# RAI Agent Functions API
A Python SDK for Azure Functions API that provides Responsible AI (RAI) operations including prompt review and testcase generation.
## Features
- **Prompt Review**: Review and update prompts with AI-powered analysis
- **Testcase Generation**: Generate comprehensive testcases from prompts
- **Azure Integration**: Built for Azure Functions with proper authentication and error handling
- **Async Support**: Full async/await support for non-blocking operations
- **Type Safety**: Complete type hints and mypy compatibility
## Installation
Install the package using pip:
```bash
pip install rai-agent-functions-api
```
## Quick Start
### Basic Usage
```python
from RAI_SDK.rai_agent_functions_api import RAIAgentFunctionsAPI
# Initialize the client
client = RAIAgentFunctionsAPI(
endpoint="https://your-function-app.azurewebsites.net/api"
)
# Review a prompt
review_result = client.reviewer.post(
body={"prompt": "Generate a sales forecast for Q4"}
)
print(review_result)
# Generate testcases
testcase_result = client.testcase.generator_post(
body={
"prompt": "Create user authentication system",
"number_of_testcases": 5,
"user_categories": ["security", "usability", "performance"]
}
)
print(testcase_result)
```
### Async Usage
```python
from RAI_SDK.rai_agent_functions_api.aio import RAIAgentFunctionsAPI
async def main():
async with RAIAgentFunctionsAPI(
endpoint="https://your-function-app.azurewebsites.net/api"
) as client:
# Async operations
review_result = await client.reviewer.post(
body={"prompt": "Generate a sales forecast for Q4"}
)
print(review_result)
import asyncio
asyncio.run(main())
```
## API Reference
### RAIAgentFunctionsAPI
The main client class for interacting with the RAI Agent Functions API.
#### Parameters
- `endpoint` (str): The base URL of your Azure Functions API. Default: `"https://func-rai-agent-eus.azurewebsites.net/api"`
#### Methods
##### reviewer.post(body)
Review and update a prompt using AI analysis.
**Parameters:**
- `body` (dict): Request payload containing:
- `prompt` (str): The prompt to review
**Returns:**
- dict: Response containing:
- `review_of_updated_prompt`: Analysis of the updated prompt
- `review_result`: Review findings and suggestions
- `updated_result`: The improved prompt
##### testcase.generator_post(body)
Generate testcases from a given prompt.
**Parameters:**
- `body` (dict): Request payload containing:
- `prompt` (str): The prompt to generate testcases for
- `number_of_testcases` (int): Number of testcases to generate
- `user_categories` (list[str]): Categories for testcase generation
**Returns:**
- dict: Response containing:
- `result`: Generated testcases and analysis
## Configuration
### Authentication
The SDK uses Azure Core's authentication mechanisms. You can configure authentication using:
```python
from azure.identity import DefaultAzureCredential
client = RAIAgentFunctionsAPI(
endpoint="https://your-function-app.azurewebsites.net/api",
credential=DefaultAzureCredential()
)
```
### Custom Headers
```python
client = RAIAgentFunctionsAPI(
endpoint="https://your-function-app.azurewebsites.net/api",
headers={"Custom-Header": "value"}
)
```
### Retry Policy
```python
from azure.core.pipeline.policies import RetryPolicy
client = RAIAgentFunctionsAPI(
endpoint="https://your-function-app.azurewebsites.net/api",
retry_policy=RetryPolicy(retry_total=3)
)
```
## Error Handling
The SDK provides comprehensive error handling:
```python
from azure.core.exceptions import HttpResponseError, ClientAuthenticationError
try:
result = client.reviewer.post(body={"prompt": "test"})
except ClientAuthenticationError:
print("Authentication failed")
except HttpResponseError as e:
print(f"HTTP error: {e.status_code} - {e.message}")
except Exception as e:
print(f"Unexpected error: {e}")
```
## Development
### Prerequisites
- Python 3.8+
- Azure Functions Core Tools (for local development)
### Installation for Development
```bash
git clone https://github.com/yourusername/rai-agent-functions-api.git
cd rai-agent-functions-api
pip install -e ".[dev]"
```
### Running Tests
```bash
pytest
```
### Code Formatting
```bash
black .
flake8 .
mypy .
