chore: import upstream snapshot with attribution
dotnet-build-and-test / dotnet-test-functions (push) Has been cancelled
dotnet-build-and-test / paths-filter (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Debug, windows-latest, net9.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net8.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-foundry-hosted-it (push) Has been cancelled
dotnet-build-and-test / dotnet-build-and-test-check (push) Has been cancelled
dotnet-build-and-test / Integration Test Report (push) Has been cancelled
CodeQL / Analyze (csharp) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
dotnet-build-and-test / dotnet-test-functions (push) Has been cancelled
dotnet-build-and-test / paths-filter (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Debug, windows-latest, net9.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net8.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-foundry-hosted-it (push) Has been cancelled
dotnet-build-and-test / dotnet-build-and-test-check (push) Has been cancelled
dotnet-build-and-test / Integration Test Report (push) Has been cancelled
CodeQL / Analyze (csharp) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
This commit is contained in:
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,67 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates writing custom evaluation functions for domain-specific
|
||||
// checks. Custom evaluators run locally — no cloud evaluator service needed.
|
||||
// For LLM-based quality scoring (relevance, coherence), see Evaluation_SimpleEval.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = projectClient.AsAIAgent(
|
||||
model: deploymentName,
|
||||
instructions: "You are a customer support agent. Help users resolve their issues "
|
||||
+ "politely and provide clear, actionable steps.",
|
||||
name: "SupportAgent");
|
||||
|
||||
// Custom check: the agent should not refuse to help.
|
||||
EvalCheck noRefusal = FunctionEvaluator.Create("no_refusal", (string response) =>
|
||||
!response.Contains("I can't help", StringComparison.OrdinalIgnoreCase)
|
||||
&& !response.Contains("I'm unable to", StringComparison.OrdinalIgnoreCase)
|
||||
&& !response.Contains("outside my scope", StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
// Custom check: response should include actionable guidance (numbered steps or bullet points).
|
||||
EvalCheck hasActionableSteps = FunctionEvaluator.Create("has_actionable_steps", (string response) =>
|
||||
response.Contains("1.", StringComparison.Ordinal)
|
||||
|| response.Contains("- ", StringComparison.Ordinal)
|
||||
|| response.Contains("• ", StringComparison.Ordinal));
|
||||
|
||||
// Custom check: response should be substantial but not excessively long.
|
||||
EvalCheck reasonableLength = FunctionEvaluator.Create("reasonable_length", (string response) =>
|
||||
response.Length >= 50 && response.Length <= 2000);
|
||||
|
||||
// Combine all custom checks into a local evaluator.
|
||||
LocalEvaluator evaluator = new(noRefusal, hasActionableSteps, reasonableLength);
|
||||
|
||||
string[] queries =
|
||||
[
|
||||
"My order hasn't arrived after two weeks. What should I do?",
|
||||
"I was charged twice for the same item. Can you help?",
|
||||
"How do I return a damaged product?",
|
||||
];
|
||||
|
||||
AgentEvaluationResults results = await agent.EvaluateAsync(queries, evaluator);
|
||||
|
||||
Console.WriteLine($"Passed: {results.Passed}/{results.Total}");
|
||||
Console.WriteLine();
|
||||
|
||||
for (int i = 0; i < results.Items.Count; i++)
|
||||
{
|
||||
Console.WriteLine($"Query: {queries[i]}");
|
||||
Console.WriteLine($"Response: {(results.InputItems?[i].Response is { } resp ? resp.Substring(0, Math.Min(50, resp.Length)) : "N/A")}...");
|
||||
foreach (var metric in results.Items[i].Metrics)
|
||||
{
|
||||
string status = metric.Value.Interpretation?.Failed == true ? "FAIL" : "PASS";
|
||||
Console.WriteLine($" [{status}] {metric.Key}");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
}
|
||||
@@ -0,0 +1,36 @@
|
||||
# Evaluation - Custom Evals
|
||||
|
||||
This sample demonstrates writing custom domain-specific evaluation functions using `FunctionEvaluator.Create`. Custom evaluators run locally with no cloud evaluator service needed — useful for enforcing business rules, format requirements, or safety guardrails.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Writing custom checks with `FunctionEvaluator.Create` for domain-specific logic
