Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Christian Weyer Co-Founder & CTO @christianweyer Community Days Softwarearchitektur & Softwareentwicklung

§ Technology catalyst § AI-powered solutions § Pragmatic end-to-end architectures § Microsoft Regional Director § Microsoft MVP for Developer Technologies & Azure ASPInsider, AzureInsider § Google GDE for Web Technologies [email protected] @christianweyer https://www.thinktecture.com Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Christian Weyer Co-Founder & CTO @ Thinktecture AG 2

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Our journey today 3 AI all-the- things? LLMs in your Solutions Talk to your Data Exciting Times… Democratizing Generative AI Talk to your Systems

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen AI all-the-things? 4

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen A.I. 5

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen AI all-the-things? 6 Data Science Artificial Intelligence Machine Learning Unsupervised, supervised, reinforcement learning Deep Learning ANN, CNN, RNN etc. NLP Generative AI GAN, VAE, Transformers etc. Image / Video Generation GAN, VAE Large Language Models Transformers

§ LLMs generate text based on input § LLMs can understand text – this changes a lot § Without having to train them on data, domains, or use cases § Prompts are the universal interface (“UI”): unstructured text with semantics as input § Human language evolves as a first-class citizen in software architecture 🤯 Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Large Language Models (LLMs) 7 Text… – really, just text?

§ LLMs are programs § LLMs are highly specialized neural networks § LLMs use(d) lots of data § LLMs need a lot of resources to be operated § LLMs have an API to be used through Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Large Language Models demystified 8

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen LLMs in your Solutions 9

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Using LLMs: It’s just HTTP APIs Inference, FTW. 10

GPT API access Open AI Playground Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 11

Barebones SDKs § E.g. Open AI SDK § Available for any programming language § Basic abstraction over HTTP APIs § Also available from other providers LangChain § Large community § Python and Typescript versions § Chains for sequences of LLM-related actions in code § Abstractions for § Prompts & LLMs § Memory § Vector stores § Tools § Loading text from a wide range of sources Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Building LLM-based end-to-end applications 12

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Talk to your Data 13

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Answering Questions on Data Retrieval-augmented generation (RAG) Cleanup & Split Text Embedding Question Text Embedding Save Query Relevant Text Question Answer LLM 14 Embedding model Embedding model 💡 Indexing / Embedding Question Answering Vector DB

RAG: Learning about company’s policies via Slack LangChain, Weaviate – Mixtral-8x7B on Groq Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 15

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Talk to your Systems 16

§ Clever & strict prompting § Schema description: JSON, TypeScript types, etc. § Framework or tools support § Kor, TypeChat, etc. § Open AI Function Calling Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Extract structured data from textual information 17

Extracting structured data from text: Flight search OpenAI Function Calling, LangChain, FastAPI, JS - GPT-4-Turbo Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 18

Extracting structured data from voice: Form filling JSON extraction, Angular Forms - Mixtral-8x7B on Groq Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 19

§ Integrate LLM-external systems to aid LLMs § Tool / function calling standard established by OpenAI § LLM outputs JSON containing arguments to call one or many functions § LLM does not call the function § All major libs support tool calling § OpenAI SDKs § LangChain § Semantic Kernel § etc. Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Extending LLM capabilities 20 curl https://api.openai.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -d '{ "model": "gpt-3.5-turbo", "messages": [ { "role": "user", "content": "What is the weather like in Boston?" } ], "tools": [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] } }, "required": ["location"] } } } ], "tool_choice": "auto" }'

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Talking to internal APIs – Ask for experts availability 21 Angular PWA Open AI Speech-to-Text Internal Systems Gateway Open AI GPT-4-T Open AI Text-to-Speech Transcribe spoken text Transcribed text Check for experts availability with text Extract { experts, booking times } from text Structured JSON data (Tool calling) Generate response with availability Response Response with experts availability 🗣 🔉 Speech-to-text for response Response audio Internal Company API Query Availability API Availability When is CL…? CL will be…

Ask for experts availability in my company systems Angular, Speech-to-text, internal HTTP API, node.js OpenAI SDK + Tool Calling, Text-to-speech – GPT-4-Turbo Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 22

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Democratizing Generative AI 23

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen LLMs everywhere OpenAI-related (cloud) OpenAI Azure OpenAI Service Big cloud providers Google Model Garden on Vertex AI Amazon Bedrock Open-source Edge IoT Server Desktop Mobile Web 24 Other providers Antrophic Cohere Mistral AI Hugging Face Open-source

§ Open-source community drives innovation in Generative AI § Important factors § Use case § Parameter size § Quantization § Processing power needed § Mistral-based family shows big potential for local use cases (7B params) Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Open-source LLMs thrive 25

Local RAG: Mistral-7B open-source LLM llama.cpp, ollama, LangChain, StreamLit Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen DEMO 26

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Exciting Times… 27

§ LLMs enable new scenarios & use cases to incorporate human language into software solutions § Fast moving and changing field § Every week something “big” happens in LLM space § Frameworks & ecosystem are evolving together with LLMs § Closed vs open LLMs § Competition drives invention & advancement § SLMs: specialized, fine-tuned for domains § SISO (sh*t in, sh*t out) § Quality of results heavily depends on your data & input Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen Current state 28

Large Language Models, Daten & APIs Integration von Generative AI in eigene Anwendungen 2024: The year of SLMs & CPU inference 29

Thank you! Christian Weyer https://thinktecture.com/christian-weyer 30 Demos https://github.com/thinktecture-labs/summit-community-gen-ai