any additional information? BTW: what is the task I ask for? What should a good prompt should look like?

Slide 66

Slide 66 text

GenAI Basics Good Prompt vs. Bad Prompt You I want to cook something. LR Topic: Recipe Recommendations

Slide 67

Slide 67 text

GenAI Basics Good Prompt vs. Bad Prompt You I want to cook something. LR You Acting as an expert home cook, for someone who enjoys vegetarian Italian food and has only 30 minutes to prepare dinner, could you recommend a recipe including a list of ingredients and step-by- step instructions? LR Output Example Context Question Role Acting as an expert home cook, for someone who enjoys vegetarian Italian food and has only 30 minutes to prepare dinner, could you recommend a recipe including a list of ingredients and step-by-step instructions? You could point at recipes you like from the BBC’s Good Food guide, providing URL’s to recipes you love. Topic: Recipe Recommendations

Slide 68

Slide 68 text

GenAI Basics Good Prompt vs. Bad Prompt You I want to learn something new. LR You Acting as a coding instructor, for a beginner with a goal to learn Python within 4 weeks, please provide a learning plan including resources and a weekly schedule for 10 hours per week. LR Output Example Context Question Role Acting as a coding instructor, for a beginner with a goal to learn Python within 4 weeks, Please provide a learning plan, including resources and a weekly schedule for 10 hours per week Point it at courses you’ve done in the past that you’ve liked. Tell it you like to learn by reading books, or websites, or by watching videos, or a mixture of both. Topic: Learning new skills

Slide 69

Slide 69 text

GenAI Basics System Prompt vs. User Prompt System Assistant User „You“ Chat-Model Behaviour of Assistant

Slide 70

Slide 70 text

GenAI Basics System Prompt vs. User Prompt System Assistant User ‘You're a friendly assistant.’ „You“ Chat-Model Behaviour of Assistant

Slide 71

Slide 71 text

GenAI Basics System Prompt vs. User Prompt System Assistant User ‘You're a friendly assistant and always keep things brief.’ ‚Which is the most beautiful city in the world?‘ ‚Which is the most beautiful city in the world?‘ ‘You are a philosopher and have a tendency to be verbose.’ ??? ??? „You“ Chat-Model Behaviour of Assistant

Slide 72

Slide 72 text

GenAI Basics System Prompt vs. User Prompt System-Prompt: ‘You're a friendly assistant and always keep things brief.’ Assistant: 65 Tokens

Slide 73

Slide 73 text

GenAI Basics System Prompt vs. User Prompt System-Prompt: ‘You are a philosopher and have a tendency to be verbose.’ Assistant: 434 Tokens

Slide 74

Slide 74 text

GenAI Basics System Prompt vs. User Prompt System-Prompt: Default GPT-4o Assistant: 296 Tokens

Slide 75

Slide 75 text

GenAI Basics Prompt Engineering Looking for inspiration? Go to https://github.com/mustvlad/ChatGPT-System-Prompts

Slide 76

Slide 76 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR Prompt Engineering Principles Source: Prompt Engineering for Generative AI, James Phoenix & Mike Taylor, O‘Reilly 2024

Slide 77

Slide 77 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR 1. Give Direction Describe the desired style in detail, or reference a relevant persona.

Slide 78

Slide 78 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR 1. Give Direction Describe the desired style in detail, or reference a relevant persona. 2. Specify Format Define the rules to follow, and the required structure to respond.

Slide 79

Slide 79 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR 1. Give Direction Describe the desired style in detail, or reference a relevant persona. 2. Specify Format Define the rules to follow, and the required structure to respond. 3. Provide Examples Insert a deverse set if test cases where the task was done correctly.

Slide 80

Slide 80 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR 1. Give Direction Describe the desired style in detail, or reference a relevant persona. 2. Specify Format Define the rules to follow, and the required structure to respond. 3. Provide Examples Insert a deverse set if test cases where the task was done correctly. 4. Evaluate Quality Identify errors and rate responses, Testing what drives performance.

