Users/singankit/promptflow eval

examples/flows/chat/chat-basic-code-first/README.md

@@ -0,0 +1,70 @@
+# Basic chat (code-first)
+This example shows how to create a basic chat flow using code-first approach. It demonstrates how to create a chatbot that can remember previous interactions and use the conversation history to generate next message.
+
+Tools used in this flow：
+- `llm` tool
+
+## Prerequisites
+
+Install promptflow sdk and other dependencies in this folder:
+```bash
+pip install -r requirements.txt
+```
+
+## What you will learn
+
+In this flow, you will learn
+- how to compose a chat flow.
+- prompt template format of LLM tool chat api. Message delimiter is a separate line containing role name and colon: "system:", "user:", "assistant:".
+See <a href="https://platform.openai.com/docs/api-reference/chat/create#chat/create-role" target="_blank">OpenAI Chat</a> for more about message role.
+    ```jinja
+    system:
+    You are a chatbot having a conversation with a human.
+
+    user:
+    {{question}}
+    ```
+- how to consume chat history in prompt.
+    ```jinja
+    {% for item in chat_history %}
+    user:
+    {{item.inputs.question}}
+    assistant:
+    {{item.outputs.answer}}
+    {% endfor %}
+    ```
+
+## Getting started
+
+### 1 Create connection for LLM tool to use
+Go to "Prompt flow" "Connections" tab. Click on "Create" button, select one of LLM tool supported connection types and fill in the configurations.
+
+Currently, there are two connection types supported by LLM tool: "AzureOpenAI" and "OpenAI". If you want to use "AzureOpenAI" connection type, you need to create an Azure OpenAI service first. Please refer to [Azure OpenAI Service](https://azure.microsoft.com/en-us/products/cognitive-services/openai-service/) for more details. If you want to use "OpenAI" connection type, you need to create an OpenAI account first. Please refer to [OpenAI](https://platform.openai.com/) for more details.
+
+```bash
+# Override keys with --set to avoid yaml file changes
+pf connection create --file ../../../connections/azure_openai.yml --set api_key=<your_api_key> api_base=<your_api_base> --name open_ai_connection
+```
+
+Note in [flow.dag.yaml](flow.dag.yaml) we are using connection named `open_ai_connection`.
+```bash
+# show registered connection 
+pf connection show --name open_ai_connection
+```
+
+### 2 Start chatting
+
+```bash
+# run chat flow with default question in flow.dag.yaml
+pf flow test --flow . 
+
+# run chat flow with new question
+pf flow test --flow . --inputs question="What's Azure Machine Learning?"
+
+# start a interactive chat session in CLI
+pf flow test --flow . --interactive
+
+# start a interactive chat session in CLI with verbose info
+pf flow test --flow . --interactive --verbose
+```
+

examples/flows/chat/chat-basic-code-first/chat.jinja2

@@ -0,0 +1,12 @@
+system:
+You are a helpful assistant.
+
+{% for item in chat_history %}
+user:
+{{item.inputs.question}}
+assistant:
+{{item.outputs.answer}}
+{% endfor %}
+
+user:
+{{question}}

examples/flows/chat/chat-basic-code-first/data.jsonl

@@ -0,0 +1,2 @@
+{"question": "What is Prompt flow?"}
+{"question": "What is ChatGPT?"}

examples/flows/chat/chat-basic-code-first/flow.dag.yaml

@@ -0,0 +1,2 @@
+$schema: https://azuremlschemas.azureedge.net/promptflow/latest/Flow.schema.json
+entry: flow.flow_entry

examples/flows/chat/chat-basic-code-first/flow.py

@@ -0,0 +1,53 @@
+from dataclasses import dataclass
+from jinja2 import Template
+from pathlib import Path
+from promptflow import trace, PFClient
+from promptflow.tools.aoai import chat
+
+
+BASE_DIR = Path(__file__).absolute().parent
+
+
+@trace
+def load_prompt(jinja2_template: str, question: str, chat_history: 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(question=question, chat_history=chat_history)
+        return prompt
+
+
+@dataclass
+class Result:
+    answer: str
+
+
+@trace
+def flow_entry(question: str='What is ChatGPT?', chat_history: list = []) -> Result:
+    """Flow entry function."""
+    from promptflow._sdk._configuration import Configuration
+
+    prompt = load_prompt("chat.jinja2", question, chat_history)
+    config = Configuration.get_instance()
+    # TODO: create your own config.json
+    workspace_config = config._get_workspace_from_config(path="./config.json")
+    config.set_config(
+        Configuration.CONNECTION_PROVIDER,
+        "azureml:" + workspace_config
+    )
+    pf = PFClient()
+    connection = pf.connections.get("open_ai_connection", with_secrets=True) # TODO: add connection to function inputs
+    output = chat(
+        connection=connection,
+        prompt=prompt,
+        deployment_name="gpt-35-turbo",
+        max_tokens=256,
+        temperature=0.7,
+    )
+    # TODO: Result(answer=output)
+    return dict(answer=output)
+
+
+if __name__ == "__main__":
+    result = flow_entry("What's Azure Machine Learning?", [])
+    print(result)

