An internal company tool serves as a practical case study for applying language and embedding models to solve real business problems.
The system combines API-based data from a third-party planning tool with document-based data from a Git-based knowledge base.
Instead of extending traditional GUIs, a universal interface allows users to interact with systems using natural language through platforms like Slack or voice.
A live demo shows how a single chat interface can query both a knowledge base and an employee availability system, providing source links to verify information.
Language models are non-deterministic and generative, while embedding models are deterministic and create vector representations for comparison and retrieval.
The RAG pattern uses embeddings and a vector database to find relevant document chunks to provide as context for an LLM's answer.
By providing a technical schema in the prompt, a language model can be forced to generate structured, machine-readable output for reliable API integration.
Semantic routing uses embeddings to classify a user's intent by finding the closest cluster of example questions, directing the request to the correct backend system.
Embeddings are crucial not just within LLMs but also for encoding meaning and enabling core architectural patterns like semantic routing and guarding.
25:17Scott Hanselman
24:24Damir
27:12Damir
27:11Emanuele Fabbiani
28:38Tomislav Tipurić
35:16Ankit Patel
32:26Krzysztof Cieślak
31:25Patrick Koss
.png?w=240&auto=compress,format)
Jobs that call for the skills explored in this talk.
CGI Group Inc.
Köln, Germany