Slide 81

Slide 81 text

GenAI Basics Prompt Engineering You Brainstorm a list of product names for a shoe that fits any foot size, in the style of Steve Jobs. Return the result as a comma separated list, in this format: Product description: A shoe that fits any foot size Product name: [list of 3 names] ## Examples Product description: A refrigerator that dispenses beer Product names: iBarFridge, iFridgeBeer, iDrinkBeerFridge Product description: A watch that can tell accurate time in space Product names: iNaut, iSpace, iTime ChatGPT Product description: A shoe that fits any foot size Product names: iFitFoot, iPerfectFit, iShoeSize <10/10> LR 1. Give Direction Describe the desired style in detail, or reference a relevant persona. 2. Specify Format Define the rules to follow, and the required structure to respond. 3. Provide Examples Insert a deverse set if test cases where the task was done correctly. 4. Evaluate Quality Identify errors and rate responses, Testing what drives performance. You Please rate the product names based on their catchines, uniqueness, simplicity. Rate them on a scale from 1 to 5, with being 5 the highest score. Respond only with a table containing the results. LR ChatGPT Product Name Catchiness Uniqueness Simplicity iFitFoot 4 4 4 iPerfectFit 5 4 3 iShoeSize 3 3 5 5. Devide Labor Split the task into multiple steps, chained together for complex goals.

Slide 82

Slide 82 text

GenAI Basics Prompt Engineering You Question: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have? Answer: The answer is 11. Question: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have? ChatGPT The answer is 27. [NOT CORRECT] LR Chain of Thoughts Pattern

Slide 83

Slide 83 text

GenAI Basics Prompt Engineering You Question: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have? Answer: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11. Question: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have? ChatGPT A cafeteria had 23 apples originally. They used 20 to make lunch. So they had 23 - 20 = 3. They bought 6 more apples, so they have 3 + 6 = 9. The answer is 9. [CORRECT] LR ‘Instead of directly asking the language model to solve the problem, we use a chain of thought as a prompt to guide the model through intermediate steps.’

Slide 84

Slide 84 text

GenAI Basics Prompt Engineering LR Source: https://promptengineering.org/master-prompting-concepts-chain-of-thought-prompting/

Slide 85

Slide 85 text

GenAI Basics Prompt Engineering You Please choose the best explanation to the question: Question: How is snow formed? Explanation1: Snow is formed when water vapor in the air freezes into ice crystals in the atmosphere, which can combine and grow into snowflakes as they fall through the atmosphere and accumulate on the ground. Explanation2: Water vapor freezes into ice crystals forming snow. Answer: ChatGPT Explanation 1 is the better explanation. It provides a more detailed and complete description of the process. It explains that water vapor freezes into ice crystals in the atmosphere and how these crystals can combine to form snowflakes as they fall through the air before accumulating on the ground. This explanation gives a clearer understanding of the formation process of snow compared to the shorter Explanation 2. LR Few-Shot Learning Pattern ???

Slide 86

Slide 86 text

GenAI Basics Prompt Engineering You Please choose the best explanation to the question: Question: Why is sky blue? Explanation1: The sky appears blue because of Rayleigh scattering, … making the sky look blue. Explanation2: Due to Rayleigh scattering effect. Answer: Explanation2 Question: What is the cause of earthquakes? Explanation1: Sudden release of energy in the Earth's crust. Explanation2: Earthquakes happen when tectonic plates suddenly slip or break apart, …. cause damage. Answer: Explanation1 Question: How is snow formed? Explanation1: Snow is formed when water vapor in the air freezes into ice crystals in the atmosphere, … on the ground. Explanation2: Water vapor freezes into ice crystals forming snow. Answer: ChatGPT Explanation 2. LR ‘Instead of feeding a model with lots and lots of data, we give it a few examples for orientation.’ Beispiel 2 Beispiel 1 ???

Slide 87

Slide 87 text

GenAI Basics Prompt Injection https://gandalf.lakera.ai/

Slide 88

Slide 88 text

GenAI Hands-on „Prompting & Models“

Slide 89

Slide 89 text

GenAI Hands-on What are you going to learn during this lesson: • Promp with a dedicated system prompt. • Apply prompting patterns and best practives. • control genAI completion via model parameters.