```
## Examples
### Complete Example
```python
from RAI_SDK.rai_agent_functions_api import RAIAgentFunctionsAPI
def main():
# Initialize client
client = RAIAgentFunctionsAPI()
# Example 1: Review a business prompt
business_prompt = "Create a marketing strategy for our new product launch"
review_response = client.reviewer.post(body={"prompt": business_prompt})
print("Original prompt:", business_prompt)
print("Review result:", review_response.get("review_result"))
print("Updated prompt:", review_response.get("updated_result"))
# Example 2: Generate testcases for a technical requirement
technical_prompt = "Implement user authentication with multi-factor authentication"
testcase_response = client.testcase.generator_post(
body={
"prompt": technical_prompt,
"number_of_testcases": 3,
"user_categories": ["security", "usability", "edge-cases"]
}
)
print("Generated testcases:", testcase_response.get("result"))
if __name__ == "__main__":
main()
```
## License
This project is licensed under the MIT License - see the LICENSE file for details.
## Contributing
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add some amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
## Support
For support and questions:
- Create an issue on GitHub
- Check the documentation
- Review the examples
## Changelog
### 1.0.0
- Initial release
- Prompt review functionality
- Testcase generation capabilities
- Full async support
- Comprehensive error handling
Raw data
{
"_id": null,
"home_page": null,
"name": "rai-agent-functions-api",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "azure, functions, api, responsible-ai, rai, prompt-review, testcase-generation",
"author": null,
"author_email": "Divyanshu Rastogi <divyanshur@maqsoftware.com>",
"download_url": "https://files.pythonhosted.org/packages/48/18/04409d05892f47068a49ddb14d55358690c7c29e27521913f2a45bcd4d17/rai_agent_functions_api-1.0.3.tar.gz",
"platform": null,
"description": "# RAI Agent Functions API\r\n\r\nA Python SDK for Azure Functions API that provides Responsible AI (RAI) operations including prompt review and testcase generation.\r\n\r\n## Features\r\n\r\n- **Prompt Review**: Review and update prompts with AI-powered analysis\r\n- **Testcase Generation**: Generate comprehensive testcases from prompts\r\n- **Azure Integration**: Built for Azure Functions with proper authentication and error handling\r\n- **Async Support**: Full async/await support for non-blocking operations\r\n- **Type Safety**: Complete type hints and mypy compatibility\r\n\r\n## Installation\r\n\r\nInstall the package using pip:\r\n\r\n```bash\r\npip install rai-agent-functions-api\r\n```\r\n\r\n## Quick Start\r\n\r\n### Basic Usage\r\n\r\n```python\r\nfrom RAI_SDK.rai_agent_functions_api import RAIAgentFunctionsAPI\r\n\r\n# Initialize the client\r\nclient = RAIAgentFunctionsAPI(\r\n endpoint=\"https://your-function-app.azurewebsites.net/api\"\r\n)\r\n\r\n# Review a prompt\r\nreview_result = client.reviewer.post(\r\n body={\"prompt\": \"Generate a sales forecast for Q4\"}\r\n)\r\nprint(review_result)\r\n\r\n# Generate testcases\r\ntestcase_result = client.testcase.generator_post(\r\n body={\r\n \"prompt\": \"Create user authentication system\",\r\n \"number_of_testcases\": 5,\r\n \"user_categories\": [\"security\", \"usability\", \"performance\"]\r\n }\r\n)\r\nprint(testcase_result)\r\n```\r\n\r\n### Async Usage\r\n\r\n```python\r\nfrom RAI_SDK.rai_agent_functions_api.aio import RAIAgentFunctionsAPI\r\n\r\nasync def main():\r\n async with RAIAgentFunctionsAPI(\r\n endpoint=\"https://your-function-app.azurewebsites.net/api\"\r\n ) as client:\r\n # Async operations\r\n review_result = await client.reviewer.post(\r\n body={\"prompt\": \"Generate a sales forecast for Q4\"}\r\n )\r\n print(review_result)\r\n\r\nimport asyncio\r\nasyncio.run(main())\r\n```\r\n\r\n## API Reference\r\n\r\n### RAIAgentFunctionsAPI\r\n\r\nThe main client class for interacting with the RAI Agent Functions API.