mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-11 00:58:30 +00:00
docs: major docs updates (#2897)
This commit is contained in:
66
docs/tools/ai-ml/overview.mdx
Normal file
66
docs/tools/ai-ml/overview.mdx
Normal file
@@ -0,0 +1,66 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Leverage AI services, generate images, process vision, and build intelligent systems"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools integrate with AI and machine learning services to enhance your agents with advanced capabilities like image generation, vision processing, and intelligent code execution.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="DALL-E Tool" icon="image" href="/tools/ai-ml/dalletool">
|
||||
Generate AI images using OpenAI's DALL-E model.
|
||||
</Card>
|
||||
|
||||
<Card title="Vision Tool" icon="eye" href="/tools/ai-ml/visiontool">
|
||||
Process and analyze images with computer vision capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="AI Mind Tool" icon="brain" href="/tools/ai-ml/aimindtool">
|
||||
Advanced AI reasoning and decision-making capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="LlamaIndex Tool" icon="llama" href="/tools/ai-ml/llamaindextool">
|
||||
Build knowledge bases and retrieval systems with LlamaIndex.
|
||||
</Card>
|
||||
|
||||
<Card title="LangChain Tool" icon="link" href="/tools/ai-ml/langchaintool">
|
||||
Integrate with LangChain for complex AI workflows.
|
||||
</Card>
|
||||
|
||||
<Card title="RAG Tool" icon="database" href="/tools/ai-ml/ragtool">
|
||||
Implement Retrieval-Augmented Generation systems.
|
||||
</Card>
|
||||
|
||||
<Card title="Code Interpreter Tool" icon="code" href="/tools/ai-ml/codeinterpretertool">
|
||||
Execute Python code and perform data analysis.
|
||||
</Card>
|
||||
|
||||
<Card title="Patronus Tools" icon="shield" href="/tools/ai-ml/patronustools">
|
||||
AI safety and content moderation capabilities.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Content Generation**: Create images, text, and multimedia content
|
||||
- **Data Analysis**: Execute code and analyze complex datasets
|
||||
- **Knowledge Systems**: Build RAG systems and intelligent databases
|
||||
- **Computer Vision**: Process and understand visual content
|
||||
- **AI Safety**: Implement content moderation and safety checks
|
||||
|
||||
```python
|
||||
from crewai_tools import DallETool, VisionTool, CodeInterpreterTool
|
||||
|
||||
# Create AI tools
|
||||
image_generator = DallETool()
|
||||
vision_processor = VisionTool()
|
||||
code_executor = CodeInterpreterTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="AI Specialist",
|
||||
tools=[image_generator, vision_processor, code_executor],
|
||||
goal="Create and analyze content using AI capabilities"
|
||||
)
|
||||
@@ -4,9 +4,7 @@ description: The `MultiOnTool` empowers CrewAI agents with the capability to nav
|
||||
icon: globe
|
||||
---
|
||||
|
||||
# `MultiOnTool`
|
||||
|
||||
## Description
|
||||
## Overview
|
||||
|
||||
The `MultiOnTool` is designed to wrap [MultiOn's](https://docs.multion.ai/welcome) web browsing capabilities, enabling CrewAI agents to control web browsers using natural language instructions. This tool facilitates seamless web browsing, making it an essential asset for projects requiring dynamic web data interaction and automation of web-based tasks.
|
||||
|
||||
55
docs/tools/automation/overview.mdx
Normal file
55
docs/tools/automation/overview.mdx
Normal file
@@ -0,0 +1,55 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Automate workflows and integrate with external platforms and services"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to automate workflows, integrate with external platforms, and connect with various third-party services for enhanced functionality.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Apify Actor Tool" icon="spider" href="/tools/automation/apifyactorstool">
|
||||
Run Apify actors for web scraping and automation tasks.
|
||||
</Card>
|
||||
|
||||
<Card title="Composio Tool" icon="puzzle-piece" href="/tools/automation/composiotool">
|
||||
Integrate with hundreds of apps and services through Composio.