Slide 90

Slide 90 text

Hands-on Prompting & Models

Slide 91

Slide 91 text

GenAI explained myDOMAIN

Slide 92

Slide 92 text

GenAI- Model Prompt GenAI Basics myDomain „What is the most beautiful holiday destination?“

Slide 93

Slide 93 text

GenAI- Model Prompt GenAI Basics myDomain „How to apply for vacation at open knowledge?“

Slide 94

Slide 94 text

GenAI- Model Prompt GenAI Basics myDomain + „Leave regulation at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 95

Slide 95 text

GenAI Hands-on „Augmention“

Slide 96

Slide 96 text

Hands-on Augmention

Slide 97

Slide 97 text

Hands-on Augmention

Slide 98

Slide 98 text

Hands-on Augmention

Slide 99

Slide 99 text

Hands-on Augmention

Slide 100

Slide 100 text

Hands-on Augmention

Slide 101

Slide 101 text

Hands-on GenAI meets Augmention

Slide 102

Slide 102 text

GenAI- Model Prompt GenAI Basics myDomain + „Leave regulation at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 103

Slide 103 text

GenAI- Model Prompt GenAI Basics myDomain + „Leave regulation at open knowledge“ „How to activate the alarm system at open knowledge?“

Slide 104

Slide 104 text

GenAI- Model Prompt GenAI Basics myDomain + + „How to activate the alarm system at open knowledge?“ „Leave regulation + Alarm system usage at open knowledge“

Slide 105

Slide 105 text

GenAI- Model Prompt GenAI Basics myDomain + „All internal knowledge (Wiki, DB, …) at open knowledge“ „How to activate the alarm system at open knowledge?“

Slide 106

Slide 106 text

GenAI- Model Prompt GenAI Basics myDomain + ERROR: Token Limit exceeded Output Size Context Window Size „How to activate the alarm system at open knowledge?“ „All internal knowledge at open knowledge“

Slide 107

Slide 107 text

GenAI- Model Prompt GenAI Basics myDomain + ERROR: Out-of-Budget Exception Context Window Size „All internal knowledge at open knowledge“ „How to activate the alarm system at open knowledge?“

Slide 108

Slide 108 text

GenAI- Model Prompt GenAI Basics myDomain + ERROR: Lost-in-the-Middle Context Window Size „All internal knowledge at open knowledge“ „How to activate the alarm system at open knowledge?“

Slide 109

Slide 109 text

GenAI Basics myDomain „What are Token Limits?“ • Context Window Size • Output Size • long Questions are expensive • long Answers are even more expensive

Slide 110

Slide 110 text

Source: GenAI Pricing on Medium.com, Ragesh Gohel, March 2024

Slide 111

Slide 111 text

Source: GenAI Pricing on Medium.com, Ragesh Gohel, March 2024 128.000 Tokens? Sounds good! But usually is too little for myDomain! 128.000 tokens correspond to approx. 350 book pages Harry Potter has > 1 Mio. words on over 6.000 Pages!

Slide 112

Slide 112 text

GenAI Advanced How can I contribute and query my own domain knowledge?

Slide 113

Slide 113 text

GenAI- Model Prompt GenAI Advanced myDomain + ERROR: Token Limit exceeded! Output Size Context Window Size „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 114

Slide 114 text

myGenAI Model Prompt GenAI Advanced myDomain „All internal knowledge at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 115

Slide 115 text

myGenAI Model Prompt GenAI Advanced myDomain Option 1: Build own Model Option 2: Fine-tune existing Model ERROR: Way to expensive ERROR: Way to complex WARNING: Out-of-Sync „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 116

Slide 116 text

Prompt GenAI Advanced myDomain „Prompt Enrichment“ „Model Enrichment“ myGenAI Model + „How to apply for vacation at open knowledge?“

Slide 117

Slide 117 text

Prompt GenAI Advanced myDomain GenAI- Model SOME MAGIC „MAGIC Enrichment“ „How to apply for vacation at open knowledge?“