\r\n\r\n#### Parameters\r\n\r\n- `endpoint` (str): The base URL of your Azure Functions API. Default: `\"https://func-rai-agent-eus.azurewebsites.net/api\"`\r\n\r\n#### Methods\r\n\r\n##### reviewer.post(body)\r\n\r\nReview and update a prompt using AI analysis.\r\n\r\n**Parameters:**\r\n- `body` (dict): Request payload containing:\r\n - `prompt` (str): The prompt to review\r\n\r\n**Returns:**\r\n- dict: Response containing:\r\n - `review_of_updated_prompt`: Analysis of the updated prompt\r\n - `review_result`: Review findings and suggestions\r\n - `updated_result`: The improved prompt\r\n\r\n##### testcase.generator_post(body)\r\n\r\nGenerate testcases from a given prompt.\r\n\r\n**Parameters:**\r\n- `body` (dict): Request payload containing:\r\n - `prompt` (str): The prompt to generate testcases for\r\n - `number_of_testcases` (int): Number of testcases to generate\r\n - `user_categories` (list[str]): Categories for testcase generation\r\n\r\n**Returns:**\r\n- dict: Response containing:\r\n - `result`: Generated testcases and analysis\r\n\r\n## Configuration\r\n\r\n### Authentication\r\n\r\nThe SDK uses Azure Core's authentication mechanisms. You can configure authentication using:\r\n\r\n```python\r\nfrom azure.identity import DefaultAzureCredential\r\n\r\nclient = RAIAgentFunctionsAPI(\r\n endpoint=\"https://your-function-app.azurewebsites.net/api\",\r\n credential=DefaultAzureCredential()\r\n)\r\n```\r\n\r\n### Custom Headers\r\n\r\n```python\r\nclient = RAIAgentFunctionsAPI(\r\n endpoint=\"https://your-function-app.azurewebsites.net/api\",\r\n headers={\"Custom-Header\": \"value\"}\r\n)\r\n```\r\n\r\n### Retry Policy\r\n\r\n```python\r\nfrom azure.core.pipeline.policies import RetryPolicy\r\n\r\nclient = RAIAgentFunctionsAPI(\r\n endpoint=\"https://your-function-app.azurewebsites.net/api\",\r\n retry_policy=RetryPolicy(retry_total=3)\r\n)\r\n```\r\n\r\n## Error Handling\r\n\r\nThe SDK provides comprehensive error handling:\r\n\r\n```python\r\nfrom azure.core.exceptions import HttpResponseError, ClientAuthenticationError\r\n\r\ntry:\r\n result = client.reviewer.post(body={\"prompt\": \"test\"})\r\nexcept ClientAuthenticationError:\r\n print(\"Authentication failed\")\r\nexcept HttpResponseError as e:\r\n print(f\"HTTP error: {e.status_code} - {e.message}\")\r\nexcept Exception as e:\r\n print(f\"Unexpected error: {e}\")\r\n```\r\n\r\n## Development\r\n\r\n### Prerequisites\r\n\r\n- Python 3.8+\r\n- Azure Functions Core Tools (for local development)\r\n\r\n### Installation for Development\r\n\r\n```bash\r\ngit clone https://github.com/yourusername/rai-agent-functions-api.git\r\ncd rai-agent-functions-api\r\npip install -e \".[dev]\"\r\n```\r\n\r\n### Running Tests\r\n\r\n```bash\r\npytest\r\n```\r\n\r\n### Code Formatting\r\n\r\n```bash\r\nblack .\r\nflake8 .\r\nmypy .