|
||||
</Card>
|
||||
|
||||
<Card title="Multion Tool" icon="window-restore" href="/tools/automation/multiontool">
|
||||
Automate browser interactions and web-based workflows.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Workflow Automation**: Automate repetitive tasks and processes
|
||||
- **API Integration**: Connect with external APIs and services
|
||||
- **Data Synchronization**: Sync data between different platforms
|
||||
- **Process Orchestration**: Coordinate complex multi-step workflows
|
||||
- **Third-party Services**: Leverage external tools and platforms
|
||||
|
||||
```python
|
||||
from crewai_tools import ApifyActorTool, ComposioTool, MultiOnTool
|
||||
|
||||
# Create automation tools
|
||||
apify_automation = ApifyActorTool()
|
||||
platform_integration = ComposioTool()
|
||||
browser_automation = MultiOnTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Automation Specialist",
|
||||
tools=[apify_automation, platform_integration, browser_automation],
|
||||
goal="Automate workflows and integrate systems"
|
||||
)
|
||||
```
|
||||
|
||||
## **Integration Benefits**
|
||||
|
||||
- **Efficiency**: Reduce manual work through automation
|
||||
- **Scalability**: Handle increased workloads automatically
|
||||
- **Reliability**: Consistent execution of workflows
|
||||
- **Connectivity**: Bridge different systems and platforms
|
||||
- **Productivity**: Focus on high-value tasks while automation handles routine work
|
||||
50
docs/tools/cloud-storage/overview.mdx
Normal file
50
docs/tools/cloud-storage/overview.mdx
Normal file
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Interact with cloud services, storage systems, and cloud-based AI platforms"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to interact with cloud services, access cloud storage, and leverage cloud-based AI platforms for scalable operations.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="S3 Reader Tool" icon="cloud" href="/tools/cloud-storage/s3readertool">
|
||||
Read files and data from Amazon S3 buckets.
|
||||
</Card>
|
||||
|
||||
<Card title="S3 Writer Tool" icon="cloud-arrow-up" href="/tools/cloud-storage/s3writertool">
|
||||
Write and upload files to Amazon S3 storage.
|
||||
</Card>
|
||||
|
||||
<Card title="Bedrock Invoke Agent" icon="aws" href="/tools/cloud-storage/bedrockinvokeagenttool">
|
||||
Invoke Amazon Bedrock agents for AI-powered tasks.
|
||||
</Card>
|
||||
|
||||
<Card title="Bedrock KB Retriever" icon="database" href="/tools/cloud-storage/bedrockkbretriever">
|
||||
Retrieve information from Amazon Bedrock knowledge bases.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **File Storage**: Store and retrieve files from cloud storage systems
|
||||
- **Data Backup**: Backup important data to cloud storage
|
||||
- **AI Services**: Access cloud-based AI models and services
|
||||
- **Knowledge Retrieval**: Query cloud-hosted knowledge bases
|
||||
- **Scalable Operations**: Leverage cloud infrastructure for processing
|
||||
|
||||
```python
|
||||
from crewai_tools import S3ReaderTool, S3WriterTool, BedrockInvokeAgentTool
|
||||
|
||||
# Create cloud tools
|
||||
s3_reader = S3ReaderTool()
|
||||
s3_writer = S3WriterTool()
|
||||
bedrock_agent = BedrockInvokeAgentTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Cloud Operations Specialist",
|
||||
tools=[s3_reader, s3_writer, bedrock_agent],
|
||||
goal="Manage cloud resources and AI services"
|
||||
)
|
||||
@@ -4,9 +4,7 @@ description: The `MySQLSearchTool` is designed to search MySQL databases and ret
|
||||
icon: database
|
||||
---
|
||||
|
||||
# `MySQLSearchTool`
|
||||
|
||||
## Description
|
||||
## Overview
|
||||
|
||||
This tool is designed to facilitate semantic searches within MySQL database tables. Leveraging the RAG (Retrieve and Generate) technology,
|
||||
the MySQLSearchTool provides users with an efficient means of querying database table content, specifically tailored for MySQL databases.
|
||||
@@ -4,9 +4,8 @@ description: The `NL2SQLTool` is designed to convert natural language to SQL que
|
||||
icon: language
|
||||
---
|
||||
|
||||
# `NL2SQLTool`
|
||||
## Overview
|
||||
|
||||
## Description
|
||||
|
||||
This tool is used to convert natural language to SQL queries. When passed to the agent it will generate queries and then use them to interact with the database.
|
||||
|
||||
57
docs/tools/database-data/overview.mdx
Normal file
57
docs/tools/database-data/overview.mdx
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Connect to databases, vector stores, and data warehouses for comprehensive data access"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to interact with various database systems, from traditional SQL databases to modern vector stores and data warehouses.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="MySQL Tool" icon="database" href="/tools/database-data/mysqltool">
|
||||
Connect to and query MySQL databases with SQL operations.
