Skip to content

AI Engineer World Fair - AI Agent Breakout session fixes #260

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cedricvidal wants to merge 2 commits into
base: main
Choose a base branch
from
Open

AI Engineer World Fair - AI Agent Breakout session fixes #260

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9c2567f
Upgrade AI Agent Evaluation Notebooks to 1RP
cedricvidal Jun 2, 2025
69edc19
Cleared cells in all notebooks
cedricvidal Jun 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ celerybeat.pid
*.sage.py

# Environments
.env
.env*
.venv
env/
venv/
Expand Down
63 changes: 33 additions & 30 deletions ...upported_Evaluation_Metrics/AI_Judge_Evaluators_Quality/AI_Judge_Evaluators_Quality.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,16 @@
"from azure.identity import DefaultAzureCredential"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"load_dotenv()"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -95,33 +105,13 @@
]
},
"outputs": [],
"source": [
"azure_ai_project = {\n",
" \"subscription_id\": \"<your-subscription-id>\",\n",
" \"resource_group_name\": \"<your-resource-group-name>\",\n",
" \"project_name\": \"<your-project-name>\",\n",
"}\n",
"\n",
"azure_openai_api_version = \"<api version>\"\n",
"azure_openai_deployment = \"<your-deployment>\"\n",
"azure_openai_endpoint = \"<your-endpoint>\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"azure_ai_project = os.environ.get(\"AZURE_AI_PROJECT\")\n",
"\n",
"# Use the following code to set the environment variables if not already set. If set, you can skip this step. In addition, you should also set \"AZURE_OPENAI_ENDPOINT\" to the endpoint of your AzureOpenAI service.\n",
"\n",
"os.environ[\"AZURE_OPENAI_API_VERSION\"] = azure_openai_api_version\n",
"os.environ[\"AZURE_OPENAI_DEPLOYMENT\"] = azure_openai_deployment\n",
"os.environ[\"AZURE_OPENAI_ENDPOINT\"] = azure_openai_endpoint"
"azure_openai_api_version = os.environ.get(\"AZURE_OPENAI_API_VERSION\")\n",
"azure_openai_deployment = os.environ.get(\"AZURE_OPENAI_DEPLOYMENT\")\n",
"azure_openai_endpoint = os.environ.get(\"AZURE_OPENAI_ENDPOINT\")"
]
},
{
Expand Down Expand Up @@ -222,7 +212,7 @@
"path = str(pathlib.Path(pathlib.Path.cwd())) + \"/data.jsonl\"\n",
"\n",
"results = evaluate(\n",
" evaluation_name=\"Eval-Run-\" + \"-\" + model_config[\"azure_deployment\"].title(),\n",
" evaluation_name=\"Quality \" + model_config[\"azure_deployment\"].title(),\n",
" data=path,\n",
" target=ModelEndpoint(model_config),\n",
" evaluators={\n",
Expand All @@ -231,7 +221,12 @@
" \"relevance\": relevance_evaluator,\n",
" \"groundedness\": groundedness_evaluator,\n",
" \"fluency\": fluency_evaluator,\n",
" \"similarity\": similarity_evaluator,\n",
" #\"similarity\": similarity_evaluator,\n",
" },\n",
" azure_ai_project={\n",
" \"subscription_id\": os.environ[\"REPORT_AZURE_SUBSCRIPTION_ID\"],\n",
" \"project_name\": os.environ[\"REPORT_PROJECT_NAME\"],\n",
" \"resource_group_name\": os.environ[\"REPORT_RESOURCE_GROUP_NAME\"],\n",
" },\n",
" evaluator_config={\n",
" \"content_safety\": {\"column_mapping\": {\"query\": \"${data.query}\", \"response\": \"${target.response}\"}},\n",
Expand Down Expand Up @@ -269,7 +264,7 @@
"metadata": {},
"outputs": [],
"source": [
"pprint(results)"
"pd.DataFrame(results[\"rows\"])"
]
},
{
Expand All @@ -278,13 +273,20 @@
"metadata": {},
"outputs": [],
"source": [
"pd.DataFrame(results[\"rows\"])"
"pprint(f'AI Foundary URL: {results.get(\"studio_url\")}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": ".venv",
"language": "python",
"name": "python3"
},
Expand All @@ -297,7 +299,8 @@
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3"
"pygments_lexer": "ipython3",
"version": "3.13.3"
}
},
"nbformat": 4,
Expand Down
63 changes: 55 additions & 8 deletions ...Risks/AI_Judge_Evaluators_Safety_Risks_Image/AI_Judge_Evaluators_Safety_Risks_Image.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,11 +62,11 @@
"from azure.ai.evaluation import ViolenceEvaluator, SexualEvaluator, SelfHarmEvaluator, HateUnfairnessEvaluator\n",
"from azure.identity import DefaultAzureCredential\n",
"\n",
"azure_ai_project = {\n",
" \"subscription_id\": \"<your-subscription-id>\",\n",
" \"resource_group_name\": \"<your-resource-group>\",\n",
" \"project_name\": \"<your-project-name>\",\n",
"}"
"from dotenv import load_dotenv\n",
"load_dotenv()\n",
"\n",
"import os\n",
"azure_ai_project = os.environ.get(\"AZURE_AI_PROJECT\")"
]
},
{
Expand All @@ -76,6 +76,22 @@