|
||||
- Checking that a customer support agent doesn't refuse to help
|
||||
- Verifying responses contain actionable steps (numbered lists or bullet points)
|
||||
- Enforcing response length constraints
|
||||
- Combining multiple custom checks into a `LocalEvaluator`
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Azure authentication available to `DefaultAzureCredential` (for local development, run `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-4o-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/Evaluation
|
||||
dotnet run --project .\Evaluation_CustomEvals
|
||||
```
|
||||
|
||||
## See also
|
||||
|
||||
- [Evaluation_SimpleEval](../Evaluation_SimpleEval/) — Simplest evaluation using Foundry quality evaluators (Relevance, Coherence)
|
||||
- [Evaluation_ExpectedOutputs](../Evaluation_ExpectedOutputs/) — Evaluating against ground-truth expected outputs
|
||||
- [Evaluation_MixedProviders](../../../05-end-to-end/Evaluation/Evaluation_MixedProviders/) — Combining custom + Foundry evaluators in one call
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,54 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates evaluating agent responses against expected outputs.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
|
||||
|
||||
// Create a math tutor agent.
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
|
||||
.AsAIAgent(
|
||||
model: deploymentName,
|
||||
instructions: "You are a math tutor. Answer concisely with the numeric result.",
|
||||
name: "MathTutor");
|
||||
|
||||
// Combine built-in checks.
|
||||
LocalEvaluator localEvaluator = new(
|
||||
EvalChecks.ContainsExpected(), // response must contain the expected answer
|
||||
EvalChecks.NonEmpty()); // response must not be empty
|
||||
|
||||
// Queries and expected outputs.
|
||||
string[] queries = ["What is 2 + 2?", "What is the square root of 144?"];
|
||||
string[] expectedOutputs = ["4", "12"];
|
||||
|
||||
// Run the agent and evaluate with expected outputs.
|
||||
AgentEvaluationResults results = await agent.EvaluateAsync(
|
||||
queries,
|
||||
localEvaluator,
|
||||
expectedOutput: expectedOutputs);
|
||||
|
||||
// Print results.
|
||||
Console.WriteLine($"Evaluation: {results.ProviderName}");
|
||||
Console.WriteLine($" Passed: {results.Passed}/{results.Total}");
|
||||
Console.WriteLine($" All passed: {results.AllPassed}");
|
||||
Console.WriteLine();
|
||||
|
||||
for (int i = 0; i < results.Items.Count; i++)
|
||||
{
|
||||
Console.WriteLine($"Query: {queries[i]} | Expected: {expectedOutputs[i]}");
|
||||
Console.WriteLine($"Response: {(results.InputItems?[i].Response is { } resp ? resp.Substring(0, Math.Min(50, resp.Length)) : "N/A")}");
|
||||
foreach (var metric in results.Items[i].Metrics)
|
||||
{
|
||||
string status = metric.Value.Interpretation?.Failed == true ? "FAIL" : "PASS";
|
||||
Console.WriteLine($" [{status}] {metric.Key}: {metric.Value.Interpretation?.Reason}");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
}
|
||||
@@ -0,0 +1,34 @@
|
||||
# Evaluation - Expected Outputs
|
||||
|
||||
This sample demonstrates evaluating agent responses against expected outputs using built-in checks.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Using `EvalChecks.ContainsExpected` for ground-truth comparison
|
||||
- Using `EvalChecks.NonEmpty` for basic response validation
|
||||
- Passing `expectedOutput` to `agent.EvaluateAsync()` so checks can access ground truth
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Azure CLI installed and authenticated (`az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-4o-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/Evaluation
|
||||
dotnet run --project .\Evaluation_ExpectedOutputs
|
||||
```
|
||||
|
||||
## See also
|
||||
|
||||
- [Evaluation_SimpleEval](../Evaluation_SimpleEval/) — Simplest evaluation with built-in and custom checks
|
||||
- [Evaluation_FoundryQuality](../../../05-end-to-end/Evaluation/Evaluation_FoundryQuality/) — Cloud-based quality evaluation with Foundry evaluators
|
||||
- [Evaluation_FoundryRubric](../../../05-end-to-end/Evaluation/Evaluation_FoundryRubric/) — Rubric (adaptive) evaluators with per-dimension scores
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,57 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates that the evaluation pipeline preserves multimodal content.