|
||||
</Card>
|
||||
|
||||
<Card title="PostgreSQL Search" icon="elephant" href="/tools/database-data/pgsearchtool">
|
||||
Search and query PostgreSQL databases efficiently.
|
||||
</Card>
|
||||
|
||||
<Card title="Snowflake Search" icon="snowflake" href="/tools/database-data/snowflakesearchtool">
|
||||
Access Snowflake data warehouse for analytics and reporting.
|
||||
</Card>
|
||||
|
||||
<Card title="NL2SQL Tool" icon="language" href="/tools/database-data/nl2sqltool">
|
||||
Convert natural language queries to SQL statements automatically.
|
||||
</Card>
|
||||
|
||||
<Card title="Qdrant Vector Search" icon="vector-square" href="/tools/database-data/qdrantvectorsearchtool">
|
||||
Search vector embeddings using Qdrant vector database.
|
||||
</Card>
|
||||
|
||||
<Card title="Weaviate Vector Search" icon="network-wired" href="/tools/database-data/weaviatevectorsearchtool">
|
||||
Perform semantic search with Weaviate vector database.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Data Analysis**: Query databases for business intelligence and reporting
|
||||
- **Vector Search**: Find similar content using semantic embeddings
|
||||
- **ETL Operations**: Extract, transform, and load data between systems
|
||||
- **Real-time Analytics**: Access live data for decision making
|
||||
|
||||
```python
|
||||
from crewai_tools import MySQLTool, QdrantVectorSearchTool, NL2SQLTool
|
||||
|
||||
# Create database tools
|
||||
mysql_db = MySQLTool()
|
||||
vector_search = QdrantVectorSearchTool()
|
||||
nl_to_sql = NL2SQLTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Data Analyst",
|
||||
tools=[mysql_db, vector_search, nl_to_sql],
|
||||
goal="Extract insights from various data sources"
|
||||
)
|
||||
@@ -1,10 +1,10 @@
|
||||
---
|
||||
title: PG RAG Search
|
||||
description: The `PGSearchTool` is designed to search PostgreSQL databases and return the most relevant results.
|
||||
icon: database
|
||||
icon: elephant
|
||||
---
|
||||
|
||||
# `PGSearchTool`
|
||||
## Overview
|
||||
|
||||
<Note>
|
||||
The PGSearchTool is currently under development. This document outlines the intended functionality and interface.
|
||||
@@ -1,10 +1,10 @@
|
||||
---
|
||||
title: 'Qdrant Vector Search Tool'
|
||||
description: 'Semantic search capabilities for CrewAI agents using Qdrant vector database'
|
||||
icon: magnifying-glass-plus
|
||||
icon: vector-square
|
||||
---
|
||||
|
||||
# `QdrantVectorSearchTool`
|
||||
## Overview
|
||||
|
||||
The Qdrant Vector Search Tool enables semantic search capabilities in your CrewAI agents by leveraging [Qdrant](https://qdrant.tech/), a vector similarity search engine. This tool allows your agents to search through documents stored in a Qdrant collection using semantic similarity.
|
||||
|
||||
@@ -1,12 +1,11 @@
|
||||
---
|
||||
title: Weaviate Vector Search
|
||||
description: The `WeaviateVectorSearchTool` is designed to search a Weaviate vector database for semantically similar documents.
|
||||
icon: database
|
||||
icon: network-wired
|
||||
---
|
||||
|
||||
# `WeaviateVectorSearchTool`
|
||||
## Overview
|
||||
|
||||
## Description
|
||||
|
||||
The `WeaviateVectorSearchTool` is specifically crafted for conducting semantic searches within documents stored in a Weaviate vector database. This tool allows you to find semantically similar documents to a given query, leveraging the power of vector embeddings for more accurate and contextually relevant search results.
|
||||
|
||||
@@ -4,14 +4,12 @@ description: The `FileReadTool` is designed to read files from the local file sy
|
||||
icon: folders
|
||||
---
|
||||
|
||||
# `FileReadTool`
|
||||
## Overview
|
||||
|
||||
<Note>
|
||||
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
|
||||
</Note>
|
||||
|
||||
## Description
|
||||
|
||||
The FileReadTool conceptually represents a suite of functionalities within the crewai_tools package aimed at facilitating file reading and content retrieval.