Slide 118

Slide 118 text

Prompt GenAI- Model GenAI Advanced myDomain SOME MAGIC „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 119

Slide 119 text

Prompt Retrieve Augment Ingesting- Pipeline Knowledge Database Retriever GenAI- Model GenAI Advanced myDomain „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 120

Slide 120 text

„How to apply for vacation at open knowledge?“ Prompt Ingesting- Pipeline Knowledge Database Retriever GenAI Advanced myDomain R etrieval Augmented Generation „All internal knowledge at open knowledge“

Slide 121

Slide 121 text

GenAI explained RAG Systems

Slide 122

Slide 122 text

„How to apply for vacation at open knowledge?“ Prompt Ingesting- Pipeline Knowledge Database Retriever GenAI Advanced RAG Systems R etrieval Augmented Generation „All internal knowledge at open knowledge“

Slide 123

Slide 123 text

Prompt Ingesting- Pipeline Knowledge Database Retriever GenAI Advanced RAG Systems R etrieval Augmented Generation „All internal knowledge at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 124

Slide 124 text

GenAI Advanced RAG Systems GenAI Model Ingesting-Pipeline (Async.) Retriever Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting UI/UX „How to apply for vacation at open knowledge?“

Slide 125

Slide 125 text

„It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype. The added value of this technology is too great and its use in the form of a chat is too intuitive. In 2024, it was expected that the leap from exploratory playing around with large language models [...].“ Document (Doc. Id:1) Chunking Embedding Ingesting Pipeline by Example

Slide 126

Slide 126 text

[„ It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype.“] [„ The added value of this technology is too great and its use in the form of a chat is too intuitive.“] Document (Doc. Id:1) Chunking Embedding Ingesting Pipeline by Example „It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype. The added value of this technology is too great and its use in the form of a chat is too intuitive. In 2024, it was expected that the leap from exploratory playing around with large language models [...].“ [ … ]

Slide 127

Slide 127 text

Chunking Embedding [-0.24, 0.15, …, 0.52] [-0.13, 0.95, …, 0.31] […] Ingesting Pipeline by Example [„ It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype.“] [„ The added value of this technology is too great and its use in the form of a chat is too intuitive.“] Document (Doc. Id:1) „It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype. The added value of this technology is too great and its use in the form of a chat is too intuitive. In 2024, it was expected that the leap from exploratory playing around with large language models [...].“ [ … ]

Slide 128

Slide 128 text

Id Doc. Id Embedding 1 1 [-0.24, 0.15, …, 0.52] 2 1 [-0.13, 0.95, …, 0.31] […] […] […] Chunking Embedding [-0.24, 0.15, …, 0.52] [-0.13, 0.95, …, 0.31] […] Ingesting Pipeline by Example [„ It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype.“] [„ The added value of this technology is too great and its use in the form of a chat is too intuitive.“] Document (Doc. Id:1) „It will soon be the second anniversary of the release of ChatGPT. There is still no end in sight to the hype. The added value of this technology is too great and its use in the form of a chat is too intuitive. In 2024, it was expected that the leap from exploratory playing around with large language models [...].“ [ … ]

Slide 129

Slide 129 text

Retrieval Pipeline by Example Embedding Top-k Fetching Augmenting ‘What is the lecture ‘The architecture for language models in practice - Retrieval Augmented Generation’ about?’

Slide 130

Slide 130 text

Retrieval Pipeline by Example Embedding Top-k Fetching Augmenting [0.35, 0.25, …, 0.62] ‘What is the lecture ‘The architecture for language models in practice - Retrieval Augmented Generation’ about?’

Slide 131

Slide 131 text

Retrieval Pipeline by Example Embedding Top-k Fetching Augmenting Embeddings from knowledge base Embeddings Dimension 1 Embed. Dim. 2 Top-k=1 document(s) [0.35, 0.25, …, 0.62] ‘What is the lecture ‘The architecture for language models in practice - Retrieval Augmented Generation’ about?’

