feat: update docs with new approach to consume Platform Actions (#3675)

This commit is contained in:
Lucas Gomide
2025-10-09 09:17:09 -03:00
committed by GitHub
parent 458f56fb33
commit 28a8a7e6fa
82 changed files with 7709 additions and 2690 deletions

View File

@@ -26,7 +26,7 @@ Before using the Google Sheets integration, ensure you have:
2. Find **Google Sheets** in the Authentication Integrations section
3. Click **Connect** and complete the OAuth flow
4. Grant the necessary permissions for spreadsheet access
5. Copy your Enterprise Token from [Account Settings](https://app.crewai.com/crewai_plus/settings/account)
5. Copy your Enterprise Token from [Integration Settings](https://app.crewai.com/crewai_plus/settings/integrations)
### 2. Install Required Package
@@ -37,64 +37,74 @@ uv add crewai-tools
## Available Actions
<AccordionGroup>
<Accordion title="GOOGLE_SHEETS_GET_ROW">
**Description:** Get rows from a Google Sheets spreadsheet.
<Accordion title="google_sheets/get_spreadsheet">
**Description:** Retrieve properties and data of a spreadsheet.
**Parameters:**
- `spreadsheetId` (string, required): Spreadsheet - Use Connect Portal Workflow Settings to allow users to select a spreadsheet. Defaults to using the first worksheet in the selected spreadsheet.
- `limit` (string, optional): Limit rows - Limit the maximum number of rows to return.
- `spreadsheetId` (string, required): The ID of the spreadsheet to retrieve.
- `ranges` (array, optional): The ranges to retrieve from the spreadsheet.
- `includeGridData` (boolean, optional): True if grid data should be returned. Default: false
- `fields` (string, optional): The fields to include in the response. Use this to improve performance by only returning needed data.
</Accordion>
<Accordion title="GOOGLE_SHEETS_CREATE_ROW">
**Description:** Create a new row in a Google Sheets spreadsheet.
<Accordion title="google_sheets/get_values">
**Description:** Returns a range of values from a spreadsheet.
**Parameters:**
- `spreadsheetId` (string, required): Spreadsheet - Use Connect Portal Workflow Settings to allow users to select a spreadsheet. Defaults to using the first worksheet in the selected spreadsheet..
- `worksheet` (string, required): Worksheet - Your worksheet must have column headers.
- `additionalFields` (object, required): Fields - Include fields to create this row with, as an object with keys of Column Names. Use Connect Portal Workflow Settings to allow users to select a Column Mapping.
- `spreadsheetId` (string, required): The ID of the spreadsheet to retrieve data from.
- `range` (string, required): The A1 notation or R1C1 notation of the range to retrieve values from.
- `valueRenderOption` (string, optional): How values should be represented in the output. Options: FORMATTED_VALUE, UNFORMATTED_VALUE, FORMULA. Default: FORMATTED_VALUE
- `dateTimeRenderOption` (string, optional): How dates, times, and durations should be represented in the output. Options: SERIAL_NUMBER, FORMATTED_STRING. Default: SERIAL_NUMBER
- `majorDimension` (string, optional): The major dimension that results should use. Options: ROWS, COLUMNS. Default: ROWS
</Accordion>
<Accordion title="google_sheets/update_values">
**Description:** Sets values in a range of a spreadsheet.
**Parameters:**
- `spreadsheetId` (string, required): The ID of the spreadsheet to update.
- `range` (string, required): The A1 notation of the range to update.
- `values` (array, required): The data to be written. Each array represents a row.
```json
{
"columnName1": "columnValue1",
"columnName2": "columnValue2",
"columnName3": "columnValue3",
"columnName4": "columnValue4"
}
[
["Value1", "Value2", "Value3"],
["Value4", "Value5", "Value6"]
]
```
- `valueInputOption` (string, optional): How the input data should be interpreted. Options: RAW, USER_ENTERED. Default: USER_ENTERED
</Accordion>
<Accordion title="GOOGLE_SHEETS_UPDATE_ROW">
**Description:** Update existing rows in a Google Sheets spreadsheet.
<Accordion title="google_sheets/append_values">
**Description:** Appends values to a spreadsheet.
**Parameters:**
- `spreadsheetId` (string, required): Spreadsheet - Use Connect Portal Workflow Settings to allow users to select a spreadsheet. Defaults to using the first worksheet in the selected spreadsheet.
- `worksheet` (string, required): Worksheet - Your worksheet must have column headers.
- `filterFormula` (object, optional): A filter in disjunctive normal form - OR of AND groups of single conditions to identify which rows to update.