|
||||
This suite includes tools for processing batch text files, reading runtime configuration files, and importing data for analytics.
|
||||
It supports a variety of text-based file formats such as `.txt`, `.csv`, `.json`, and more. Depending on the file type, the suite offers specialized functionality,
|
||||
88
docs/tools/file-document/overview.mdx
Normal file
88
docs/tools/file-document/overview.mdx
Normal file
@@ -0,0 +1,88 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Read, write, and search through various file formats with CrewAI's document processing tools"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to work with various file formats and document types. From reading PDFs to processing JSON data, these tools handle all your document processing needs.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="File Read Tool" icon="folders" href="/tools/file-document/filereadtool">
|
||||
Read content from any file type including text, markdown, and more.
|
||||
</Card>
|
||||
|
||||
<Card title="File Write Tool" icon="file-pen" href="/tools/file-document/filewritetool">
|
||||
Write content to files, create new documents, and save processed data.
|
||||
</Card>
|
||||
|
||||
<Card title="PDF Search Tool" icon="file-pdf" href="/tools/file-document/pdfsearchtool">
|
||||
Search and extract text content from PDF documents efficiently.
|
||||
</Card>
|
||||
|
||||
<Card title="DOCX Search Tool" icon="file-word" href="/tools/file-document/docxsearchtool">
|
||||
Search through Microsoft Word documents and extract relevant content.
|
||||
</Card>
|
||||
|
||||
<Card title="JSON Search Tool" icon="brackets-curly" href="/tools/file-document/jsonsearchtool">
|
||||
Parse and search through JSON files with advanced query capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="CSV Search Tool" icon="table" href="/tools/file-document/csvsearchtool">
|
||||
Process and search through CSV files, extract specific rows and columns.
|
||||
</Card>
|
||||
|
||||
<Card title="XML Search Tool" icon="code" href="/tools/file-document/xmlsearchtool">
|
||||
Parse XML files and search for specific elements and attributes.
|
||||
</Card>
|
||||
|
||||
<Card title="MDX Search Tool" icon="markdown" href="/tools/file-document/mdxsearchtool">
|
||||
Search through MDX files and extract content from documentation.
|
||||
</Card>
|
||||
|
||||
<Card title="TXT Search Tool" icon="file-lines" href="/tools/file-document/txtsearchtool">
|
||||
Search through plain text files with pattern matching capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="Directory Search Tool" icon="folder-open" href="/tools/file-document/directorysearchtool">
|
||||
Search for files and folders within directory structures.
|
||||
</Card>
|
||||
|
||||
<Card title="Directory Read Tool" icon="folder" href="/tools/file-document/directoryreadtool">
|
||||
Read and list directory contents, file structures, and metadata.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Document Processing**: Extract and analyze content from various file formats
|
||||
- **Data Import**: Read structured data from CSV, JSON, and XML files
|
||||
- **Content Search**: Find specific information within large document collections
|
||||
- **File Management**: Organize and manipulate files and directories
|
||||
- **Data Export**: Save processed results to various file formats
|
||||
|
||||
## **Quick Start Example**
|
||||
|
||||
```python
|
||||
from crewai_tools import FileReadTool, PDFSearchTool, JSONSearchTool
|
||||
|
||||
# Create tools
|
||||
file_reader = FileReadTool()
|
||||
pdf_searcher = PDFSearchTool()
|
||||
json_processor = JSONSearchTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Document Analyst",
|
||||
tools=[file_reader, pdf_searcher, json_processor],
|
||||
goal="Process and analyze various document types"
|
||||
)
|
||||
```
|
||||
|
||||
## **Tips for Document Processing**
|
||||
|
||||
- **File Permissions**: Ensure your agent has proper read/write permissions
|
||||
- **Large Files**: Consider chunking for very large documents
|
||||
- **Format Support**: Check tool documentation for supported file formats
|
||||
- **Error Handling**: Implement proper error handling for corrupted or inaccessible files
|
||||
@@ -4,14 +4,12 @@ description: The `TXTSearchTool` is designed to perform a RAG (Retrieval-Augment
|
||||
icon: file-lines
|
||||
---
|
||||
|
||||
# `TXTSearchTool`
|
||||
## Overview
|
||||
|
||||
<Note>
|
||||
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
|
||||
</Note>
|
||||
|
||||
## Description
|
||||
|
||||
This tool is used to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.
