Global AI Bootcamp 2025: Semantic AI: Language & Embedding Models hand-in-hand

Generative AI has reshaped how we build intelligent systems, but true AI reliability goes beyond text generation. Semantic AI shifts the focus from mere language generation to deep understanding and structured decision-making, where language models and embedding models work together to power robust applications.
SLMs & LLMs process and generate natural language, enabling structured outputs for APIs and interactive applications. Embedding models, on the other hand, capture semantic relationships within data, enhancing query filtering, task routing, and retrieval accuracy. Together, they create AI systems that are more context-aware, scalable, and precise.
Christian explores how structured outputs from LMs and embedding-driven semantics can work together to improve an AI system's performance. Through a real-world example, he demonstrates how query validation, task routing, and API integration create robust AI-powered interactions.

Transcript

1. Semantic AI Language & Embedding Models hand-in-hand Christian Weyer | Co-Founder & CTO | Thinktecture AG | christian.weyer@thinktecture.com
2. Semantic AI Language & Embedding Models hand-in-hand LLM- ALL-THE-THINGS?
3. Language Models understand and generate semantically rich human language, transforming it into text or structured data for both humans and machines. ⚠ Non-deterministic: same input can lead to different outputs. Embedding Models capture semantic meaning by encoding human language into numerical vector representations, facilitating understanding, comparison, and retrieval for both humans and machines. ✅ Deterministic: same input always results in the same embedding. Semantic AI Language & Embedding Models hand-in-hand 🫱 🫲 Semantic AI Generative AI 3
4. Semantic AI Language & Embedding Models hand-in-hand MODELS FOR OUR SOFTWARE
5. Semantic AI Language & Embedding Models hand-in-hand Classical applications & UIs 5
6. Semantic AI Language & Embedding Models hand-in-hand Language-enabled “UIs” 6
7. Semantic AI Language & Embedding Models hand-in-hand SEMANTIC AI PATTERN LOCAL RAG [RETRIEVAL-AUGMENTED GENERATION]
8. Semantic AI Language & Embedding Models hand-in-hand “Talk to your data” Cleanup & Split Text Embedding Question Text Embedding Save Query Relevant Results Question Answ er LLM Embedding Model Embedding Model 💡 Indexing / Embedding Question Answering .md, .docx, .pdf etc. “Lorem ipsum…?” 💡 Vector DB 8
9. § Frameworks § LangChain § Fastembed § Lightweight & efficient for generating text embeddings § Embedding model § jinaai/jina-embeddings-v2-base-de (local, no GPU required) § Vector store § PostgreSql (pgvector) vector store § LLM/SLM § Llama 3.3 70B on Cerebras (very fast) Semantic AI Language & Embedding Models hand-in-hand Technical implementation – Local RAG 9
10. Semantic AI Language & Embedding Models hand-in-hand SEMANTIC AI PATTERN STRUCTURED OUTPUT
11. Semantic AI Language & Embedding Models hand-in-hand Structured data from unstructured input – e.g. for API calling “OK, when is my colleague CW available for a two- days workshop?” System Prompt (with employee data) + Schema / Function Calling (for structured output) Web API Availability business logic 11
12. § Frameworks § Pydantic § Instructor § Methodology § Schema with JSON Mode (or Function Calling) § SLM/LLM § Llama 3.3 70B on Cerebras (very fast) Semantic AI Language & Embedding Models hand-in-hand Technical implementation – Structured Output 12
13. Semantic AI Language & Embedding Models hand-in-hand SEMANTIC AI PATTERN SEMANTIC GUARDING & ROUTING
14. Semantic AI Language & Embedding Models hand-in-hand Semantics-based decisions for user interactions Guarding (e.g. prompt injection) Routing (selecting correct target) “Lorem ipsum…?” Target RAG 1 Target Structured Output & API Call Target … something else … Fine-tuned Language Model Embedding Model 14
15. Guarding § Frameworks § llm-guard § HuggingFace Transformers § Model § deepset/deberta-v3-base- injection (local, no GPU required) Routing § Frameworks § semantic-routing § Fastembed § Embedding model § BAAI/bge-small-en-v1.5 (local, no GPU required) § Vector store § PostgreSql (pgvector) Semantic AI Language & Embedding Models hand-in-hand Technical implementation – Semantic Guarding & Routing 15
16. Language Models Embedding Models Semantic AI Language & Embedding Models hand-in-hand 🫱 🫲 Semantic AI 16
17. Thank you! Christian Weyer https://thinktecture.com/christian-weyer christian.weyer@thinktecture.com 17
18. § Technology catalyst § AI-powered solutions § Pragmatic end-to-end architectures § Microsoft Regional Director § Microsoft MVP for AI § Google GDE for Web AI christian.weyer@thinktecture.com https://www.thinktecture.com Semantic AI Language & Embedding Models hand-in-hand Christian Weyer Co-Founder & CTO @ Thinktecture AG 18
19. Semantic AI Language & Embedding Models hand-in-hand END-TO-END SOLUTION ILLUSTRATED 19
20. Semantic routing Semantic AI Language & Embedding Models hand-in-hand "Talk to your systems"(for Availability info) Web App / Watch App Speech-to-Text Internal Gateway (Python FastAPI) LLM / SLM Text-to-Speech Transcribe spoken text Transcribed text Check for experts availability with text Extract { experts, booking times } from text Structured JSON data (Function calling) Generate response with availability Response Response with experts availability 🔉 Speech-to-text for response Response audio Internal Business API (node.js – veeeery old) Query Availability API Availability When is CL…? CL will be… 20