Slide 132

Slide 132 text

Retrieval Pipeline by Example Embedding Top-k Fetching Augmenting Embeddings from knowledge base Embeddings Dimension 1 Embed. Dim. 2 Top-k=1 document(s) [0.35, 0.25, …, 0.62] & „ What is the lecture […] based on the following context: ‘An upstream retrieval process to pull in relevant information from our own dynamic database can provide well-founded answers.’ ‘What is the lecture ‘The architecture for language models in practice - Retrieval Augmented Generation’ about?’

Slide 133

Slide 133 text

Sherlock RAG in Action

Slide 134

Slide 134 text

No content

Slide 135

Slide 135 text

No content

Slide 136

Slide 136 text

No content

Slide 137

Slide 137 text

GenAI Hands-on „Simple RAG“

Slide 138

Slide 138 text

GenAI Hands-on What are you going to learn during this lesson: • Implementing a RAG system based on a ingestion and a retrival pipeline. • Apply the RAG system to answer domain specific questions.

Slide 139

Slide 139 text

Hands-on Simple RAG

Slide 140

Slide 140 text

Retrieval Augmented Knowledge Database Retriever Generation Ingesting- Pipeline GenAI Advanced RAG Systems „How to apply for vacation at open knowledge?“

Slide 141

Slide 141 text

Retrieval Augmented Knowledge Database Retriever Generation Ingesting- Pipeline GenAI Advanced RAG Systems „How to apply for vacation at open knowledge?“ „Working like this you doesn't need a holiday. Lazy piece!“

Slide 142

Slide 142 text

GenAI Professional What is still missing for a sustainable and productive operation?

Slide 143

Slide 143 text

Retrieval Augmented Knowledge Database Retriever Generation Ingesting- Pipeline GenAI Professional Guardrails „How to apply for vacation at open knowledge?“ „Working like this you doesn't need a holiday. Lazy piece!“

Slide 144

Slide 144 text

Retrieval Augmented Knowledge Database Retriever Generation Guarding Output Ingesting- Pipeline GenAI Professional Guardrails Output Profanity Check „How to apply for vacation at open knowledge?“ „Working like this you doesn't need a holiday. Lazy piece!“

Slide 145

Slide 145 text

Retrieval Augmented Knowledge Database Retriever Generation Guarding Output Ingesting- Pipeline GenAI Professional Guardrails „Unfortunately, I can't answer that!“ Output Profanity Check „…. Lazy piece! …“ „How to apply for vacation at open knowledge?“ „Working like this you doesn't need a holiday. Lazy piece!“

Slide 146

Slide 146 text

Retrieval Augmented Knowledge Database Retriever Generation Input Output Ingesting- Pipeline GenAI Professional Guardrails Guarding Topic Check „Which Netflix series do you recommend?“

Slide 147

Slide 147 text

Retrieval Augmented Knowledge Database Retriever Generation Input Output Ingesting- Pipeline GenAI Professional Guardrails Guarding Topic Check „Which Netflix series do you recommend?“ „Sorry, but this does not fall within my area of responsibility.“

Slide 148

Slide 148 text

Retrieval Augmented Knowledge Database Retriever Generation Input Output Ingesting- Pipeline GenAI Professional Guardrails Output-Governance: Toxic Speech, Fact-Checking, Ethical-Guidelines, Cross-Validation, … Input-Evaluation: Prompt-Injection, Jailbreak-Attemp, Topic-Filter, PII-Cleansing, Rate-Limiting,… Guarding

Slide 149

Slide 149 text

Sherlock RAG in Action

Slide 150

Slide 150 text

No content

Slide 151

Slide 151 text

GenAI Hands-on „Guardrails to the rescue“

Slide 152

Slide 152 text

GenAI Hands-on What are you going to learn during this lesson: • Implement an input and output guardrail to detect and avoid toxic speech. • Implement fact checker guradrails to detect and avoid hallucination.

Slide 153

Slide 153 text

Hands-on Guardrails to the rescue

Slide 154

Slide 154 text

Retrieval Augmented Knowledge Database Retriever Generation Input Output Ingesting- Pipeline GenAI Professional Guarding What else is missing for a professional and productive system?