|
||||
It allows for semantic searching of a query within a specified text file's content,
|
||||
making it an invaluable resource for quickly extracting information or finding specific sections of text based on the query provided.
|
||||
120
docs/tools/overview.mdx
Normal file
120
docs/tools/overview.mdx
Normal file
@@ -0,0 +1,120 @@
|
||||
---
|
||||
title: "Tools Overview"
|
||||
description: "Discover CrewAI's extensive library of 40+ tools to supercharge your AI agents"
|
||||
icon: "toolbox"
|
||||
---
|
||||
|
||||
CrewAI provides an extensive library of pre-built tools to enhance your agents' capabilities. From file processing to web scraping, database queries to AI services - we've got you covered.
|
||||
|
||||
## **Tool Categories**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card
|
||||
title="File & Document"
|
||||
icon="file-check"
|
||||
href="/tools/file-document/overview"
|
||||
color="#3B82F6"
|
||||
>
|
||||
Read, write, and search through various file formats including PDF, DOCX, JSON, CSV, and more. Perfect for document processing workflows.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="Web Scraping & Browsing"
|
||||
icon="globe"
|
||||
href="/tools/web-scraping/overview"
|
||||
color="#10B981"
|
||||
>
|
||||
Extract data from websites, automate browser interactions, and scrape content at scale with tools like Firecrawl, Selenium, and more.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="Search & Research"
|
||||
icon="magnifying-glass"
|
||||
href="/tools/search-research/overview"
|
||||
color="#F59E0B"
|
||||
>
|
||||
Perform web searches, find code repositories, research YouTube content, and discover information across the internet.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="Database & Data"
|
||||
icon="database"
|
||||
href="/tools/database-data/overview"
|
||||
color="#8B5CF6"
|
||||
>
|
||||
Connect to SQL databases, vector stores, and data warehouses. Query MySQL, PostgreSQL, Snowflake, Qdrant, and Weaviate.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="AI & Machine Learning"
|
||||
icon="brain"
|
||||
href="/tools/ai-ml/overview"
|
||||
color="#EF4444"
|
||||
>
|
||||
Generate images with DALL-E, process vision tasks, integrate with LangChain, build RAG systems, and leverage code interpreters.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="Cloud & Storage"
|
||||
icon="cloud"
|
||||
href="/tools/cloud-storage/overview"
|
||||
color="#06B6D4"
|
||||
>
|
||||
Interact with cloud services including AWS S3, Amazon Bedrock, and other cloud storage and AI services.
|
||||
</Card>
|
||||
|
||||
<Card
|
||||
title="Automation & Integration"
|
||||
icon="bolt"
|
||||
href="/tools/automation/overview"
|
||||
color="#84CC16"
|
||||
>
|
||||
Automate workflows with Apify, Composio, and other integration platforms to connect your agents with external services.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Quick Access**
|
||||
|
||||
Need a specific tool? Here are some popular choices:
|
||||
|
||||
<CardGroup cols={3}>
|
||||
<Card title="RAG Tool" icon="image" href="/tools/ai-ml/ragtool">
|
||||
Implement Retrieval-Augmented Generation
|
||||
</Card>
|
||||
<Card title="Serper Dev" icon="book-atlas" href="/tools/search-research/serperdevtool">
|
||||
Google search API
|
||||
</Card>
|
||||
<Card title="File Read" icon="file" href="/tools/file-document/filereadtool">
|
||||
Read any file type
|
||||
</Card>
|
||||
<Card title="Scrape Website" icon="globe" href="/tools/web-scraping/scrapewebsitetool">
|
||||
Extract web content
|
||||
</Card>
|
||||
<Card title="Code Interpreter" icon="code" href="/tools/ai-ml/codeinterpretertool">
|
||||
Execute Python code
|
||||
</Card>
|
||||
<Card title="S3 Reader" icon="cloud" href="/tools/cloud-storage/s3readertool">
|
||||
Access AWS S3 files
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Getting Started**
|
||||
|
||||
To use any tool in your CrewAI project:
|
||||
|
||||
1. **Import** the tool in your crew configuration
|
||||
2. **Add** it to your agent's tools list
|
||||
3. **Configure** any required API keys or settings
|
||||
|
||||
```python
|
||||
from crewai_tools import FileReadTool, SerperDevTool
|
||||
|
||||
# Add tools to your agent
|
||||
agent = Agent(
|
||||
role="Research Analyst",
|
||||
tools=[FileReadTool(), SerperDevTool()],
|
||||
# ... other configuration
|
||||
)
|
||||
```
|
||||
|
||||
Ready to explore? Pick a category above to discover tools that fit your use case!
