开发 Prompty

实验性功能

这是一个实验性功能，随时可能更改。了解更多。

Promptflow 引入了 prompty 功能，旨在简化客户的提示模板开发。

创建 Prompty

Prompty 规范

在 Promptflow 中，扩展名为 .prompty 的文件被识别为 prompty。这种独特的文件类型有助于提示模板的开发。

Prompty 是一个 Markdown 文件，其前言以 YAML 结构化，封装了一系列元数据字段，这些字段对于定义模型的配置和 prompty 的输入至关重要。前言之后是提示模板，以 Jinja 格式表达。

前言中的字段

字段	描述
name	提示的名称。
描述	提示的描述。
模型	详细说明 prompty 的模型配置，包括连接信息和 LLM 请求的参数。
输入	传递给提示模板的输入定义。
输出	指定 prompty 结果中的字段。（仅当 response_format 为 json_object 时有效）。
示例	提供包含输入样本数据的字典或 JSON 文件。

---
name: Basic Prompt
description: A basic prompt that uses the GPT-3 chat API to answer questions
model:
  api: chat
  configuration:
    type: azure_openai
    azure_deployment: gpt-35-turbo
    connection: azure_open_ai_connection
  parameters:
    max_tokens: 128
    temperature: 0.2
inputs:
  first_name:
    type: string
  last_name:
    type: string
  question:
    type: string
sample:
  first_name: John
  last_name: Doe
  question: Who is the most famous person in the world?
---
system:
You are an AI assistant who helps people find information.
As the assistant, you answer questions briefly, succinctly,
and in a personable manner using markdown and even add some personal flair with appropriate emojis.

# Safety
- You **should always** reference factual statements to search results based on [relevant documents]
- Search results based on [relevant documents] may be incomplete or irrelevant. You do not make assumptions
# Customer
You are helping {{first_name}} {{last_name}} to find answers to their questions.
Use their name to address them in your responses.

user:
{{question}}

加载 Prompty

Prompty 的设计考虑了灵活性，允许用户在加载过程中覆盖默认模型配置。

Azure OpenAI

---
name: Basic Prompt
description: A basic prompt that uses the GPT-3 chat API to answer questions
model:
  api: chat
  configuration:
    type: azure_openai
    azure_deployment: gpt-35-turbo
    api_key: ${env:AZURE_OPENAI_API_KEY}
    api_version: ${env:AZURE_OPENAI_API_VERSION}
    azure_endpoint: ${env:AZURE_OPENAI_ENDPOINT}
  parameters:
    max_tokens: 128
    temperature: 0.2
inputs:
  first_name:
    type: string
  last_name:
    type: string
  question:
    type: string
sample:
  first_name: John
  last_name: Doe
  question: Who is the most famous person in the world?
---
system:
You are an AI assistant who helps people find information.
As the assistant, you answer questions briefly, succinctly,
and in a personable manner using markdown and even add some personal flair with appropriate emojis.

# Safety
- You **should always** reference factual statements to search results based on [relevant documents]
- Search results based on [relevant documents] may be incomplete or irrelevant. You do not make assumptions
# Customer
You are helping {{first_name}} {{last_name}} to find answers to their questions.
Use their name to address them in your responses.

user:
{{question}}

用户可以指定替代参数或利用环境变量来调整模型设置。格式 ${env:ENV_NAME} 用于引用环境变量。

• 使用字典

  from promptflow.core import Prompty
  
  # Load prompty with dict override
  override_model = {
      "configuration": {
          "api_key": "${env:AZURE_OPENAI_API_KEY}",
          "api_version": "${env:AZURE_OPENAI_API_VERSION}",
          "azure_endpoint": "${env:AZURE_OPENAI_ENDPOINT}"
      },
      "parameters": {"max_tokens": 512}
  }
  prompty = Prompty.load(source="path/to/prompty.prompty", model=override_model)
  

• 使用 AzureOpenAIModelConfiguration

  from promptflow.core import Prompty, AzureOpenAIModelConfiguration
  
  # Load prompty with AzureOpenAIModelConfiguration override
  configuration = AzureOpenAIModelConfiguration(
      azure_deployment="gpt-3.5-turbo",
      api_key="${env:AZURE_OPENAI_API_KEY}",
      api_version="${env:AZURE_OPENAI_API_VERSION}",
      azure_endpoint="${env:AZURE_OPENAI_ENDPOINT}"
  )
  override_model = {
      "configuration": configuration,
      "parameters": {"max_tokens": 512}
  }
  prompty = Prompty.load(source="path/to/prompty.prompty", model=override_model)
  

OpenAI

---
name: Basic Prompt
description: A basic prompt that uses the GPT-3 chat API to answer questions
model:
  api: chat
  configuration:
    type: openai
    model: gpt-3.5-turbo
    api_key: ${env:OPENAI_API_KEY}
    base_url: ${env:OPENAI_BASE_URL}
  parameters:
    max_tokens: 128
    temperature: 0.2
inputs:
  first_name:
    type: string
  last_name:
    type: string
  question:
    type: string
sample:
  first_name: John
  last_name: Doe
  question: Who is the most famous person in the world?
---
system:
You are an AI assistant who helps people find information.
As the assistant, you answer questions briefly, succinctly,
and in a personable manner using markdown and even add some personal flair with appropriate emojis.