|
||||
// When an agent conversation includes images, EvalChecks.HasImageContent() can verify
|
||||
// they survived into the EvalItem — useful for testing vision-capable agents.
|
||||
//
|
||||
// No Azure credentials needed: this sample builds EvalItems locally to show the pattern.
|
||||
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
// Simulate a vision agent conversation where the user sends an image.
|
||||
// Just pass the conversation — query/response are derived automatically.
|
||||
// For cloud-based quality evaluation of multimodal conversations, see the
|
||||
// 05-end-to-end/Evaluation samples (FoundryQuality, ConversationSplits).
|
||||
EvalItem imageItem = new(
|
||||
conversation:
|
||||
[
|
||||
new(ChatRole.User,
|
||||
[
|
||||
new TextContent("What do you see in this image?"),
|
||||
new UriContent(new Uri("https://example.com/mountain.png"), "image/png"),
|
||||
]),
|
||||
new(ChatRole.Assistant, "The image shows a mountain landscape with snow-capped peaks."),
|
||||
]);
|
||||
|
||||
// Simulate a text-only conversation (no image).
|
||||
EvalItem textItem = new(
|
||||
query: "Tell me about mountains.",
|
||||
response: "Mountains are large landforms that rise above the surrounding terrain.");
|
||||
|
||||
// HasImageContent() passes when the conversation contains an image, fails otherwise.
|
||||
// This lets you verify that your vision agent actually received the image.
|
||||
LocalEvaluator evaluator = new(
|
||||
EvalChecks.HasImageContent(),
|
||||
EvalChecks.NonEmpty());
|
||||
|
||||
AgentEvaluationResults results = await evaluator.EvaluateAsync([imageItem, textItem]);
|
||||
|
||||
Console.WriteLine($"Evaluation: {results.Passed}/{results.Total} passed");
|
||||
Console.WriteLine();
|
||||
|
||||
Console.WriteLine($"Image conversation: has_image_content = {imageItem.HasImageContent}"); // true
|
||||
Console.WriteLine($"Text conversation: has_image_content = {textItem.HasImageContent}"); // false
|
||||
Console.WriteLine();
|
||||
|
||||
for (int i = 0; i < results.Items.Count; i++)
|
||||
{
|
||||
Console.WriteLine($"Item {i + 1}: {results.InputItems![i].Query}");
|
||||
foreach (var metric in results.Items[i].Metrics)
|
||||
{
|
||||
string status = metric.Value.Interpretation?.Failed == true ? "FAIL" : "PASS";
|
||||
Console.WriteLine($" [{status}] {metric.Key}: {metric.Value.Interpretation?.Reason}");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
# Evaluation - Multimodal
|
||||
|
||||
This sample demonstrates that the evaluation pipeline preserves multimodal content. When conversations include images, `EvalChecks.HasImageContent` can verify they survived into the `EvalItem`.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Building `EvalItem` objects with `UriContent` image content
|
||||
- Using built-in `EvalChecks.HasImageContent` to detect images in conversations
|
||||
- Comparing image vs. text-only conversations to show when the check passes/fails
|
||||
- Evaluating directly with `LocalEvaluator.EvaluateAsync()` (no agent needed)
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
|
||||
No Azure credentials or environment variables are required for this sample since it evaluates locally without calling an agent.