|
||||
71
docs/tools/search-research/overview.mdx
Normal file
71
docs/tools/search-research/overview.mdx
Normal file
@@ -0,0 +1,71 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Perform web searches, find repositories, and research information across the internet"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to search the web, research topics, and find information across various platforms including search engines, GitHub, and YouTube.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Serper Dev Tool" icon="google" href="/tools/search-research/serperdevtool">
|
||||
Google search API integration for comprehensive web search capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="Brave Search Tool" icon="shield" href="/tools/search-research/bravesearchtool">
|
||||
Privacy-focused search with Brave's independent search index.
|
||||
</Card>
|
||||
|
||||
<Card title="Exa Search Tool" icon="magnifying-glass" href="/tools/search-research/exasearchtool">
|
||||
AI-powered search for finding specific and relevant content.
|
||||
</Card>
|
||||
|
||||
<Card title="LinkUp Search Tool" icon="link" href="/tools/search-research/linkupsearchtool">
|
||||
Real-time web search with fresh content indexing.
|
||||
</Card>
|
||||
|
||||
<Card title="GitHub Search Tool" icon="github" href="/tools/search-research/githubsearchtool">
|
||||
Search GitHub repositories, code, issues, and documentation.
|
||||
</Card>
|
||||
|
||||
<Card title="Website Search Tool" icon="globe" href="/tools/search-research/websitesearchtool">
|
||||
Search within specific websites and domains.
|
||||
</Card>
|
||||
|
||||
<Card title="Code Docs Search Tool" icon="code" href="/tools/search-research/codedocssearchtool">
|
||||
Search through code documentation and technical resources.
|
||||
</Card>
|
||||
|
||||
<Card title="YouTube Channel Search" icon="youtube" href="/tools/search-research/youtubechannelsearchtool">
|
||||
Search YouTube channels for specific content and creators.
|
||||
</Card>
|
||||
|
||||
<Card title="YouTube Video Search" icon="play" href="/tools/search-research/youtubevideosearchtool">
|
||||
Find and analyze YouTube videos by topic, keyword, or criteria.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Market Research**: Search for industry trends and competitor analysis
|
||||
- **Content Discovery**: Find relevant articles, videos, and resources
|
||||
- **Code Research**: Search repositories and documentation for solutions
|
||||
- **Lead Generation**: Research companies and individuals
|
||||
- **Academic Research**: Find scholarly articles and technical papers
|
||||
|
||||
```python
|
||||
from crewai_tools import SerperDevTool, GitHubSearchTool, YoutubeVideoSearchTool
|
||||
|
||||
# Create research tools
|
||||
web_search = SerperDevTool()
|
||||
code_search = GitHubSearchTool()
|
||||
video_research = YoutubeVideoSearchTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Research Analyst",
|
||||
tools=[web_search, code_search, video_research],
|
||||
goal="Gather comprehensive information on any topic"
|
||||
)
|
||||
```
|
||||
103
docs/tools/web-scraping/overview.mdx
Normal file
103
docs/tools/web-scraping/overview.mdx
Normal file
@@ -0,0 +1,103 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Extract data from websites and automate browser interactions with powerful scraping tools"
|
||||
icon: "face-smile"
|
||||
---
|
||||
|
||||
These tools enable your agents to interact with the web, extract data from websites, and automate browser-based tasks. From simple web scraping to complex browser automation, these tools cover all your web interaction needs.
|
||||
|
||||
## **Available Tools**
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Scrape Website Tool" icon="globe" href="/tools/web-scraping/scrapewebsitetool">
|
||||
General-purpose web scraping tool for extracting content from any website.
|
||||
</Card>
|
||||
|
||||
<Card title="Scrape Element Tool" icon="crosshairs" href="/tools/web-scraping/scrapeelementfromwebsitetool">
|
||||
Target specific elements on web pages with precision scraping capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="Firecrawl Crawl Tool" icon="spider" href="/tools/web-scraping/firecrawlcrawlwebsitetool">
|
||||
Crawl entire websites systematically with Firecrawl's powerful engine.