- `spreadsheetId` (string, required): The ID of the spreadsheet to update.
- `range` (string, required): The A1 notation of a range to search for a logical table of data.
- `values` (array, required): The data to append. Each array represents a row.
```json
{
"operator": "OR",
"conditions": [
{
"operator": "AND",
"conditions": [
{
"field": "status",
"operator": "$stringExactlyMatches",
"value": "pending"
}
]
[
["Value1", "Value2", "Value3"],
["Value4", "Value5", "Value6"]
]
```
- `valueInputOption` (string, optional): How the input data should be interpreted. Options: RAW, USER_ENTERED. Default: USER_ENTERED
- `insertDataOption` (string, optional): How the input data should be inserted. Options: OVERWRITE, INSERT_ROWS. Default: INSERT_ROWS
</Accordion>
<Accordion title="google_sheets/create_spreadsheet">
**Description:** Creates a new spreadsheet.
**Parameters:**
- `title` (string, required): The title of the new spreadsheet.
- `sheets` (array, optional): The sheets that are part of the spreadsheet.
```json
[
{
"properties": {
"title": "Sheet1"
}
]
}
```
Available operators: `$stringContains`, `$stringDoesNotContain`, `$stringExactlyMatches`, `$stringDoesNotExactlyMatch`, `$stringStartsWith`, `$stringDoesNotStartWith`, `$stringEndsWith`, `$stringDoesNotEndWith`, `$numberGreaterThan`, `$numberLessThan`, `$numberEquals`, `$numberDoesNotEqual`, `$dateTimeAfter`, `$dateTimeBefore`, `$dateTimeEquals`, `$booleanTrue`, `$booleanFalse`, `$exists`, `$doesNotExist`
- `additionalFields` (object, required): Fields - Include fields to update, as an object with keys of Column Names. Use Connect Portal Workflow Settings to allow users to select a Column Mapping.
```json
{
"columnName1": "newValue1",
"columnName2": "newValue2",
"columnName3": "newValue3",
"columnName4": "newValue4"
}
}
]
```
</Accordion>
</AccordionGroup>
@@ -105,19 +115,13 @@ uv add crewai-tools
```python
from crewai import Agent, Task, Crew
from crewai_tools import CrewaiEnterpriseTools
# Get enterprise tools (Google Sheets tools will be included)
enterprise_tools = CrewaiEnterpriseTools(
enterprise_token="your_enterprise_token"
)
# Create an agent with Google Sheets capabilities
sheets_agent = Agent(
role="Data Manager",
goal="Manage spreadsheet data and track information efficiently",
backstory="An AI assistant specialized in data management and spreadsheet operations.",
tools=[enterprise_tools]
apps=['google_sheets']
)
# Task to add new data to a spreadsheet
@@ -139,19 +143,17 @@ crew.kickoff()
### Filtering Specific Google Sheets Tools
```python
from crewai_tools import CrewaiEnterpriseTools
# Get only specific Google Sheets tools
enterprise_tools = CrewaiEnterpriseTools(
enterprise_token="your_enterprise_token",
actions_list=["google_sheets_get_row", "google_sheets_create_row"]
)
from crewai import Agent, Task, Crew
# Create agent with specific Google Sheets actions only
data_collector = Agent(
role="Data Collector",
goal="Collect and organize data in spreadsheets",
backstory="An AI assistant that focuses on data collection and organization.",
tools=enterprise_tools
apps=[
'google_sheets/get_values',
'google_sheets/update_values'
]
)
# Task to collect and organize data
@@ -173,17 +175,12 @@ crew.kickoff()
```python
from crewai import Agent, Task, Crew
from crewai_tools import CrewaiEnterpriseTools
enterprise_tools = CrewaiEnterpriseTools(
enterprise_token="your_enterprise_token"
)
data_analyst = Agent(
role="Data Analyst",
goal="Analyze spreadsheet data and generate insights",
backstory="An experienced data analyst who extracts insights from spreadsheet data.",
tools=[enterprise_tools]
apps=['google_sheets']
)
# Task to analyze data and create reports
@@ -205,33 +202,59 @@ crew = Crew(
crew.kickoff()
```
### Spreadsheet Creation and Management
```python
from crewai import Agent, Task, Crew
spreadsheet_manager = Agent(
role="Spreadsheet Manager",
goal="Create and manage spreadsheets efficiently",
backstory="An AI assistant that specializes in creating and organizing spreadsheets.",
apps=['google_sheets']
)
# Task to create and set up new spreadsheets
setup_task = Task(
description="""
1. Create a new spreadsheet for quarterly reports
2. Set up proper headers and structure
3. Add initial data and formatting
""",
agent=spreadsheet_manager,
expected_output="New quarterly report spreadsheet created and properly structured"
)
crew = Crew(
agents=[spreadsheet_manager],
tasks=[setup_task]
)
crew.kickoff()
```
### Automated Data Updates
```python