Slide 155

Slide 155 text

Retrieval Augmented Knowledge Database Retriever Generation Input Output Ingesting- Pipeline RAG-Monitoring Cost- Monitoring Model- Monitoring Response-Quality- Monitoring GenAI Professional Monitoring Guarding

Slide 156

Slide 156 text

Retrieval Augmented Generation GenAI Professional Response Quality Monitoring https://docs.confident-ai.com/docs/metrics-llm-evals G-Eval Summerization Answer Relevancy Faithfulness Summerization Hallucination Contextual Recall Contextual Relevancy Contextual Precision Relevant Context Generated Answer User Input

Slide 157

Slide 157 text

Retrieval Augmented Generation User Input GenAI Professional Response Quality Monitoring Faithfulness Is the supported by the ? Relevant Context Generated Answer

Slide 158

Slide 158 text

Retrieval Augmented Generation User Input GenAI Professional Response Quality Monitoring Does the match the ? Relevant Context Generated Answer Answer Relevancy

Slide 159

Slide 159 text

GenAI Professional Response Quality Monitoring Step 1: Generate possible questions ( ) from Embeddings Dimension 1 Embed. Dim. 2 Answer Relevancy Does the match the ?

Slide 160

Slide 160 text

GenAI Professional Response Quality Monitoring Step 1: Generate possible questions ( ) from Step 2: Determine the average distance from Embeddings Dimension 1 Embed. Dim. 2 Answer Relevancy Does the match the ?

Slide 161

Slide 161 text

RAG in Action aka Sherlock RAG

Slide 162

Slide 162 text

No content

Slide 163

Slide 163 text

Best Practices What are the typical pitfalls that I will run into - and how do I deal with them?

Slide 164

Slide 164 text

Retrieval Augmented Knowledge Database Retriever Generation Guarding Input Output Ingesting- Pipeline RAG-Monitoring Cost- Monitoring Model- Monitoring Response-Quality- Monitoring GenAI Best Practices Real Life Survival Guide

Slide 165

Slide 165 text

‘The answers sound conclusive, but they are wrong!’ GenAI Best Practices Real Life Survival Guide

Slide 166

Slide 166 text

GenAI Model UI/UX Guardrails Output Ingesting-Pipeline (Async.) Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting Input Hallucination (via Faithfulness / Answer Relevancy) GenAI Best Practices Real Life Survival Guide

Slide 167

Slide 167 text

GenAI Model UI/UX Guardrails Output Ingesting-Pipeline (Async.) Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting Input Missing Data GenAI Best Practices Real Life Survival Guide

Slide 168

Slide 168 text

GenAI Model UI/UX Guardrails Output Ingesting-Pipeline (Async.) Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting Input Missing Data GenAI Best Practices Real Life Survival Guide Chunk not found

Slide 169

Slide 169 text

GenAI Model UI/UX Guardrails Output Ingesting-Pipeline (Async.) Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting Input Missing Data GenAI Best Practices Real Life Survival Guide Chunk not found Chunk not relevant

Slide 170

Slide 170 text

Ingesting-Pipeline (Async.) Chunking Embedding Real Life RAG #1 Missing-Data Challenge Missing Data

Slide 171

Slide 171 text

Ingesting-Pipeline (Async.) Chunking Embedding Real Life RAG #1 Missing-Data Challenge Missing Data Problem: RAG does not know the required data.

Slide 172

Slide 172 text

Ingesting-Pipeline (Async.) Chunking Embedding Real Life RAG #1 Missing-Data Challenge Missing Data Problem: RAG does not know the required data. Solution : Implement a suitable ingestor.

Slide 173

Slide 173 text

Ingesting-Pipeline (Async.) Chunking Embedding Real Life RAG #1 Missing-Data Challenge Missing Data Problem: Snapshot of the data is not up-to-date.

Slide 174

Slide 174 text

Ingesting-Pipeline (Async.) Chunking Embedding Real Life RAG #1 Missing-Data Challenge Missing Data Problem: Snapshot of the data is not up-to-date. Solution: Interface for ‘continuous’ data sync.