examples/flows/chat/chat-basic-code-first/requirements.txt

@@ -0,0 +1,2 @@
+--extra-index-url https://azuremlsdktestpypi.azureedge.net/test-promptflow/
+promptflow[azure]==0.0.116642424

examples/flows/evaluation/eval-code-quality/.env.example

@@ -0,0 +1,3 @@
+AZURE_OPENAI_API_KEY=<your_AOAI_key>
+AZURE_OPENAI_API_BASE=<your_AOAI_endpoint>
+AZURE_OPENAI_API_TYPE=azure

examples/flows/evaluation/eval-code-quality/README.md

@@ -0,0 +1,30 @@
+# Eval Code Quality
+A example flow shows how to evaluate the quality of code snippet.
+
+## Prerequisites
+
+Install promptflow sdk and other dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+## Run flow
+
+- Prepare your Azure Open AI resource follow this [instruction](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal) and get your `api_key` if you don't have one.
+
+- Setup environment variables
+
+Ensure you have put your azure open ai endpoint key in [.env](.env) file. You can create one refer to this [example file](.env.example).
+
+```bash
+cat .env
+```
+
+- Test flow/node
+```bash
+# correct
+pf flow test --flow . --inputs code='print(\"Hello, world!\")'
+
+# incorrect
+pf flow test --flow . --inputs code='print("Hello, world!")'
+```

examples/flows/evaluation/eval-code-quality/flow.dag.yaml

@@ -0,0 +1,3 @@
+$schema: https://azuremlschemas.azureedge.net/promptflow/latest/Flow.schema.json
+# flow is defined as python function
+entry: flow:eval_code

examples/flows/evaluation/eval-code-quality/flow.py

@@ -0,0 +1,76 @@
+import json
+import os
+from dataclasses import dataclass
+from pathlib import Path
+
+from dotenv import load_dotenv
+from jinja2 import Template
+
+from promptflow import trace
+from promptflow._sdk.entities import AzureOpenAIConnection
+from promptflow.tools.aoai import AzureOpenAI
+
+BASE_DIR = Path(__file__).absolute().parent
+
+
+@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
+
+
+@dataclass
+class Result:
+    correctness: float
+    readability: float
+    explanation: str
+
+
+@trace
+def eval_code(code: str) -> Result:
+    """Evaluate the code based on correctness, readability, and adherence to best practices."""
+    examples = [
+        {
+            "code": 'print("Hello, world!")',
+            "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.",
+        }
+    ]
+
+    prompt = load_prompt("prompt.md", code, examples)
+
+    if "AZURE_OPENAI_API_KEY" not in os.environ:
+        # load environment variables from .env file
+        load_dotenv()
+
+    if "AZURE_OPENAI_API_KEY" not in os.environ:
+        raise Exception("Please specify environment variables: AZURE_OPENAI_API_KEY")
+
+    connection = AzureOpenAIConnection(
+        api_key=os.environ["AZURE_OPENAI_API_KEY"],
+        api_base=os.environ["AZURE_OPENAI_API_BASE"],
+        api_version=os.environ.get("AZURE_OPENAI_API_VERSION", "2023-07-01-preview"),
+    )
+
+    output = AzureOpenAI(connection).chat(
+        prompt=prompt,
+        deployment_name="gpt-35-turbo",
+        max_tokens=256,
+        temperature=0.7,
+    )
+    output = Result(**json.loads(output))
+    return output
+
+
+if __name__ == "__main__":
+    from promptflow._trace._start_trace import start_trace  # TODO move to public API
+
+    start_trace()
+
+    result = eval_code('print("Hello, world!")')
+    print(result)

examples/flows/evaluation/eval-code-quality/prompt.md

@@ -0,0 +1,20 @@
+
+# system:
+You are an AI assistant. 
+You task is to evaluate the code based on correctness, readability.
+
+
+# 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 correctness produced should be 1 or 2 or 3 or 4 or 5.
+
+Here are a few examples:
+{% for ex in examples %}
+Code: {{ex.code}}
+OUTPUT:
+{"correctness": "{{ex.correctness}}", "readability": "{{ex.readability}}", "explanation":"{{ex.explanation}}"}
+{% endfor %}
+
+For a given code, valuate the code based on correctness, readability:
+Code: {{code}}
+OUTPUT:

examples/flows/evaluation/eval-code-quality/requirement.txt

@@ -0,0 +1,2 @@
+promptflow
+promptflow-tools

examples/flows/standard/basic-code-first/.env.example

@@ -0,0 +1,3 @@
+AZURE_OPENAI_API_KEY=<your_AOAI_key>
+AZURE_OPENAI_API_BASE=<your_AOAI_endpoint>
+AZURE_OPENAI_API_TYPE=azure