Tutorials

The following tutorials offer simple walk-throughs for common Stained Glass Transform Proxy use-cases.

• Inference with Stained Glass Transform (SGT) Proxy and vLLM

  ---

  This notebook demonstrates: - Various use-cases of inference from a vLLM instance running a Llama base model via OpenAI Chat Completions API compatible clients while using **Stained Glass...

  View Notebook

• Private RAG Chatbot with Stained Glass Transform Proxy and Langchain

  ---

  This notebook demonstrates how to build a private chatbot with a Retrieval Augmented Generation (RAG) architecture with a Stained Glass Transform Proxy, Langchain, Qdrant, and Gradio.

  View Notebook

• Directly requesting Stained Glass Transform embeddings and sending to vLLM

  ---

  Stained Glass Transform Proxy's normal operation (when using the /v1/chat/completions endpoint) transforms a prompt and then forwards the request to an upstream inference server that accepts prompt embeddings.

  View Notebook

• Tool Calling with Stained Glass Proxy (SGP) and Output Protected vLLM.

  ---

  Large Language Models (LLMs) increasingly exhibit agentic behavior through their ability to use external tools.

  View Notebook

• Agentic AI with Stained Glass Proxy (SGP) and Output Protected vLLM.

  ---

  This notebook demonstrates a Pydantic AI agentic workflow using Protopia's Stained Glass Transform (SGT) Proxy and Output Protected vLLM as the data privacy preservation layer.

  View Notebook