# Safety
- You **should always** reference factual statements to search results based on [relevant documents]
- Search results based on [relevant documents] may be incomplete or irrelevant. You do not make assumptions
# Customer
You are helping {{first_name}} {{last_name}} to find answers to their questions.
Use their name to address them in your responses.

user:
  {{question}}

用户可以指定替代参数或利用环境变量来调整模型设置。格式 ${env:ENV_NAME} 用于引用环境变量。

• 使用字典

  from promptflow.core import Prompty
  
  # Load prompty with dict override
  override_model = {
      "configuration": {
          "api_key": "${env:OPENAI_API_KEY}",
          "base_url": "${env:OPENAI_BASE_URL}",
      },
      "parameters": {"max_tokens": 512}
  }
  prompty = Prompty.load(source="path/to/prompty.prompty", model=override_model)
  

• 使用 OpenAIModelConfiguration

  from promptflow.core import Prompty, OpenAIModelConfiguration
  
  # Load prompty with OpenAIModelConfiguration override
  configuration = OpenAIModelConfiguration(
      model="gpt-35-turbo",
      base_url="${env:OPENAI_BASE_URL}",
      api_key="${env:OPENAI_API_KEY}",
  )
  override_model = {
      "configuration": configuration,
      "parameters": {"max_tokens": 512}
  }
  prompty = Prompty.load(source="path/to/prompty.prompty", model=override_model)
  

执行 Prompty

Promptflow 提供多种执行 prompty 的方法，以满足不同场景下客户的需求。

直接函数调用

加载后，Prompty 对象可以直接作为函数调用，返回 LLM 响应中第一个选择的内容。

from promptflow.core import Prompty

prompty_obj = Prompty.load(source="path/to/prompty.prompty")
result = prompty_obj(first_name="John", last_name="Doh", question="What is the capital of France?")

测试 Prompty

流测试

使用输入或示例文件执行和测试您的 Prompty。

CLI

# Test prompty with default inputs
pf flow test --flow path/to/prompty.prompty

# Test prompty with specified inputs
pf flow test --flow path/to/prompty.prompty --inputs first_name=John last_name=Doh question="What is the capital of France?"

# Test prompty with sample file
pf flow test --flow path/to/prompty.prompty --inputs path/to/sample.json

终端中将提供一个跟踪链接，用于可视化此命令的内部执行详细信息。对于 Prompty，用户可以在跟踪 UI 中找到生成的提示、LLM 请求参数和其他信息。了解更多。

SDK

from promptflow.client import PFClient

pf = PFClient()

# Test prompty with specified inputs
result = pf.test(flow="path/to/prompty.prompty", inputs={"first_name": "John", "last_name": "Doh", "question": "What is the capital of France?"})

# Test prompty with sample file
result = pf.test(flow="path/to/prompty.prompty", inputs="path/to/sample.json")

使用交互模式测试

Promptflow CLI 还提供交互式聊天会话以测试聊天流。

pf flow test --flow path/to/prompty.prompty --interactive

---
name: Basic Prompt With Chat History
description: A basic prompt that uses the GPT-3 chat API to answer questions
model:
  api: chat
  configuration:
    type: azure_open_ai
    azure_deployment: gpt-35-turbo
    connection: azure_open_ai_connection

  parameters:
    max_tokens: 128
    temperature: 0.2
inputs:
  first_name:
    type: string
  last_name:
    type: string
  question:
    type: string
   chat_history:
    type: list
sample:
  first_name: John
  last_name: Doe
  question: Who is the most famous person in the world?
  chat_history: [ { "role": "user", "content": "what's the capital of France?" }, { "role": "assistant", "content": "Paris" } ]
---
system:
You are an AI assistant who helps people find information.
As the assistant, you answer questions briefly, succinctly,
and in a personable manner using markdown and even add some personal flair with appropriate emojis.

# Safety
- You **should always** reference factual statements to search results based on [relevant documents]
- Search results based on [relevant documents] may be incomplete or irrelevant. You do not make assumptions
# Customer
You are helping {{first_name}} {{last_name}} to find answers to their questions.
Use their name to address them in your responses.

Here is a chat history you had with the user:
{% for item in chat_history %}
   {{item.role}}: {{item.content}}
{% endfor %}

user:
  {{question}}

终端输出

批量运行 Prompty

CLI

要在 Promptflow 中执行 Prompty 的批量运行，您可以使用以下命令

pf run create --flow path/to/prompty.prompty --data path/to/inputs.jsonl

SDK

要在 Promptflow 中执行 Prompty 的批量运行，您可以使用以下 SDK

from promptflow.client import PFClient

pf = PFClient() 
# create run
prompty_run = pf.run(
    flow="path/to/prompty.prompty",
    data="path/to/inputs.jsonl",
)
pf.stream(prompty_run)

在执行批量运行时，Promptflow 提供了一个跟踪 UI 来可视化运行的内部执行详细信息。此功能允许您跟踪数据文件中每一行的执行详细信息，包括提示和 LLM 请求参数。了解更多。

例如，在启动 Prompt flow 服务后，您可能会在终端中看到如下输出

Prompt flow service has started...
You can view the traces from local: http://127.0.0.1:49240/v1.0/ui/traces/?#run=prompty_variant_0_20240424_152808_282517
[2024-04-24 15:28:12,597][promptflow._sdk._orchestrator.run_submitter][INFO] - Submitting run prompty_variant_0_20240424_152808_282517, log path: .promptflow\.runs\prompty_variant_0_20240424_152808_282517\logs.txt

跟踪 UI 将记录数据文件中每一行的执行详细信息，提供批量运行性能和结果的全面视图。