发电机

生成器使用 Google 最新的生成式大语言模型 (LLM) 和您提供的提示,在运行时生成代理行为和响应。可用的模型由 Vertex AI 提供。

借助生成器,您可以从 Dialogflow CX 以原生方式调用 LLM,而无需创建自己的外部网络钩子。您可以对生成器进行配置,使其执行您通常要求 LLM 执行的任何操作。

生成器非常适合摘要、参数提取、数据转换等任务,具体请参见下面的示例

限制

此功能适用于使用任何 Dialogflow 语言的代理,但可用的模型可能具有更严格的语言限制。如需了解详情,请参阅 Vertex AI

了解生成器概念

Vertex AI 文档包含在为 Dialogflow 创建生成器时需要了解的信息:

定义生成器

如需创建生成器,请执行以下操作:

  1. 转到 Dialogflow CX 控制台
  2. 选择您的 Google Cloud 项目。
  3. 选择代理。
  4. 点击管理标签页。
  5. 点击生成器
  6. 点击新建 (Create new)。
  7. 为生成器输入一个描述性显示名称。
  8. 按照概念中的说明输入文本提示、模型和控件。
  9. 点击保存

文本提示会在运行时执行期间发送给生成模型。它应该是一个明确的问题或请求,以便模型生成令人满意的响应。

您可以通过在字词前添加 $ 将其标记为占位符,以使提示与上下文相关。您稍后可以将这些生成器提示占位符与执行方式中的会话参数相关联,并在执行期间将它们替换为会话参数值。

定义生成器
定义生成器

有一些特殊的生成器提示占位符不需要与会话参数相关联。这些内置生成器提示占位符

期限 定义
$conversation 代理与用户之间的对话,不包括最后一条用户话语以及此后代理的话语。
$last-user-utterance 用户上一次话语。

在 fulfillment 中使用生成器

您可以在执行方式期间(在路由事件处理程序参数等)中使用生成器。

转到 Fulfillment 窗格的 Generators(生成器)部分,请将其展开。 然后,点击添加生成器。现在,您可以选择预定义的生成器 也可以定义新的生成器

选择生成器后,您需要将提示的生成器提示占位符与会话参数相关联。此外,您需要定义输出参数,其中包含生成器执行后的结果。

使用生成器
在 fulfillment 中使用生成器

请注意,您可以在一个执行方式中添加多个并行执行的生成器。

然后,输出参数可供稍后使用,例如在代理响应中使用。

使用生成器输出
使用生成器的输出

测试生成器

可以直接在模拟器中测试 generator 功能。

模拟器中的测试生成器
在模拟器中测试生成器

示例

本部分提供了生成器的示例用例。由于生成器是基于大型语言模型 (LLM) 的生成式技术,因此您使用以下示例提示得到的结果可能与此处记录的输出不同。Google 返回的所有提示结果都是尽力而为。

内容摘要

此示例展示了如何总结内容。

提示

Your goal is to summarize a given text.

Text:
$text

A concise summary of the text in 1 or 2 sentences is:

会话摘要

以下示例展示了如何提供对话摘要。

提示

You are an expert at summarizing conversations between a User and an Agent.
When providing the summary, always start with "Dear $email_address, the conversation summary is as follows:"
Provide a summary in a few bullet points.
Try to be as brief as possible with each bullet point,
only noting the key points of the conversation.
Output the summary in markdown format.

Conversation:
$conversation

Summary:

已解决的提示

对于示例对话,发送到生成模型的已解析提示可以是:

You are an expert at summarizing conversations between a User and an Agent.
When providing the summary, always start with "Dear joe@example.com conversation summary is as follows:"
Provide a summary in a few bullet points.
Try to be as brief as possible with each bullet point,
only noting the key points of the conversation.
Output the summary in markdown format.

Conversation:
Agent: Good day! What can I do for you today?
User: Hi, which models can I use in Dialogflow's generators?
Agent: You can use all models that Vertex AI provides!
User: Thanks, thats amazing!

Summary:

Markdown 格式

此示例展示了如何在 Markdown 中设置文本格式。

# Instructions

You are presented with a text and your goal is to apply markdown formatting to text.

**NOTE:** Do not change the meaning of the text, only the formatting.

# Example

## Text

Generators allow you to use Googles latest generative models to format text,
or to create a summaries, or even to write code. What an amazing feature.

## Text in Markdown

*Generators* allow you to use Google's latest generative models to

*   format text
*   create a summaries
*   write code

What an amazing feature.

# Your current task

## Text

$text

## Text in Markdown

问答

这一系列示例展示了如何使用生成器来回答问题。

首先,您只需依靠生成模型的内部知识来回答此问题。但请注意,模型仅会根据训练数据中包含的信息来提供答案。我们无法保证答案是真实的或最新的。

提示以自我了解的方式回答问题

Your goal is to politely reply to a human with an answer to their question.