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/Evaluation
|
||||
dotnet run --project .\Evaluation_Multimodal
|
||||
```
|
||||
|
||||
## See also
|
||||
|
||||
- [Evaluation_SimpleEval](../Evaluation_SimpleEval/) — Simplest evaluation with built-in checks and `agent.EvaluateAsync()`
|
||||
- [Evaluation_FoundryQuality](../../../05-end-to-end/Evaluation/Evaluation_FoundryQuality/) — Cloud-based quality evaluation with Foundry evaluators
|
||||
- [Evaluation_FoundryRubric](../../../05-end-to-end/Evaluation/Evaluation_FoundryRubric/) — Rubric (adaptive) evaluators with per-dimension scores
|
||||
- [Evaluation_ConversationSplits](../../../05-end-to-end/Evaluation/Evaluation_ConversationSplits/) — Multi-turn conversation split strategies
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,55 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// Simplest possible agent evaluation: create a Foundry agent, run it against
|
||||
// test questions, and use Foundry quality evaluators to score the responses.
|
||||
// For custom domain-specific checks, see the Evaluation_CustomEvals sample.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI.Evaluation;
|
||||
using FoundryEvals = Microsoft.Agents.AI.Foundry.FoundryEvals;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = projectClient.AsAIAgent(
|
||||
model: deploymentName,
|
||||
instructions: "You are a helpful assistant. Provide clear, accurate answers.",
|
||||
name: "SimpleAgent");
|
||||
|
||||
// Configure Foundry quality evaluators — runs evaluations server-side via the Foundry Evals API.
|
||||
FoundryEvals evaluator = new(projectClient, deploymentName, FoundryEvals.Relevance, FoundryEvals.Coherence);
|
||||
|
||||
// Run the agent against test queries and evaluate in one call.
|
||||
string[] queries = ["What is photosynthesis?", "How do vaccines work?"];
|
||||
AgentEvaluationResults results = await agent.EvaluateAsync(queries, evaluator);
|
||||
|
||||
// Print results.
|
||||
Console.WriteLine($"Passed: {results.Passed}/{results.Total}");
|
||||
if (results.ReportUrl is not null)
|
||||
{
|
||||
Console.WriteLine($"Report: {results.ReportUrl}");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
|
||||
for (int i = 0; i < results.Items.Count; i++)
|
||||
{
|
||||
Console.WriteLine($"Query: {queries[i]}");
|
||||
Console.WriteLine($"Response: {(results.InputItems?[i].Response is { } resp ? resp.Substring(0, Math.Min(50, resp.Length)) : "N/A")}...");
|
||||
foreach (var metric in results.Items[i].Metrics)
|
||||
{
|
||||
string score = metric.Value is NumericMetric nm && nm.Value.HasValue
|
||||
? nm.Value.Value.ToString("F1")
|
||||
: "N/A";
|
||||
Console.WriteLine($" {metric.Key}: {score}");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
}
|
||||
@@ -0,0 +1,35 @@
|
||||
# Evaluation - Simple Eval
|
||||
|
||||
The simplest agent evaluation: create a Foundry agent, run it against test questions, and use Foundry quality evaluators (Relevance, Coherence) to score the responses.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating an agent with `AIProjectClient.AsAIAgent()`
|
||||
- Using `FoundryEvals` with Relevance and Coherence quality evaluators
|
||||
- Running evaluation with `agent.EvaluateAsync()` — runs the agent and evaluates in one call
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Azure authentication available to `DefaultAzureCredential` (for local development, run `az login`)
|
||||
- A deployed model in your Azure AI Foundry project
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-4o-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/Evaluation
|
||||
dotnet run --project .\Evaluation_SimpleEval
|
||||
```
|
||||
|
||||
## See also
|
||||
|
||||
- [Evaluation_CustomEvals](../Evaluation_CustomEvals/) — Writing custom domain-specific evaluation checks
|
||||
- [Evaluation_ExpectedOutputs](../Evaluation_ExpectedOutputs/) — Evaluating against ground-truth expected outputs
|
||||
- [Evaluation_MixedProviders](../../../05-end-to-end/Evaluation/Evaluation_MixedProviders/) — Combining local + Foundry evaluators in one call
|
||||
Reference in New Issue
Block a user