Web Search
Overview
Web Search Drivers can be used to search for links from a search query. They are used by WebSearch to provide its functionality. All Web Search Drivers implement the following methods:
search()
searches the web and returns a ListArtifact that contains JSON-serializable TextArtifacts with the search results.
You can use Web Search Drivers with Structures:
from griptape.drivers.web_search.duck_duck_go import DuckDuckGoWebSearchDriver
from griptape.structures import Agent
from griptape.tools import PromptSummaryTool, WebSearchTool
agent = Agent(
tools=[WebSearchTool(web_search_driver=DuckDuckGoWebSearchDriver()), PromptSummaryTool(off_prompt=False)],
)
agent.run("Give me some websites with information about AI frameworks.")
[02/27/25 20:25:03] INFO PromptTask a34c6c2830d04e818a9b6c9739ce7962
Input: Give me some websites with information about
AI frameworks.
[02/27/25 20:25:04] INFO Subtask c79db30526e24bc0b7acbf6f6d92e5b0
Actions: [
{
"tag": "call_btudHOuIJlYSioi7V3FcdAVW",
"name": "WebSearchTool",
"path": "search",
"input": {
"values": {
"query": "AI frameworks information
websites"
}
}
}
]
[02/27/25 20:25:05] INFO Subtask c79db30526e24bc0b7acbf6f6d92e5b0
Response: {"title": "The Top 16 AI Frameworks and
Libraries: A Beginner's Guide", "url":
"https://www.datacamp.com/blog/top-ai-frameworks-an
d-libraries", "description": "Let's consider what
AI frameworks and libraries are \u2014 a collection
of pre-built tools and resources that simplify the
process of building applications on the basis of
Artificial Intelligence. These frameworks provide a
foundation for implementing machine learning and
deep learning algorithms, making it easier to
develop intelligent software."}
{"title": "Top 10 AI Frameworks to Learn in 2025 -
GeeksforGeeks", "url":
"https://www.geeksforgeeks.org/top-artificial-intel
ligence-frameworks/", "description": "Top
Artificial Intelligence Frameworks in 2025 - FAQs
What is an AI framework? An AI framework is a
software collection containing libraries, tools,
and pre-built functions designed to simplify
building and deploying AI models. It streamlines
the development process by offering: Standardized
development environment: A consistent structure for
your AI projects."}
{"title": "Top 10 AI Frameworks | AI Magazine",
"url":
"https://aimagazine.com/articles/top-10-ai-framewor
ks", "description": "Software plays a crucial role
in streamlining business operations through AI
frameworks and libraries. The integration of
AI-powered software solutions enables businesses to
optimise their processes, make data-driven
decisions, and gain a competitive edge in the
market.. By leveraging these tools, companies can
automate tasks, reduce manual labour, enhance
accuracy, save time and resources ..."}
{"title": "30 Best AI Websites You Should Visit",
"url":
"https://artificialintelligencejobs.net/30-best-ai-
websites-you-should-visit/", "description": "This
blog post lists the 30 best AI websites you should
visit, explaining what makes each unique and why
they deserve your attention. 1. OpenAI. Website:
OpenAI. ... TensorFlow is Google's open-source
machine learning framework, widely used by
developers and researchers to build AI models for a
range of applications, from image recognition to
..."}
{"title": "Top 10 Open Source AI Libraries in 2025
- GeeksforGeeks", "url":
"https://www.geeksforgeeks.org/top-open-source-ai-l
ibraries/", "description": "Open-Source AI
frameworks are more mainstream than ever and
driving innovation at a global scale. Developers
are choosing open source over closed source for
transparency and flexibility. These frameworks have
allowed for cutting-edge advancements in machine
learning and artificial intelligence. These
platforms allow the developers to modify and ..."}
[02/27/25 20:25:08] INFO PromptTask a34c6c2830d04e818a9b6c9739ce7962
Output: Here are some websites with information
about AI frameworks:
1. [The Top 16 AI Frameworks and Libraries: A
Beginner's Guide -
DataCamp](https://www.datacamp.com/blog/top-ai-fram
eworks-and-libraries): This guide provides an
overview of AI frameworks and libraries, explaining
how they simplify the process of building AI
applications.
2. [Top 10 AI Frameworks to Learn in 2025 -
GeeksforGeeks](https://www.geeksforgeeks.org/top-ar
tificial-intelligence-frameworks/): This article
lists the top AI frameworks to learn, detailing
their features and benefits for building and
deploying AI models.
3. [Top 10 AI Frameworks - AI
Magazine](https://aimagazine.com/articles/top-10-ai
-frameworks): This article discusses the role of AI
frameworks in streamlining business operations and
enhancing decision-making processes.
4. [30 Best AI Websites You Should Visit -
Artificial Intelligence
Jobs](https://artificialintelligencejobs.net/30-bes
t-ai-websites-you-should-visit/): This blog post
lists top AI websites, including those focused on
AI frameworks like TensorFlow.
5. [Top 10 Open Source AI Libraries in 2025 -
GeeksforGeeks](https://www.geeksforgeeks.org/top-op
en-source-ai-libraries/): This article highlights
open-source AI frameworks that are driving
innovation and providing flexibility for
developers.
