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

Python: Fix Eval samples (#4033)

Browse Source 
* fix red team sample

* Updated self-reflection

* fix for workflow eval sample

* fix test
This commit is contained in:
Eduard van Valkenburg
2026-02-18 20:50:33 +01:00
committed by GitHub
Unverified
parent 6a39d5a652
commit aab80d9ed9
38 changed files with 536 additions and 2629 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/05-end-to-end/evaluation/self_reflection/README.md
+9 -4
View File
@@ -7,23 +7,22 @@ This sample demonstrates the self-reflection pattern using Agent Framework and A
**What it demonstrates:**
- Iterative self-reflection loop that automatically improves responses based on groundedness evaluation
- Batch processing of prompts from JSONL files with progress tracking
- Using `AzureOpenAIChatClient` with Azure CLI authentication
- Using `AzureOpenAIResponsesClient` with a Project Endpoint and Azure CLI authentication
- Comprehensive summary statistics and detailed result tracking
## Prerequisites
### Azure Resources
- **Azure OpenAI**: Deploy models (default: gpt-4.1 for both agent and judge)
- **Azure OpenAI Responses in Foundry**: Deploy models (default: gpt-5.2 for both agent and judge)
- **Azure CLI**: Run `az login` to authenticate
### Python Environment
```bash
pip install agent-framework-core azure-ai-projects pandas --pre
pip install agent-framework-core pandas --pre
```
### Environment Variables
```bash
# .env file
AZURE_AI_PROJECT_ENDPOINT=https://<your-ai-resource>.services.ai.azure.com/api/projects/<your-ai-project>/
```
@@ -67,6 +66,12 @@ The agent iteratively improves responses:
✓ Completed with score: 5/5 (best at iteration 2/3)
```
In the Foundry UI, under `Build`/`Evaluations` you can view detailed results for each prompt, including:
- Context
- Query
- Response
- Groundedness scores and reasoning for each interation of each prompt
## Related Resources
- [Reflexion Paper](https://arxiv.org/abs/2303.11366)