All Products
Search
Document Center

Intelligent Media Management:ContextualAnswer

Last Updated:Aug 27, 2026

Generates contextual answers in AI Assistant conversations based on indexed file content.

Operation description

Precautions

  • Before using this API, make sure you fully understand the billing method and pricing of Intelligent Media Management.

  • Before calling this API, ensure that you have indexed files into a dataset by using binding (CreateBinding) or active indexing (IndexFileMeta or BatchIndexFileMeta).

  • The returned result is only an example. Depending on the workflow template configuration, the categories and content of file metadata may differ from the example. If you have questions, join the DingTalk group 21714099.

Usage Restrictions

  • The maximum length of the historical conversation is 100, including both user and assistant messages.

  • Each message should not exceed 1000 Chinese characters.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

  • Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.

  • API: The API that you can call to perform the action.

  • Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.

  • Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.

    • For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.

    • For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.

  • Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.

  • Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

imm:ContextualAnswer

none

*All Resource

*

None None

Request parameters

Parameter

Type

Required

Description

Example

ProjectName

string

Yes

Project name. For how to obtain it, see Creating a Project.

test-project

Messages

array

Yes

The history of conversations and tool invocations. The latest message is at the end (index n-1), and the oldest message is at the beginning (index 0). Messages must be in user-assistant pairs, with a total count of 2*n+1. The latest question must not exceed 1000 characters. The maximum conversation history length is 100.

ContextualMessage

No

List of conversation messages

Files

array

No

The content of files relevant to the current Q&A. We recommend that you use the return value of the ContextualRetrieval API as input.

ContextualFile

No

List of files involved in the Q&A

Response elements

Element

Type

Description

Example

object

Schema of Response

RequestId

string

The request ID.

22F081FB-90D7-525A-BFE4-D28DC906A28F

Answer Answer

The response content generated by the LLM.

Code

string

Error code.

ResourceNotFound

Message

string

Error message.

The specified resource project is not found.

Examples

Success response

JSON format

{
  "RequestId": "22F081FB-90D7-525A-BFE4-D28DC906A28F",
  "Answer": {
    "Content": "你好",
    "References": [
      {
        "ProjectName": "test-project",
        "DatasetName": "test-dataset",
        "ObjectId": "75d5de2c50754e3dadd5c35dbca5f9949369e37eb342a73821f690c94c36c7f7",
        "URI": "oss://test-bucket/test-object.jpg"
      }
    ]
  },
  "Code": "ResourceNotFound",
  "Message": "The specified resource project is not found."
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.