TextSearchProvider Class

Definition

public sealed class TextSearchProvider : Microsoft.Agents.AI.MessageAIContextProvider

type TextSearchProvider = class
    inherit MessageAIContextProvider

Public NotInheritable Class TextSearchProvider
Inherits MessageAIContextProvider

Inheritance

Object

AIContextProvider

MessageAIContextProvider

TextSearchProvider

Remarks

The provider supports two behaviors controlled via SearchTime:

• BeforeAIInvoke – Automatically performs a search prior to every AI invocation and injects results as additional messages.
• OnDemandFunctionCalling – Exposes a function tool that the model may invoke to retrieve contextual information when needed.

When RecentMessageMemoryLimit is greater than zero the provider will retain the most recent user and assistant messages (up to the configured limit) across invocations and prepend them (in chronological order) to the current request messages when forming the search input. This can improve search relevance by providing multi-turn context to the retrieval layer without permanently altering the conversation history.

Security considerations: Search results retrieved from external sources are injected into the LLM context and may contain adversarial content designed to manipulate LLM behavior via indirect prompt injection. Developers should be aware that:

• The search query may be constructed from user input or LLM-generated content, both of which are untrusted. Implementers of the search delegate should validate search inputs and apply appropriate access controls to search results.
• Retrieved documents are formatted and injected as messages in the AI request context. If the external data source is compromised, adversarial content could influence the LLM's responses.
• When using OnDemandFunctionCalling, the AI model controls when and what to search for — the search query text is AI-generated and should be treated as untrusted input by the search implementation.