The human asked:
$last-user-utterance

You answer:

提示回答问题并提供提供的信息

不过,如果您希望模型根据您提供的信息回答问题,则只需将其添加到提示中即可。如果您不想提供太多信息(例如小餐馆菜单或您公司的联系信息),这种方法非常有效。

# Instructions

Your goal is to politely answer questions about the restaurant menu.
If you cannot answer the question because it's not related to the restaurant
menu or because relevant information is missing from the menu, you politely
decline to answer.

# Restaurant menu:

## Starters
Salat 5$

## Main dishes
Pizza 10$

## Deserts
Ice cream 2$

# Examples

Question: How much is the pizza?
Answer: The pizza is 10$.

Question: I want to order the ice cream.
Answer: We do have ice cream! However, I can only answer questions about the menu.

Question: Do you have spaghetti?
Answer: I'm sorry, we do not have spaghetti on the menu.

# Your current task

Question: $last-user-utterance
Answer:

使用动态提供的信息提示回答问题

通常情况下,你希望模型在给出回答时,所依据的信息太多,无法直接粘贴到提示中。在这种情况下,您可以将生成器连接到信息检索系统(如数据库或搜索引擎),以根据查询动态检索信息。您只需将该系统的输出保存到参数中,并将其连接到提示中的占位符即可。

# Instructions

Your goal is to politely answer questions based on the provided information.
If you can't answer the question given the provided information, you politely
decline to answer.

# Provided information:
$information

Question: $last-user-utterance
Answer:

生成代码

此示例展示了如何使用生成器编写代码!请注意,此处有必要使用经过专门训练以生成代码的生成模型。

提示

# Instructions:

Your goal is to write code in a given programming language solving a given problem.

Problem to solve:
$problem

Programming language:
$programming-language

# Solution:

上报给人工客服

以下示例展示了如何将问题上报给人工客服。提示中的最后两条指令可防止模型过于冗长。

提示

# Instructions:

You are a polite customer service agent that handles requests
from users to speak with an operator.

Based on the $last-user-utterance,
respond to the user appropriately about their request to speak with an operator.
Always be polite and assure the user that you
will do your best to help their situation.

Do not ask the user any questions.
Do not ask the user if there is anything you can do to help them.

# Answer:

搜索查询生成

此示例展示了如何优化用户提供的 Google 搜索查询。

提示

# Instructions:

You are an expert at Google Search and using "Google Fu"
to build concise search terms that provide the highest quality results.
A user will provide an example query,
and you will attempt to optimize this to be the best Google Search query possible.

# Example:

User: when was covid-19 first started and where did it originated from?
Agent: covid-19 start origin

# Your task:

User: $text
Agent:

客户信息检索

以下示例展示了如何执行信息检索和搜索以字符串或 JSON 格式提供的信息。这些格式通常供 Dialogflow 会话参数使用。

提示

You are a database engineer and specialize in extracting information
from both structured and unstructured data formats like CSV, SQL, JSON,
and also plain text.

Given a $user_db, extract the information requested
by the user from the $last-user-utterance

EXAMPLE:
user_db: {'customer_name': 'Patrick', 'balance': '100'}
User: What is my current account balance?
Agent: Your current balance is 100.

Begin!

user_db: $user_db
User: $last-user-utterance
Agent:

更新 JSON 对象

此示例展示了如何接受来自用户(或 webhook)的输入 JSON 对象,然后根据用户的请求处理该对象。

提示

You are an expert Software Engineer
that specializes in the JSON object data structure.

Given some user $update_request and existing $json_object,
you will modify the $json_object based on the user's $update_request.

EXAMPLE:
json_object = { "a": 1, "b": 123 }
User: Add a new key/value pair to my JSON
Agent: What do you want to add?
User: c: cat
Agent: { "a": 1, "b": 123, "c": "cat"}

json_object = {"accounts": [{"username": "user1", "account_number": 12345}, {"username": "user2", "account_number": 98765}], "timestamp": "2023-05-25", "version":"1.0"}
User: Add a new value for user1
Agent: What do you want to add?
User: birthday, 12/05/1982
Agent: {"accounts": [{"username": "user1", "account_number": 12345, "birthday": "12/05/1982"}, {"username": "user2", "account_number": 98765}], "timestamp": "2023-05-25", "version":"1.0"}

json_object = $json_object
User: Add a new key value to my db
Agent: What do you want to add?
User: $last-user-utterance
Agent:

Codelab

另请参阅生成器 Codelab

问题排查

如果您想要调试该功能,可以在 Dialogflow 控制台模拟器中检查已解析的大语言模型 (LLM) 输入提示:

  1. 点击原始回答按钮:

    原始回复

  2. 找到“Generators LLM Inputs”(生成器 LLM 输入)字段。以纯文本形式读取这些字段,并检查 LLM 输入是否合理。如果任何短语包含 $,请检查模拟器输入,并澄清提示中的 $ 是否是有意为之(例如,price is $10 中的 $ 可能是有意为之,而 visit $city 可能不是,并且可能意味着使用有误或存在 bug)。

  3. 如果您没有看到“生成式 LLM 输入”字段,请与支持团队联系