|
||||
</Card>
|
||||
|
||||
<Card title="Firecrawl Scrape Tool" icon="fire" href="/tools/web-scraping/firecrawlscrapewebsitetool">
|
||||
High-performance web scraping with Firecrawl's advanced capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="Firecrawl Search Tool" icon="magnifying-glass" href="/tools/web-scraping/firecrawlsearchtool">
|
||||
Search and extract specific content using Firecrawl's search features.
|
||||
</Card>
|
||||
|
||||
<Card title="Selenium Scraping Tool" icon="robot" href="/tools/web-scraping/seleniumscrapingtool">
|
||||
Browser automation and scraping with Selenium WebDriver capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="ScrapFly Tool" icon="plane" href="/tools/web-scraping/scrapflyscrapetool">
|
||||
Professional web scraping with ScrapFly's premium scraping service.
|
||||
</Card>
|
||||
|
||||
<Card title="ScrapGraph Tool" icon="network-wired" href="/tools/web-scraping/scrapegraphscrapetool">
|
||||
Graph-based web scraping for complex data relationships.
|
||||
</Card>
|
||||
|
||||
<Card title="Spider Tool" icon="spider" href="/tools/web-scraping/spidertool">
|
||||
Comprehensive web crawling and data extraction capabilities.
|
||||
</Card>
|
||||
|
||||
<Card title="BrowserBase Tool" icon="browser" href="/tools/web-scraping/browserbaseloadtool">
|
||||
Cloud-based browser automation with BrowserBase infrastructure.
|
||||
</Card>
|
||||
|
||||
<Card title="HyperBrowser Tool" icon="window-maximize" href="/tools/web-scraping/hyperbrowserloadtool">
|
||||
Fast browser interactions with HyperBrowser's optimized engine.
|
||||
</Card>
|
||||
|
||||
<Card title="Stagehand Tool" icon="hand" href="/tools/web-scraping/stagehandtool">
|
||||
Intelligent browser automation with natural language commands.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## **Common Use Cases**
|
||||
|
||||
- **Data Extraction**: Scrape product information, prices, and reviews
|
||||
- **Content Monitoring**: Track changes on websites and news sources
|
||||
- **Lead Generation**: Extract contact information and business data
|
||||
- **Market Research**: Gather competitive intelligence and market data
|
||||
- **Testing & QA**: Automate browser testing and validation workflows
|
||||
- **Social Media**: Extract posts, comments, and social media analytics
|
||||
|
||||
## **Quick Start Example**
|
||||
|
||||
```python
|
||||
from crewai_tools import ScrapeWebsiteTool, FirecrawlScrapeWebsiteTool, SeleniumScrapingTool
|
||||
|
||||
# Create scraping tools
|
||||
simple_scraper = ScrapeWebsiteTool()
|
||||
advanced_scraper = FirecrawlScrapeWebsiteTool()
|
||||
browser_automation = SeleniumScrapingTool()
|
||||
|
||||
# Add to your agent
|
||||
agent = Agent(
|
||||
role="Web Research Specialist",
|
||||
tools=[simple_scraper, advanced_scraper, browser_automation],
|
||||
goal="Extract and analyze web data efficiently"
|
||||
)
|
||||
```
|
||||
|
||||
## **Scraping Best Practices**
|
||||
|
||||
- **Respect robots.txt**: Always check and follow website scraping policies
|
||||
- **Rate Limiting**: Implement delays between requests to avoid overwhelming servers
|
||||
- **User Agents**: Use appropriate user agent strings to identify your bot
|
||||
- **Legal Compliance**: Ensure your scraping activities comply with terms of service
|
||||
- **Error Handling**: Implement robust error handling for network issues and blocked requests
|
||||
- **Data Quality**: Validate and clean extracted data before processing
|
||||
|
||||
## **Tool Selection Guide**
|
||||
|
||||
- **Simple Tasks**: Use `ScrapeWebsiteTool` for basic content extraction
|
||||
- **JavaScript-Heavy Sites**: Use `SeleniumScrapingTool` for dynamic content
|
||||
- **Scale & Performance**: Use `FirecrawlScrapeWebsiteTool` for high-volume scraping
|
||||
- **Cloud Infrastructure**: Use `BrowserBaseLoadTool` for scalable browser automation
|
||||
- **Complex Workflows**: Use `StagehandTool` for intelligent browser interactions
|
||||
Reference in New Issue
Block a user