chore: import upstream snapshot with attribution

examples/flows/integrations/unify-ai/eval_code_flow/code-eval-flow.flex.yaml

@@ -0,0 +1,6 @@
+$schema: https://azuremlschemas.azureedge.net/promptflow/latest/Flow.schema.json
+# flow is defined as python function
+entry: code_quality_unify_ai:CodeEvaluator
+environment:
+  # image: mcr.microsoft.com/azureml/promptflow/promptflow-python
+  python_requirements_txt: requirements.txt

examples/flows/integrations/unify-ai/eval_code_flow/code_quality_unify_ai.py

@@ -0,0 +1,61 @@
+import json
+from pathlib import Path
+from typing import TypedDict
+
+from jinja2 import Template
+
+from promptflow.core import OpenAIModelConfiguration
+from promptflow.core._flow import Prompty
+from promptflow.tracing import trace
+
+BASE_DIR = Path(__file__).absolute().parent
+
+# Derived from https://github.com/microsoft/promptflow/blob/main/examples/flex-flows/eval-code-quality/
+
+
+@trace
+def load_prompt(jinja2_template: str, code: str, examples: list) -> str:
+    """Load prompt function."""
+    with open(BASE_DIR / jinja2_template, "r", encoding="utf-8") as f:
+        tmpl = Template(f.read(), trim_blocks=True, keep_trailing_newline=True)
+        prompt = tmpl.render(code=code, examples=examples)
+        return prompt
+
+
+class Result(TypedDict):
+    correctness: float
+    readability: float
+    explanation: str
+
+
+class CodeEvaluator:
+    """ Uses Unify AI's LLM to evaluate a code block.
+    Note:
+    OpenAI client is being repurposed to call Unify AI API, Since Unify AI API is competable with OpenAI API.
+    This enables reusing Promptflow's OpenAI integration/support with Unify AI.
+
+    """
+    def __init__(self, model_config: OpenAIModelConfiguration):
+        self.model_config = model_config
+
+    def __call__(self, code: str) -> Result:
+        """Evaluate the code based on correctness, readability."""
+        prompty = Prompty.load(
+            source=BASE_DIR / "eval_code_quality.prompty",
+            model={"configuration": self.model_config},
+        )
+        output = prompty(code=code)
+        output = json.loads(output)
+        output = Result(**output)
+        return output
+
+    def __aggregate__(self, line_results: list) -> dict:
+        """Aggregate the results."""
+        total = len(line_results)
+        avg_correctness = sum(int(r["correctness"]) for r in line_results) / total
+        avg_readability = sum(int(r["readability"]) for r in line_results) / total
+        return {
+            "average_correctness": avg_correctness,
+            "average_readability": avg_readability,
+            "total": total,
+        }

examples/flows/integrations/unify-ai/eval_code_flow/eval_code_quality.prompty

@@ -0,0 +1,39 @@
+---
+name: Evaluate code quality
+description: Evaluate the quality of code snippet.
+model:
+  api: chat
+  configuration:
+    type: unify
+    model_name: llama-3.1-8b-chat
+    provider_name: together-ai
+  parameters:
+    temperature: 0.2
+inputs: 
+  code:
+    type: string
+sample: ${file:sample.json}
+---
+# system:
+You are an AI assistant. 
+You task is to evaluate the code based on correctness, readability.
+Only accepts valid JSON format response without extra prefix or postfix.
+
+# user:
+This correctness value should always be an integer between 1 and 5. So the correctness produced should be 1 or 2 or 3 or 4 or 5.
+This readability value should always be an integer between 1 and 5. So the readability produced should be 1 or 2 or 3 or 4 or 5.
+
+Here are a few examples:
+
+**Example 1**
+Code: print(\"Hello, world!\")
+OUTPUT:
+{
+    "correctness": 5,
+    "readability": 5,
+    "explanation": "The code is correct as it is a simple question and answer format. The readability is also good as the code is short and easy to understand."
+}
+
+For a given code, valuate the code based on correctness, readability:
+Code: {{code}}
+OUTPUT:

examples/flows/integrations/unify-ai/eval_code_flow/sample.json

@@ -0,0 +1,3 @@
+{
+    "code": "print(\"Hello, world!\")"
+}