agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update foundry hosting samples

Browse Source
This commit is contained in:
Tao Chen
2026-04-24 11:48:17 -07:00
parent 0b69d7fd15
commit 334ce4dfe0
55 changed files with 653 additions and 259 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/04-hosting/foundry-hosted-agents/invocations/01_basic/README.md
+22 -10
View File
@@ -1,18 +1,26 @@
# Basic example of hosting an agent with the `invocations` API
# What this sample demonstrates
## Running the server locally
An [Agent Framework](https://github.com/microsoft/agent-framework) agent hosted using the **Invocations protocol** with session management. Unlike the Responses protocol, the Invocations protocol does **not** provide built-in server-side conversation history — this agent maintains an in-memory session store keyed by `agent_session_id`. In production, replace it with durable storage (Redis, Cosmos DB, etc.) so history survives restarts.
### Environment setup
## How It Works
Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
### Model Integration
Run the following command to start the server:
The agent uses `FoundryChatClient` from the Agent Framework to create a Responses client from the project endpoint and model deployment. When a request arrives, the handler looks up (or creates) a session by `session_id`, runs the agent with the user message and session context, and returns the reply. The agent supports both streaming (SSE events) and non-streaming (JSON) response modes.
```bash
python main.py
```
See [main.py](main.py) for the full implementation.
### Interacting with the agent
### Agent Hosting
The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `InvocationsHostServer`, which provisions a REST API endpoint compatible with the Azure AI Invocations protocol.
## Running the Agent Host
Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
## Interacting with the agent
> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.
Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:
@@ -22,7 +30,7 @@ curl -X POST http://localhost:8088/invocations -i -H "Content-Type: application/
The server will respond with a JSON object containing the response text. The `-i` flag in the `curl` command includes the HTTP response headers in the output, which includes the session ID that can be used for multi-turn conversations. Here is an example of the response:
```bash
```
HTTP/1.1 200
content-length: 34
content-type: application/json
@@ -42,3 +50,7 @@ To have a multi-turn conversation with the agent, take the session ID from the r
```bash
curl -X POST http://localhost:8088/invocations?agent_session_id=9370b9d4-cd13-4436-a57f-03b843ac0e17 -i -H "Content-Type: application/json" -d '{"message": "How are you?"}'
```
## Deploying the Agent to Foundry
To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.