PromptTask 45a53f1024494baab41a1f10a67017b1
Output: Here are some websites with information about AI
frameworks:
1. [The Top 16 AI Frameworks and Libraries: A Beginner's Guide -
DataCamp](https://www.datacamp.com/blog/top-ai-frameworks-and-lib
raries)
2. [AI Frameworks: Top Types To Adopt in 2024 -
Splunk](https://www.splunk.com/en_us/blog/learn/ai-frameworks.htm
l)
3. [Top AI Frameworks in 2024: A Review -
BairesDev](https://www.bairesdev.com/blog/ai-frameworks/)
4. [The Top 16 AI Frameworks and Libraries - AI
Slackers](https://aislackers.com/the-top-16-ai-frameworks-and-lib
raries/)
5. [Top AI Frameworks in 2024: Artificial Intelligence Frameworks
Comparison - Clockwise
Software](https://clockwise.software/blog/artificial-intelligence
-framework/)
Or use them independently:
from griptape.drivers.web_search.duck_duck_go import DuckDuckGoWebSearchDriver
driver = DuckDuckGoWebSearchDriver()
driver.search("griptape ai")
{"title": "The Top 16 AI Frameworks and Libraries: A Beginner's Guide", "url": "https://www.datacamp.com/blog/top-ai-frameworks-and-libraries", "description": "PyTorch. Torch is an open-source machine learning library known for its dynamic computational graph and is favored by researchers. The framework is excellent for prototyping and experimentation. Moreover, it's empowered by growing community support, with tools like PyTorch being built on the library."}
{"title": "Top 11 AI Frameworks and Tools in 2024 | Fively | 5ly.co", "url": "https://5ly.co/blog/best-ai-frameworks/", "description": "Discover the top 11 modern artificial intelligence tools and frameworks to build robust architectures for your AI-powered apps. ... - Some advanced use cases may need further fine-tuning. Caffe 2. Now we move on to deep learning tools and frameworks. The first one is Caffe 2: an open-source deep learning framework with modularity and speed in ..."}
{"title": "The Top 16 AI Frameworks and Libraries | AI Slackers", "url": "https://aislackers.com/the-top-16-ai-frameworks-and-libraries/", "description": "Experiment with different frameworks to find the one that aligns with your needs and goals as a data practitioner. Embrace the world of AI frameworks, and embark on a journey of building smarter software with confidence. Discover the top AI frameworks and libraries like PyTorch, Scikit-Learn, TensorFlow, Keras, LangChain, and more."}
Web Search Drivers
The GoogleWebSearchDriver uses the Google Custom Search JSON API for web searching.
import os
from griptape.drivers.web_search.google import GoogleWebSearchDriver
driver = GoogleWebSearchDriver(
api_key=os.environ["GOOGLE_API_KEY"],
search_id=os.environ["GOOGLE_API_SEARCH_ID"],
)
driver.search("griptape ai")
DuckDuckGo
Info
This driver requires the drivers-web-search-duckduckgo
extra.
The DuckDuckGoWebSearchDriver uses the duckduckgo_search SDK for web searching.
from griptape.drivers.web_search.duck_duck_go import DuckDuckGoWebSearchDriver
driver = DuckDuckGoWebSearchDriver()
driver.search("griptape ai")
Tavily
import os
from griptape.drivers.web_search.tavily import TavilyWebSearchDriver
driver = TavilyWebSearchDriver(api_key=os.environ["TAVILY_API_KEY"])
driver.search("griptape ai")
Exa
import os
from griptape.drivers.web_search.exa import ExaWebSearchDriver
driver = ExaWebSearchDriver(api_key=os.environ["EXA_API_KEY"])
driver.search("griptape ai")
Perplexity
The PerplexityWebSearchDriver uses the Perplexity Prompt Driver internally.
Info
This driver requires a Perplexity Sonar api key
import os
from griptape.drivers.web_search.perplexity import PerplexityWebSearchDriver
driver = PerplexityWebSearchDriver(
api_key=os.environ["PERPLEXITY_API_KEY"],
)
result = driver.search("griptape ai")
print(result.to_text())
# The search results will only contain a single Artifact.
# This Artifact contains the search results and any citations.
for citation in result[0].meta["citations"]:
print(citation)
Griptape is a modular Python framework for building AI-powered applications that securely connect to enterprise data and APIs[1][2]. It offers developers the ability to create AI systems that operate across two dimensions: predictability and creativity[2].
## Key Features
- **AI Agent Framework**: Griptape provides clean abstractions for building Gen AI Agents, Systems of Agents, Pipelines, Workflows, and RAG (Retrieval-Augmented Generation) implementations[1].
- **Flexibility**: The framework allows developers to move between predictability and creativity dimensions according to their use case[2].
- **Structures**: Griptape uses structures like sequential pipelines and directed acyclic graphs (DAGs) to enforce predictability[2].
- **Tools**: It facilitates creativity by safely prompting LLMs with Griptape Tools that connect to external APIs and data sources[2].
## Griptape Cloud
Griptape Cloud is a platform that extends the capabilities of the Griptape framework:
- **Data Connectors**: Allow users to bring their own data into the cloud for ingestion and transformation[4].
- **Knowledge Bases**: Organize multiple data sources and make them accessible for querying by AI applications[4].
- **Structures**: Custom Python applications powered by LLMs that can be deployed as hosted endpoints[4].
- **Threads**: Enable conversation memory for AI applications[4].
- **Rulesets and Rules**: Shape agent behavior and enhance responses[4].
## Getting Started
1. Install Griptape:
```bash
pip install griptape-all
```
2. Set up your OpenAI API key:
```bash
export OPENAI_API_KEY=your_api_key_here
```
3. Create a Python file (e.g., `app.py`) and import necessary modules from Griptape[3].
4. Build your AI application using Griptape's components such as agents, pipelines, and tools[3].
Griptape offers a powerful and flexible way to create AI-driven applications, from simple chatbots to complex multi-agent systems. Its modular approach allows developers to easily integrate custom tools and external resources, enhancing the capabilities of AI agents[3][4].
https://www.griptape.ai
https://github.com/griptape-ai
https://www.youtube.com/watch?v=AEcztigpnc0
https://www.youtube.com/watch?v=1FFeMZyWxJA
https://github.com/griptape-ai/griptape
https://www.youtube.com/@griptape-ai