\r\n```\r\n\r\n## Examples\r\n\r\n### Complete Example\r\n\r\n```python\r\nfrom RAI_SDK.rai_agent_functions_api import RAIAgentFunctionsAPI\r\n\r\ndef main():\r\n # Initialize client\r\n client = RAIAgentFunctionsAPI()\r\n \r\n # Example 1: Review a business prompt\r\n business_prompt = \"Create a marketing strategy for our new product launch\"\r\n review_response = client.reviewer.post(body={\"prompt\": business_prompt})\r\n \r\n print(\"Original prompt:\", business_prompt)\r\n print(\"Review result:\", review_response.get(\"review_result\"))\r\n print(\"Updated prompt:\", review_response.get(\"updated_result\"))\r\n \r\n # Example 2: Generate testcases for a technical requirement\r\n technical_prompt = \"Implement user authentication with multi-factor authentication\"\r\n testcase_response = client.testcase.generator_post(\r\n body={\r\n \"prompt\": technical_prompt,\r\n \"number_of_testcases\": 3,\r\n \"user_categories\": [\"security\", \"usability\", \"edge-cases\"]\r\n }\r\n )\r\n \r\n print(\"Generated testcases:\", testcase_response.get(\"result\"))\r\n\r\nif __name__ == \"__main__\":\r\n main()\r\n```\r\n\r\n## License\r\n\r\nThis project is licensed under the MIT License - see the LICENSE file for details.\r\n\r\n## Contributing\r\n\r\n1. Fork the repository\r\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\r\n3. Commit your changes (`git commit -m 'Add some amazing feature'`)\r\n4. Push to the branch (`git push origin feature/amazing-feature`)\r\n5. Open a Pull Request\r\n\r\n## Support\r\n\r\nFor support and questions:\r\n\r\n- Create an issue on GitHub\r\n- Check the documentation\r\n- Review the examples\r\n\r\n## Changelog\r\n\r\n### 1.0.0\r\n\r\n- Initial release\r\n- Prompt review functionality\r\n- Testcase generation capabilities\r\n- Full async support\r\n- Comprehensive error handling\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Azure Functions API client for RAI (Responsible AI) operations including prompt review and testcase generation",
"version": "1.0.3",
"project_urls": {
"Bug Tracker": "https://github.com/DivyanshuMaq/rai-agent-functions-api/issues",
"Documentation": "https://github.com/DivyanshuMaq/rai-agent-functions-api#readme",
"Homepage": "https://github.com/DivyanshuMaq/rai-agent-functions-api",
"Repository": "https://github.com/DivyanshuMaq/rai-agent-functions-api.git"
},
"split_keywords": [
"azure",
" functions",
" api",
" responsible-ai",
" rai",
" prompt-review",
" testcase-generation"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "379af677c411b501a1a5aaa6f8e1a8b02cfb27273d7f79b563973419a705f90f",
"md5": "c84ba29dfde09a4b33eb1f6648553993",
"sha256": "34db17e5b9fb0eca66e62f64e9c09298de5b33494d15ca854700cbe7cf3bc603"
},
"downloads": -1,
"filename": "rai_agent_functions_api-1.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c84ba29dfde09a4b33eb1f6648553993",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 36840,
"upload_time": "2025-10-07T11:13:55",
"upload_time_iso_8601": "2025-10-07T11:13:55.872332Z",
"url": "https://files.pythonhosted.org/packages/37/9a/f677c411b501a1a5aaa6f8e1a8b02cfb27273d7f79b563973419a705f90f/rai_agent_functions_api-1.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "481804409d05892f47068a49ddb14d55358690c7c29e27521913f2a45bcd4d17",
"md5": "9a76f4a4c0e775e4bc103a90be2bc7bc",
"sha256": "2a3b09b028884aaf99e45ad5ed73d327846353d66abb92b0501ecd6e2f6f8968"
},
"downloads": -1,
"filename": "rai_agent_functions_api-1.0.3.tar.gz",
"has_sig": false,
"md5_digest": "9a76f4a4c0e775e4bc103a90be2bc7bc",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 31376,
"upload_time": "2025-10-07T11:13:57",
"upload_time_iso_8601": "2025-10-07T11:13:57.604263Z",
"url": "https://files.pythonhosted.org/packages/48/18/04409d05892f47068a49ddb14d55358690c7c29e27521913f2a45bcd4d17/rai_agent_functions_api-1.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-07 11:13:57",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "DivyanshuMaq",
"github_project": "rai-agent-functions-api",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "rai-agent-functions-api"
}
JSON
