Auf dieser Seite wird die empfohlene Struktur für das Verfassen effektiver Prompts für Ihre Daten-Agents für die Conversational Analytics API beschrieben, die eine Verbindung zu BigQuery-Daten herstellen. Diese Prompts sind Kontext, den Sie als Strings mit dem Parameter system_instruction definieren.
Beispiele für wichtige Komponenten von Systemanweisungen
Die folgenden Abschnitte enthalten Beispiele für wichtige Komponenten von Systemanweisungen in BigQuery. Dazu gehören die folgenden Schlüssel:
tablesfieldsmeasuresgolden_queriesgolden_action_plansrelationshipsglossariesadditional_descriptions
Beschreibungen dieser wichtigen Komponenten finden Sie auf der Dokumentationsseite Agent-Verhalten mit selbst erstelltem Kontext steuern.
Daten mit tables beschreiben
Der folgende YAML-Codeblock zeigt die grundlegende Struktur für den Schlüssel tables für die Tabelle bigquery-public-data.thelook_ecommerce.orders:
- tables:
- table:
- name: bigquery-public-data.thelook_ecommerce.orders
- description: Data for customer orders in The Look fictitious e-commerce store.
- synonyms:
- sales
- orders_data
- tags:
- ecommerce
- transaction
Häufig verwendete Felder mit fields beschreiben
Im folgenden YAML-Beispielcode werden die wichtigsten Felder wie order_id, status, created_at, num_of_items und earnings für die Tabelle orders beschrieben:
- tables:
- table:
- name: bigquery-public-data.thelook_ecommerce.orders
- fields:
- field:
- name: order_id
- description: The unique identifier for each customer order.
- field:
- name: user_id
- description: The unique identifier for each customer.
- field:
- name: status
- description: The current status of the order.
- sample_values:
- complete
- shipped
- returned
- field:
- name: created_at
- description: The timestamp when the order was created.
- field:
- name: num_of_items
- description: The total number of items in the order.
- aggregations:
- sum
- avg
- field:
- name: earnings
- description: The sales amount for the order.
- aggregations:
- sum
- avg
Geschäftliche Messwerte mit measures definieren
Sie können beispielsweise einen profit-Messwert als Berechnung des Umsatzes abzüglich der Kosten definieren:
- tables:
- table:
- name: bigquery-public-data.thelook_ecommerce.orders
- measures:
- measure:
- name: profit
- description: Raw profit (earnings minus cost).
- exp: earnings - cost
- synonyms: gains
Genauigkeit mit golden_queries verbessern
Sie können beispielsweise Gold-Abfragen für häufige Analysen für die Daten in der Tabelle orders so definieren:
- tables:
- table:
- golden_queries:
- golden_query:
- natural_language_query: How many orders are there?
- sql_query: SELECT COUNT(*) FROM sqlgen-testing.thelook_ecommerce.orders
- golden_query:
- natural_language_query: How many orders were shipped?
- sql_query: >-
SELECT COUNT(*) FROM sqlgen-testing.thelook_ecommerce.orders
WHERE status = 'shipped'
Mehrstufige Aufgaben mit golden_action_plans skizzieren
Sie können beispielsweise einen Aktionsplan definieren, um Aufschlüsselungen von Bestellungen nach Altersgruppe zu präsentieren, und Details zur SQL-Abfrage und zu den Schritten für die Visualisierung einfügen:
- tables:
- table:
- golden_action_plans:
- golden_action_plan:
- natural_language_query: Show me the number of orders broken down by age group.
- action_plan:
- step: >-
Run a SQL query that joins the table
sqlgen-testing.thelook_ecommerce.orders and
sqlgen-testing.thelook_ecommerce.users to get a
breakdown of order count by age group.
- step: >-
Create a vertical bar plot using the retrieved data,
with one bar per age group.
Tabellenverknüpfungen mit relationships definieren
Sie können beispielsweise eine orders_to_user-Beziehung zwischen der Tabelle bigquery-public-data.thelook_ecommerce.orders und der Tabelle bigquery-public-data.thelook_ecommerce.users so definieren:
- relationships:
- relationship:
- name: orders_to_user
- description: >-
Connects customer order data to user information with the user_id and id fields to allow an aggregated view of sales by customer demographics.
- relationship_type: many-to-one
- join_type: left
- left_table: bigquery-public-data.thelook_ecommerce.orders
- right_table: bigquery-public-data.thelook_ecommerce.users
- relationship_columns:
- left_column: user_id
- right_column: id
Geschäftsbedingungen mit glossaries erläutern
Sie können beispielsweise Begriffe wie allgemeine Unternehmensstatus und „OMPF“ (Order Management and Product Fulfillment) entsprechend Ihrem spezifischen geschäftlichen Kontext so definieren:
- glossaries:
- glossary:
- term: complete
- description: Represents an order status where the order has been completed.
- synonyms: 'finish, done, fulfilled'
- glossary:
- term: shipped
- description: Represents an order status where the order has been shipped to the customer.