Slide 175

Slide 175 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found

Slide 176

Slide 176 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found.

Slide 177

Slide 177 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found. Solution #1: Adapt chunk-sizes and overlapping.

Slide 178

Slide 178 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found. Solution #2: Choose a different splitter (e.g. Semantic-Splitter).

Slide 179

Slide 179 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found. Solution #3: Optimize the distance threshold or k from top-k.

Slide 180

Slide 180 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found. Solution #4: Selection of a more suitable embedding model.

Slide 181

Slide 181 text

Query- Embedding Top-k Fetching Ingesting-Pipeline (Async.) Chunking Embedding Augmenting Retrieval-Pipeline (Sync.) Real Life RAG #2 Chunk-not-found Challenge Chunk not found Problem: Existing chunks will not be found. Solution #5: Hypothetical document embeddings (HyDE) Input HyDE

Slide 182

Slide 182 text

Guardrails Input Output Gao et al. (2023) HyDE = Hypothetical Document Embeddings Real Life RAG #2 Chunk-not-found Challenge HyDE

Slide 183

Slide 183 text

Real Life RAG #3 Chunk-not-relevant Challenge Chunk not relevant GenAI Model Query- Embedding Top-k Fetching Augmenting Retrieval-Pipeline (Sync.)

Slide 184

Slide 184 text

Real Life RAG #3 Chunk-not-relevant Challenge Problem: Chunk is not considered to be relevant by the model. Chunk not relevant GenAI Model Query- Embedding Top-k Fetching Augmenting Retrieval-Pipeline (Sync.)

Slide 185

Slide 185 text

Real Life RAG #3 Chunk-not-relevant Challenge Chunk not relevant Query- Embedding Top-k Fetching Augmenting Retrieval-Pipeline (Sync.) Problem: Chunk is not considered to be relevant by the model. Solution #1: Select a more suitable model for the use case. GenAI Model

Slide 186

Slide 186 text

Real Life RAG #3 Chunk-not-relevant Challenge Chunk not relevant Query- Embedding Top-k Fetching Augmenting Retrieval-Pipeline (Sync.) GenAI Model Problem: Chunk is not considered to be relevant by the model. Solution #2: Add additional context to the chunk (small-to-big). Chunk

Slide 187

Slide 187 text

GenAI Model UI/UX Guardrails Input Output Ingesting-Pipeline (Async.) Chunking Embedding Retrieval-Pipeline (Sync.) Query- Embedding Top-k Fetching Augmenting

Slide 188

Slide 188 text

GenAI Hands-on „RAG Pitfalls“

Slide 189

Slide 189 text

GenAI Hands-on What are you going to learn during this lesson: • Surviving the RAG jungle: Applying patterns and best practices for content ingestion and retrieval.

Slide 190

Slide 190 text

Hands-on Surviving the RAG jungle

Slide 191

Slide 191 text

Outlook What else is possible in addition to the pure knowledge query?

Slide 192

Slide 192 text

Prompt Retrieve Augment Ingesting- Pipeline Knowledge Database Retriever GenAI- Model GenAI Outlook What else is there to consider? „All internal knowledge at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 193

Slide 193 text

GenAI explained I18N

Slide 194

Slide 194 text

UI/UX Enterprise Integration „Comment demander des vacances chez ok?“ Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model GenAI Outlook Multi-Language RAG Knowledge Database „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 195

Slide 195 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model Language- Detection Translation Translation Translation GenAI Outlook Multi-Language RAG Knowledge Database „All internal knowledge at open knowledge“ „Comment demander des vacances chez ok?“

Slide 196

Slide 196 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Knowledge Database Retriever GenAI- Model Translation Translation Translation Translation FR_fr language not supported domain specific wording GenAI Outlook Multi-Language RAG Language- Detection „Comment demander des vacances chez ok?“ „All internal knowledge at open knowledge in multiple languages.“

Slide 197

Slide 197 text

GenAI explained ACCESS CONTROL

Slide 198

Slide 198 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model Knowledge Database GenAI Outlook Access Control „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 199