"### 1. Multi-modal Content Safety Evaluator"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Tom Cruise\n",
"#eval_image_url = \"https://cdn.britannica.com/68/178268-050-5B4E7FB6/Tom-Cruise-2013.jpg\"\n",
"\n",
"# Hellraiser\n",
"eval_image_url = \"https://dotcomstories.com/wp-content/uploads/2023/07/Hellraiser-1987.jpg\"\n",
"\n",
"from IPython.display import Image, display\n",
"display(Image(url=eval_image_url))"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -99,7 +115,7 @@
" {\"type\": \"text\", \"text\": \"Can you describe this image?\"},\n",
" {\n",
" \"type\": \"image_url\",\n",
" \"image_url\": {\"url\": \"https://cdn.britannica.com/68/178268-050-5B4E7FB6/Tom-Cruise-2013.jpg\"},\n",
" \"image_url\": {\"url\": eval_image_url},\n",
" },\n",
" ],\n",
" },\n",
Expand Down Expand Up @@ -192,12 +208,35 @@
"\n",
"result = evaluate(\n",
" data=file_path,\n",
" azure_ai_project=azure_ai_project,\n",
" azure_ai_project={\n",
" \"subscription_id\": os.environ[\"REPORT_AZURE_SUBSCRIPTION_ID\"],\n",
" \"project_name\": os.environ[\"REPORT_PROJECT_NAME\"],\n",
" \"resource_group_name\": os.environ[\"REPORT_RESOURCE_GROUP_NAME\"],\n",
" },\n",
" evaluators={\"content_safety\": content_safety_eval},\n",
")\n",
"pprint(result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pprint(f'AI Foundary URL: {result.get(\"studio_url\")}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"pd.DataFrame(result[\"rows\"])"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -232,6 +271,13 @@
"result = evaluator(conversation=conversation)\n",
"pprint(result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand All @@ -249,7 +295,8 @@
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3"
"pygments_lexer": "ipython3",
"version": "3.13.3"
}
},
"nbformat": 4,
Expand Down
64 changes: 58 additions & 6 deletions .../Supported_Evaluation_Metrics/Agent_Evaluation/AI_Judge_Evaluator_Intent_Resolution.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,35 @@
"### Initialize Intent Resolution Evaluator\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install azure-ai-projects azure-identity azure-ai-evaluation python-dotenv"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"azure_ai_project = os.environ.get(\"AZURE_AI_PROJECT\")"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -71,13 +100,16 @@
"import os\n",
"from azure.ai.evaluation import AzureOpenAIModelConfiguration\n",
"from azure.ai.evaluation import IntentResolutionEvaluator\n",
"from azure.identity import DefaultAzureCredential, get_bearer_token_provider\n",
"from pprint import pprint\n",
"\n",
"token_provider = get_bearer_token_provider(DefaultAzureCredential(), \"https://cognitiveservices.azure.com/.default\")\n",
"\n",
"model_config = AzureOpenAIModelConfiguration(\n",
" azure_endpoint=os.environ[\"AZURE_OPENAI_ENDPOINT\"],\n",
" api_key=os.environ[\"AZURE_OPENAI_API_KEY\"],\n",
" api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
" azure_deployment=os.environ[\"MODEL_DEPLOYMENT_NAME\"],\n",
" azure_deployment=os.environ[\"AZURE_OPENAI_DEPLOYMENT\"],\n",
")\n",
"\n",
"intent_resolution_evaluator = IntentResolutionEvaluator(model_config)"
Expand Down Expand Up @@ -318,25 +350,44 @@
"# This was saved using agent thread and converter.\n",
"file_name = \"evaluation_data.jsonl\"\n",
"\n",
"azure_ai_project = \"https://cvi-aie-wf-swedencentra-resource.services.ai.azure.com/api/projects/cvi-aie-wf-swedencentral\"\n",
"\n",
"response = evaluate(\n",
" data=file_name,\n",
" evaluation_name=\"Intent Resolution Evaluation\",\n",
" evaluators={\n",
" \"intent_resolution\": intent_resolution_evaluator,\n",
" },\n",
" azure_ai_project={\n",
" \"subscription_id\": os.environ[\"AZURE_SUBSCRIPTION_ID\"],\n",
" \"project_name\": os.environ[\"PROJECT_NAME\"],\n",
" \"resource_group_name\": os.environ[\"RESOURCE_GROUP_NAME\"],\n",
" \"subscription_id\": os.environ[\"REPORT_AZURE_SUBSCRIPTION_ID\"],\n",
" \"project_name\": os.environ[\"REPORT_PROJECT_NAME\"],\n",
" \"resource_group_name\": os.environ[\"REPORT_RESOURCE_GROUP_NAME\"],\n",
" },\n",
")\n",
"pprint(f'AI Foundary URL: {response.get(\"studio_url\")}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"pd.DataFrame(response[\"rows\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "test_agent_eval_sample",
"display_name": ".venv",
"language": "python",
"name": "python3"
},
Expand All @@ -349,7 +400,8 @@
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3"
"pygments_lexer": "ipython3",
"version": "3.13.3"
}
},
"nbformat": 4,
Expand Down
Loading
Loading