from crewai import Agent, Task, Crew
from crewai_tools import CrewaiEnterpriseTools
enterprise_tools = CrewaiEnterpriseTools(
enterprise_token="your_enterprise_token"
)
data_updater = Agent(
role="Data Updater",
goal="Automatically update and maintain spreadsheet data",
backstory="An AI assistant that maintains data accuracy and updates records automatically.",
tools=[enterprise_tools]
apps=['google_sheets']
)
# Task to update data based on conditions
update_task = Task(
description="""
1. Find all pending orders in the orders spreadsheet
2. Update their status to 'processing'
3. Add a timestamp for when the status was updated
4. Log the changes in a separate tracking sheet
1. Get spreadsheet properties and structure
2. Read current data from specific ranges
3. Update values in target ranges with new data
4. Append new records to the bottom of the sheet
""",
agent=data_updater,
expected_output="All pending orders updated to processing status with timestamps logged"
expected_output="Spreadsheet data updated successfully with new values and records"
)
crew = Crew(
@@ -246,30 +269,25 @@ crew.kickoff()
```python
from crewai import Agent, Task, Crew
from crewai_tools import CrewaiEnterpriseTools
enterprise_tools = CrewaiEnterpriseTools(
enterprise_token="your_enterprise_token"
)
workflow_manager = Agent(
role="Data Workflow Manager",
goal="Manage complex data workflows across multiple spreadsheets",
backstory="An AI assistant that orchestrates complex data operations across multiple spreadsheets.",
tools=[enterprise_tools]
apps=['google_sheets']
)
# Complex workflow task
workflow_task = Task(
description="""
1. Get all customer data from the main customer spreadsheet
2. Create monthly summary entries for active customers
3. Update customer status based on activity in the last 30 days
4. Generate a monthly report with customer metrics
5. Archive inactive customer records to a separate sheet
2. Create a new monthly summary spreadsheet
3. Append summary data to the new spreadsheet
4. Update customer status based on activity metrics
5. Generate reports with proper formatting
""",
agent=workflow_manager,
expected_output="Monthly customer workflow completed with updated statuses and generated reports"
expected_output="Monthly customer workflow completed with new spreadsheet and updated data"
)
crew = Crew(
@@ -291,29 +309,28 @@ crew.kickoff()
**Spreadsheet Structure Issues**
- Ensure worksheets have proper column headers before creating or updating rows
- Verify that column names in `additionalFields` match the actual column headers
- Check that the specified worksheet exists in the spreadsheet
- Verify that range notation (A1 format) is correct for the target cells
- Check that the specified spreadsheet ID exists and is accessible
**Data Type and Format Issues**
- Ensure data values match the expected format for each column
- Use proper date formats for date columns (ISO format recommended)
- Verify that numeric values are properly formatted for number columns
**Filter Formula Issues**
- Ensure filter formulas follow the correct JSON structure for disjunctive normal form
- Use valid field names that match actual column headers
- Test simple filters before building complex multi-condition queries
- Verify that operator types match the data types in the columns
**Range and Cell Reference Issues**
- Use proper A1 notation for ranges (e.g., "A1:C10", "Sheet1!A1:B5")
- Ensure range references don't exceed the actual spreadsheet dimensions
- Verify that sheet names in range references match actual sheet names
**Row Limits and Performance**
- Be mindful of row limits when using `GOOGLE_SHEETS_GET_ROW`
- Consider pagination for large datasets
- Use specific filters to reduce the amount of data processed
**Value Input and Rendering Options**
- Choose appropriate `valueInputOption` (RAW vs USER_ENTERED) for your data
- Select proper `valueRenderOption` based on how you want data formatted
- Consider `dateTimeRenderOption` for consistent date/time handling
**Update Operations**
- Ensure filter conditions properly identify the intended rows for updates
- Test filter conditions with small datasets before large updates
- Verify that all required fields are included in update operations
**Spreadsheet Creation Issues**
- Ensure spreadsheet titles are unique and follow naming conventions
- Verify that sheet properties are properly structured when creating sheets
- Check that you have permissions to create new spreadsheets in your account
### Getting Help