Slide 199 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model Knowledge Database GenAI Outlook Access Control „What are the top secret KPIs of open knowledge?“ „All internal knowledge at open knowledge“ incl C-Level information.“

Slide 200

Slide 200 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model Token Knowledge Database Input Guardrail Some kind of Attack? Prompt-Injection? Prompt-Abuse? Rate-Limit? GenAI Outlook Access Control „What are the top secret KPIs of open knowledge?“ „All internal knowledge at open knowledge“ incl C-Level information.“

Slide 201

Slide 201 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Knowledge Database with AC Meta Data Retriever GenAI- Model RBAC via PBF Token Token Input Guardrail GenAI Outlook Access Control RBAC = Role based Access Control PBF = Permission based Filtering „What are the top secret KPIs of open knowledge?“ „All internal knowledge at open knowledge“ incl C-Level information.“

Slide 202

Slide 202 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Knowledge Database with AC Meta Data Retriever GenAI- Model RBAC via PBF Token Token Input Guardrail Output Guardrail PII: Personally identifiable information? GenAI Outlook Access Control „What does the personal data of X look like at ok?“ „All internal knowledge at open knowledge“ incl C-Level information.“

Slide 203

Slide 203 text

GenAI explained INTEGRATION

Slide 204

Slide 204 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Retriever GenAI- Model Knowledge Database GenAI Outlook Integration „All internal knowledge at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 205

Slide 205 text

GenAI Outlook Integration GenAI based Service A P I ML as a Service Input Output UI/UX Enterprise Integration „All internal knowledge at open knowledge“ „How to apply for vacation at open knowledge?“

Slide 206

Slide 206 text

GenAI Hands-on „GenAI as a Service“

Slide 207

Slide 207 text

Hands-on GenAI-as-a-Service

Slide 208

Slide 208 text

GenAI explained AGENTS

Slide 209

Slide 209 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Knowledge Database Retriever GenAI- Model GenAI Outlook Multi-Agenten Systeme „How to apply for vacation at open knowledge?“ „All internal knowledge at open knowledge“

Slide 210

Slide 210 text

UI/UX Enterprise Integration Retrieve Augment Ingesting- Pipeline Knowledge Database Retriever GenAI- Model GenAI Outlook Multi-Agenten Systeme „All internal knowledge at open knowledge“ „Apply for my vacation from […] to [… ], please.“

Slide 211

Slide 211 text

GenAI Outlook Multi-Agenten Systeme Retriever Memory Tools Planning Database Prompting Models API-Call UI/UX „Apply for my vacation from […] to [… ], please.“ „I applied for … .“

Slide 212

Slide 212 text

Conclusion What should I take away from the workshop for myself and my team?

Slide 213

Slide 213 text

GenAI from prototype to production Your personal „takeaways“: • GenAI is powerful. But also expensive. • Professional prompting is your super power. • Every model has its own character. • RAG for your own domain knowledge. • GenAI is also just software. Your use case determines the right path!

Slide 214

Slide 214 text

„When deploying Generative AI technology, it is essential to adhere to best practices including employing models through validation, understanding the model’s limitations, ensuring ethical use, and monitoring for biases continuously.“ (Source: https://www.tredence.com/generative-ai-101)

Slide 215

Slide 215 text

No content

Slide 216

Slide 216 text

Time for Questions? Yes, sure!

Slide 217

Slide 217 text

#WISSENTEILEN Many Thanks! #WISSENTEILEN by open knowledge GmbH @_openKnowledge | @mobileLarson Lars Röwekamp, CIO New Technologies

Slide 218

Slide 218 text

Looking beyond the RAG horizon: Cognitive Architecture blog.langchain.dev/what-is-a-cognitive-architecture Wir sind hier

Slide 219

Slide 219 text

#WISSENTEILEN #WISSENTEILEN IMAGE REFERENCE Folie 21: © photoplotnikov - istockphoto.com Folie 23: © Mix und Match Studios - shutterstock.com Folie 23: © Mix und Match Studios - shutterstock.com All other pictures, drawings and icons originate from • pexels.com, • pixabay.com, • unsplash.com, • flaticon.com or are created by my own.