mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-11 00:58:30 +00:00
docs: Tool docs improvements (#2259)
* docs: add Qdrant vector search tool documentation * Update installation docs to use uv and improve quickstart guide * docs: improve installation instructions and add structured outputs video * Update tool documentation with agent integration examples and consistent formatting
This commit is contained in:
112
docs/tools/linkupsearchtool.mdx
Normal file
112
docs/tools/linkupsearchtool.mdx
Normal file
@@ -0,0 +1,112 @@
|
||||
---
|
||||
title: Linkup Search Tool
|
||||
description: The `LinkupSearchTool` enables querying the Linkup API for contextual information.
|
||||
icon: link
|
||||
---
|
||||
|
||||
# `LinkupSearchTool`
|
||||
|
||||
## Description
|
||||
|
||||
The `LinkupSearchTool` provides the ability to query the Linkup API for contextual information and retrieve structured results. This tool is ideal for enriching workflows with up-to-date and reliable information from Linkup, allowing agents to access relevant data during their tasks.
|
||||
|
||||
## Installation
|
||||
|
||||
To use this tool, you need to install the Linkup SDK:
|
||||
|
||||
```shell
|
||||
uv add linkup-sdk
|
||||
```
|
||||
|
||||
## Steps to Get Started
|
||||
|
||||
To effectively use the `LinkupSearchTool`, follow these steps:
|
||||
|
||||
1. **API Key**: Obtain a Linkup API key.
|
||||
2. **Environment Setup**: Set up your environment with the API key.
|
||||
3. **Install SDK**: Install the Linkup SDK using the command above.
|
||||
|
||||
## Example
|
||||
|
||||
The following example demonstrates how to initialize the tool and use it in an agent:
|
||||
|
||||
```python Code
|
||||
from crewai_tools import LinkupSearchTool
|
||||
from crewai import Agent
|
||||
import os
|
||||
|
||||
# Initialize the tool with your API key
|
||||
linkup_tool = LinkupSearchTool(api_key=os.getenv("LINKUP_API_KEY"))
|
||||
|
||||
# Define an agent that uses the tool
|
||||
@agent
|
||||
def researcher(self) -> Agent:
|
||||
'''
|
||||
This agent uses the LinkupSearchTool to retrieve contextual information
|
||||
from the Linkup API.
|
||||
'''
|
||||
return Agent(
|
||||
config=self.agents_config["researcher"],
|
||||
tools=[linkup_tool]
|
||||
)
|
||||
```
|
||||
|
||||
## Parameters
|
||||
|
||||
The `LinkupSearchTool` accepts the following parameters:
|
||||
|
||||
### Constructor Parameters
|
||||
- **api_key**: Required. Your Linkup API key.
|
||||
|
||||
### Run Parameters
|
||||
- **query**: Required. The search term or phrase.
|
||||
- **depth**: Optional. The search depth. Default is "standard".
|
||||
- **output_type**: Optional. The type of output. Default is "searchResults".
|
||||
|
||||
## Advanced Usage
|
||||
|
||||
You can customize the search parameters for more specific results:
|
||||
|
||||
```python Code
|
||||
# Perform a search with custom parameters
|
||||
results = linkup_tool.run(
|
||||
query="Women Nobel Prize Physics",
|
||||
depth="deep",
|
||||
output_type="searchResults"
|
||||
)
|
||||
```
|
||||
|
||||
## Return Format
|
||||
|
||||
The tool returns results in the following format:
|
||||
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"results": [
|
||||
{
|
||||
"name": "Result Title",
|
||||
"url": "https://example.com/result",
|
||||
"content": "Content of the result..."
|
||||
},
|
||||
// Additional results...
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
If an error occurs, the response will be:
|
||||
|
||||
```json
|
||||
{
|
||||
"success": false,
|
||||
"error": "Error message"
|
||||
}
|
||||
```
|
||||
|
||||
## Error Handling
|
||||
|
||||
The tool gracefully handles API errors and provides structured feedback. If the API request fails, the tool will return a dictionary with `success: false` and an error message.
|
||||
|
||||
## Conclusion
|
||||
|
||||
The `LinkupSearchTool` provides a seamless way to integrate Linkup's contextual information retrieval capabilities into your CrewAI agents. By leveraging this tool, agents can access relevant and up-to-date information to enhance their decision-making and task execution.
|
||||
Reference in New Issue
Block a user