- glossary:
- term: returned
- description: Represents an order status where the customer has returned the order.
- glossary:
- term: OMPF
- description: Order Management and Product Fulfillment
Weitere Anweisungen mit additional_descriptions einfügen
Mit dem Schlüssel additional_descriptions können Sie beispielsweise Informationen zu Ihrer Organisation angeben:
- additional_descriptions:
- text: All the sales data pertains to The Look, a fictitious ecommerce store.
- text: 'Orders can be of three categories: food, clothes, and electronics.'
Beispiel: Systemanweisungen in BigQuery
Das folgende Beispiel zeigt Beispielsystemanweisungen für einen fiktiven Agent für die Vertriebsanalyse:
- system_instruction: >-
You are an expert sales analyst for a fictitious ecommerce store. You will answer questions about sales, orders, and customer data. Your responses should be concise and data-driven.
- tables:
- table:
- name: bigquery-public-data.thelook_ecommerce.orders
- description: Data for orders in The Look, a fictitious ecommerce store.
- synonyms: sales
- tags: 'sale, order, sales_order'
- fields:
- field:
- name: order_id
- description: The unique identifier for each customer order.
- field:
- name: user_id
- description: The unique identifier for each customer.
- field:
- name: status
- description: The current status of the order.
- sample_values:
- complete
- shipped
- returned
- field:
- name: created_at
- description: >-
The date and time at which the order was created in timestamp
format.
- field:
- name: returned_at
- description: >-
The date and time at which the order was returned in timestamp
format.
- field:
- name: num_of_items
- description: The total number of items in the order.
- aggregations: 'sum, avg'
- field:
- name: earnings
- description: The sales revenue for the order.
- aggregations: 'sum, avg'
- field:
- name: cost
- description: The cost for the items in the order.
- aggregations: 'sum, avg'
- measures:
- measure:
- name: profit
- description: Raw profit (earnings minus cost).
- exp: earnings - cost
- synonyms: gains
- golden_queries:
- golden_query:
- natural_language_query: How many orders are there?
- sql_query: SELECT COUNT(*) FROM sqlgen-testing.thelook_ecommerce.orders
- golden_query:
- natural_language_query: How many orders were shipped?
- sql_query: >-
SELECT COUNT(*) FROM sqlgen-testing.thelook_ecommerce.orders
WHERE status = 'shipped'
- golden_action_plans:
- golden_action_plan:
- natural_language_query: Show me the number of orders broken down by age group.
- action_plan:
- step: >-
Run a SQL query that joins the table
sqlgen-testing.thelook_ecommerce.orders and
sqlgen-testing.thelook_ecommerce.users to get a
breakdown of order count by age group.
- step: >-
Create a vertical bar plot using the retrieved data,
with one bar per age group.
- table:
- name: bigquery-public-data.thelook_ecommerce.users
- description: Data for users in The Look, a fictitious ecommerce store.
- synonyms: customers
- tags: 'user, customer, buyer'
- fields:
- field:
- name: id
- description: The unique identifier for each user.
- field:
- name: first_name
- description: The first name of the user.
- tag: person
- sample_values: 'alex, izumi, nur'
- field:
- name: last_name
- description: The first name of the user.
- tag: person
- sample_values: 'warmer, stilles, smith'
- field:
- name: age_group
- description: The age demographic group of the user.
- sample_values:
- 18-24
- 25-34
- 35-49
- 50+
- field:
- name: email
- description: The email address of the user.
- tag: contact
- sample_values: '222larabrown@gmail.com, cloudysanfrancisco@gmail.com'
- golden_queries:
- golden_query:
- natural_language_query: How many unique customers are there?
- sql_query: >-
SELECT COUNT(DISTINCT id) FROM
bigquery-public-data.thelook_ecommerce.users
- golden_query:
- natural_language_query: How many users in the 25-34 age group have a cymbalgroup email address?
- sql_query: >-
SELECT COUNT(DISTINCT id) FROM
bigquery-public-data.thelook_ecommerce.users WHERE users.age_group =
'25-34' AND users.email LIKE '%@cymbalgroup.com';
- relationships:
- relationship:
- name: orders_to_user
- description: >-
Connects customer order data to user information with the user_id and id fields to allow an aggregated view of sales by customer demographics.
- relationship_type: many-to-one
- join_type: left
- left_table: bigquery-public-data.thelook_ecommerce.orders
- right_table: bigquery-public-data.thelook_ecommerce.users
- relationship_columns:
- left_column: user_id
- right_column: id
- glossaries:
- glossary:
- term: complete
- description: Represents an order status where the order has been completed.
- synonyms: 'finish, done, fulfilled'
- glossary:
- term: shipped
- description: Represents an order status where the order has been shipped to the customer.
- glossary:
- term: returned
- description: Represents an order status where the customer has returned the order.
- glossary:
- term: OMPF
- description: Order Management and Product Fulfillment
- additional_descriptions:
- text: All the sales data pertains to The Look, a fictitious ecommerce store.
- text: 'Orders can be of three categories: food, clothes, and electronics.'