xAI: SDK Python v1.14.0 adds enable_image_search to web_search and SERVER_SIDE_TOOL_IMAGE_SEARCH enum
xAI released Python SDK v1.14.0 which brings support for image search within the web_search functionality. The new enable_image_search field and SERVER_SIDE_TOOL_IMAGE_SEARCH enum constant allow development teams building Grok-based applications to enable server-side visual content search alongside standard web text search.
This article was generated using artificial intelligence from primary sources.
xAI released Python SDK v1.14.0 with an extension of the Grok model’s web search capabilities. The update brings two new components for development teams building applications on the xAI API: the enable_image_search parameter and the SERVER_SIDE_TOOL_IMAGE_SEARCH enum constant.
What does enable_image_search add to Grok web search?
Web search (web_search) was available in the xAI SDK as a tool that Grok can use to retrieve current information from the internet. Version v1.14.0 extends this functionality: the new enable_image_search option allows activating visual content search alongside standard text web search.
In practice, this means Grok-based applications can search for and return images as part of web search results — opening up possibilities for multi-modal responses that combine text and visual content from web sources. This is particularly relevant for applications that need visual references, product images, or diagrammatic explanations in real time.
How does the SERVER_SIDE_TOOL_IMAGE_SEARCH enum work?
SERVER_SIDE_TOOL_IMAGE_SEARCH is a new constant within the enum type that defines available server-side tools in the xAI ecosystem. Server-side tools are capabilities that the xAI infrastructure executes on its own side — as opposed to client-side tools that the development application must implement itself.
By including this enum value in the configuration, the developer signals that Grok may activate the image search tool when processing requests that require it. This approach keeps control with the development team — image search is not activated automatically, but only when explicitly permitted.
Context: open-source contribution and xAI SDK development dynamics
Version v1.14.0 is also notable for including a contribution from an external collaborator — user @ushiromiya-lion on GitHub is marked as a first-time contributor to the xai-org/xai-sdk-python repository. Pull requests #152 and #153 that make up this update are open for review in the repository.
The xAI Python SDK is available on the xai-org/xai-sdk-python GitHub repository and is intended for developers who want to integrate Grok models (Grok 3, Grok 4 series) into Python applications. The SDK follows standard Python packaging conventions, and updates are available through the PyPI distribution platform.
Frequently Asked Questions
- What is enable_image_search in xAI Python SDK v1.14.0?
- enable_image_search is a new parameter added to the web_search function in the xAI Python SDK that enables activating image search alongside standard web search. When active, Grok can search for and return visual content as part of web search results.
- What is SERVER_SIDE_TOOL_IMAGE_SEARCH in the xAI SDK?
- SERVER_SIDE_TOOL_IMAGE_SEARCH is a new enum constant in the xAI Python SDK that identifies image search as a server-side tool. It is used to configure which server-side tools the Grok model may use when processing requests.
- What is the GitHub repository for the xAI Python SDK?
- The xAI Python SDK is located at github.com/xai-org/xai-sdk-python. Version v1.14.0 includes a contribution from the repository's first external collaborator (@ushiromiya-lion) who added the image search functionality.
📬 AI news in your inbox
A daily digest built your way — pick topics, sources and cadence. One-click unsubscribe.
Related news
CNCF: HAMi becomes Incubating project — GPU virtualization for Kubernetes AI workloads
LF AI & Data: 'context is the new bottleneck' — open infrastructure Docling and DocLang
PyTorch: Triton 3.7 brings plugin extensions and TLX — up to +15% throughput on AMD MI350