02-agents/

This sample shows how to use dependency injection to register an Agent and use it from a hosted service with a user input chat loop.

This sample shows how to write custom agent middleware.

This sample uses the reusable harness setup with a normal Foundry agent.

This sample recalls chat messages from earlier sessions for the same user.

This sample archives older chat messages and recalls them from a vector store.

This sample stores generated embeddings in Azure AI Search and runs scoped vector and hybrid queries.

This sample stores generated embeddings in a temporary Cosmos DB container.

This sample demonstrates long-running agent operations using the OpenAI Responses API "background" option.

This sample shows how to download files generated by Code Interpreter using the OpenAI Containers API.

This sample retrieves text from an in-memory vector store before each agent invocation and keeps retrieved context out of retained conversation history.

This sample uses a custom Qdrant schema to retrieve Agent Framework documentation, including recent conversation context in each search.

This sample uploads a knowledge base and creates a Foundry vector store and prompt agent version that uses server-side file search.

This sample retrieves graph-enriched text from a Neo4j full-text index.