Add Python Equivalents for Bing & Google Search Plugins in Semantic Kernel

[shethaadit]

PR Description:

This PR adds Python equivalents for the Bing and Google search integration within the Semantic Kernel. The implementation mirrors the existing C# functionality, enabling Python developers to leverage web search for grounded AI responses using:

• BingTextSearch Plugin with Bing Search API
• GoogleTextSearch Plugin with Google Custom Search Engine

Key Changes:

• Implemented BingTextSearch and GoogleTextSearch plugins in Python
• Integrated with OpenAI’s gpt-4o for context-aware responses
• Ensured parity with the C# implementation
• Used KernelArguments for dynamic query handling

This enhancement broadens Semantic Kernel’s usability, allowing Python developers to build AI-powered applications with real-time web search capabilities.

[learn-build-service-prod]

Learn Build status updates of commit 6738f71:

✅ Validation status: passed

File	Status	Preview URL	Details
semantic-kernel/concepts/text-search/index.md	✅Succeeded

For more details, please refer to the build report.

For any questions, please:

• Try searching the learn.microsoft.com contributor guides
• Post your question in the Learn support channel

[learn-build-service-prod]

Learn Build status updates of commit 8d39f17:

✅ Validation status: passed

File	Status	Preview URL	Details
semantic-kernel/concepts/text-search/index.md	✅Succeeded

For more details, please refer to the build report.

For any questions, please:

• Try searching the learn.microsoft.com contributor guides
• Post your question in the Learn support channel

[learn-build-service-prod]

Learn Build status updates of commit 19cf1f2:

✅ Validation status: passed

File	Status	Preview URL	Details
semantic-kernel/concepts/text-search/index.md	✅Succeeded

For more details, please refer to the build report.

For any questions, please:

• Try searching the learn.microsoft.com contributor guides
• Post your question in the Learn support channel

[learn-build-service-prod]

Learn Build status updates of commit de14297:

✅ Validation status: passed

File	Status	Preview URL	Details
semantic-kernel/concepts/text-search/index.md	✅Succeeded

For more details, please refer to the build report.

For any questions, please:

• Try searching the learn.microsoft.com contributor guides
• Post your question in the Learn support channel

[eavanvalkenburg]

Thanks for looking at this, much appreciated! But some cleanup to do!

[learn-build-service-prod]

Learn Build status updates of commit 898718d:

✅ Validation status: passed

File	Status	Preview URL	Details
semantic-kernel/concepts/text-search/index.md	✅Succeeded

For more details, please refer to the build report.

For any questions, please:

• Try searching the learn.microsoft.com contributor guides
• Post your question in the Learn support channel

[shethaadit]

Hi @eavanvalkenburg / @moonbox3, Thank you for the reviews. I have tried to resolve all comments.

Here are both codes. Please let me know if they are correct.

Bing web search

# Create a kernel with OpenAI chat completion
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.connectors.search.bing import BingSearch
from semantic_kernel.functions import KernelArguments, KernelPlugin

# Initialize the Kernel
kernel = Kernel()

# Add OpenAI/Azure OpenAI chat completion service
kernel.add_service(AzureChatCompletion(service_id="chat"))

# Create a Bing Search instance (API key will be picked up from the environment)
bing_search = BingSearch()

# Build a Bing Search plugin and add it to the kernel
search_plugin = KernelPlugin.from_text_search_with_search(
    bing_search,
    description="Get search results using Bing."
)

# Add plugin to the kernel with a specific plugin name
kernel.add_plugin(search_plugin, plugin_name="bing")

# Define query and prompt
query = "What is Semantic Kernel?"
prompt = "{{bing.search $query}}. {{$query}}"

# Execute search query using the plugin
arguments = KernelArguments(query=query)
result = kernel.invoke_prompt(prompt, arguments)

# Display result
print(result)

Google web search

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.connectors.search.google import GoogleSearch
from semantic_kernel.functions import KernelArguments, KernelPlugin

# Initialize the Kernel
kernel = Kernel()

# Add OpenAI/Azure OpenAI chat completion service
kernel.add_service(AzureChatCompletion(service_id="chat"))

# Create a Google Search instance (API key and Search Engine ID picked from environment)
google_search = GoogleSearch()

# Build a Google Search plugin and add it to the kernel
search_plugin = KernelPlugin.from_text_search_with_search(
    google_search,
    description="Get details about Semantic Kernel concepts."
)

# Add plugin to the kernel with a specific plugin name
kernel.add_plugin(search_plugin, plugin_name="google")

# Define query and prompt
query = "What is Semantic Kernel?"
prompt = "{{google.search $query}}. {{$query}}"

# Execute search query using the plugin
arguments = KernelArguments(query=query)
result = kernel.invoke_prompt(prompt, arguments)

# Display result
print(result)