Google

Overview

Search Google for web results, images, news, and places through a simple Python interface.

from ziet.integrations import google

# Search Google
results = google.search("best restaurants in SF")

# Search images
images = google.images("golden gate bridge")

# Search news
news = google.news("latest AI developments")

# Search maps/places
places = google.maps("coffee shops", location="San Francisco")

How It Works

Default (Ziet’s Keys)

No setup required - start searching immediately:

from ziet.integrations import google

results = google.search("machine learning")

Free tier: 100 searches/day

Bring Your Own Keys

For higher limits:

Get API key from Google Cloud Console
Get Search Engine ID from Programmable Search Engine
Add both to Ziet Dashboard → Google

Your code stays the same - Ziet uses your keys automatically.

Methods

search()

Search Google for web results:

results = google.search(
    query="python tutorials",
    num_results=10
)

Parameters:

query (string, required): Search query
num_results (int, default 10): Number of results (max 100)

Returns:

[
    {
        "title": "Learn Python - Tutorial",
        "url": "https://example.com/python",
        "snippet": "Complete Python tutorial for beginners...",
        "position": 1
    },
    ...
]

Example:

from ziet import Action, memory
from ziet.integrations import google

@Action(
    id="search_python",
    name="Search Python",
    description="Search for Python tutorials"
)
def search_python() -> None:
    results = google.search("python tutorials", num_results=10)
    memory.add(key="search_results", value=results)

images()

Search Google Images:

images = google.images(
    query="golden gate bridge",
    num_results=10
)

Returns:

[
    {
        "title": "Golden Gate Bridge",
        "url": "https://example.com/image.jpg",
        "thumbnail": "https://example.com/thumb.jpg",
        "width": 1920,
        "height": 1080
    },
    ...
]

news()

Search Google News:

news = google.news(
    query="artificial intelligence",
    num_results=10
)

Returns:

[
    {
        "title": "Latest AI Breakthrough",
        "url": "https://news.example.com/article",
        "snippet": "Scientists announce major advancement...",
        "source": "Tech News",
        "published": "2 hours ago"
    },
    ...
]

maps()

Search Google Maps/Places:

places = google.maps(
    query="coffee shops",
    location="San Francisco, CA"
)

Returns:

[
    {
        "name": "Blue Bottle Coffee",
        "address": "66 Mint St, San Francisco, CA 94103",
        "rating": 4.5,
        "reviews": 1234,
        "phone": "+1 510-653-3394",
        "hours": "Open until 6:00 PM"
    },
    ...
]

Complete Example

from ziet import Action, Agent, memory
from ziet.integrations import google, openai

@Action(
    id="search_topic",
    name="Search Topic",
    description="Search Google for a topic"
)
def search_topic(topic: str) -> None:
    results = google.search(topic, num_results=10)
    memory.add(key="search_results", value=results)

@Action(
    id="get_news",
    name="Get News",
    description="Get latest news on topic"
)
def get_news(topic: str) -> None:
    news = google.news(topic, num_results=5)
    memory.add(key="news_results", value=news)

@Action(
    id="summarize_findings",
    name="Summarize Findings",
    description="Summarize research findings"
)
def summarize_findings() -> None:
    search = memory.get("search_results")
    news = memory.get("news_results")
    
    prompt = f"Summarize this research:\n\nWeb: {search}\n\nNews: {news}"
    summary = openai.chat([{"role": "user", "content": prompt}])
    
    memory.add(key="final_summary", value=summary)

@Agent(
    id="research_agent",
    name="ResearchAgent",
    instructions="""
    Research a topic comprehensively:
    1. Search Google for web results
    2. Get latest news
    3. Summarize all findings
    Store everything in memory for later retrieval.
    """,
    actions=["search_topic", "get_news", "summarize_findings"]
)
class ResearchAgent:
    pass

Best Practices

Cache results

Avoid redundant searches:

from ziet import memory

# Check cache first
cached = memory.get(f"search_{query}")
if cached:
    return

# Search and cache
results = google.search(query)
memory.add(key=f"search_{query}", value=results)

Filter results

Post-process for better quality:

results = google.search("python tutorials")

# Filter by domain
official = [r for r in results if "python.org" in r["url"]]

# Filter by keywords
advanced = [r for r in results if "advanced" in r["title"].lower()]

Handle errors

from ziet import Action, memory
from ziet.integrations import google

@Action(
    id="safe_search",
    name="Safe Search",
    description="Search with error handling",
    retries=2
)
def safe_search(query: str) -> None:
    try:
        results = google.search(query)
        memory.add(key="results", value=results)
    except Exception as e:
        memory.add(key="error", value=str(e))
        memory.add(key="results", value=[])

Next Steps

Apify

Scrape search results for detailed data

OpenAI

Summarize search results with AI

Memory

Cache and store search results

Actions

Build search actions

Getting Started

Agentic

Application

Integrations

Deployment

Overview

How It Works

Default (Ziet’s Keys)

Bring Your Own Keys

Methods

search()

images()

news()

maps()

Complete Example

Best Practices

Next Steps

Apify

OpenAI

Memory

Actions

​Overview

​How It Works

​Default (Ziet’s Keys)

​Bring Your Own Keys

​Methods

​search()

​images()

​news()

​maps()

​Complete Example

​Best Practices

​Next Steps

Apify

OpenAI

Memory

Actions

Overview

How It Works

Default (Ziet’s Keys)

Bring Your Own Keys

Methods

search()

images()

news()

maps()

Complete Example

Best Practices

Next Steps