Get Agent

Get full Agent details, with support for specifying a version.

Prerequisites

Obtain an Alibaba Cloud Model Studio API Key and workspace ID first. For authentication, see API Authentication. This is a read operation and requires only an API Key.

Endpoint

POST /api/v1/indices/rag/app/get

Query the detailed information of a specified Agent, including name, description, scene, status, and configuration details for each version. You can specify a version number via agent_version to query a specific version; if not provided, all versions are returned.

Request body

Field	Required	Type	Description
agent_id	Yes	string	Agent ID.
agent_version	No	string	Specify a version number (beta or a number such as 1). If not provided, all version information is returned.

Request example

curl -X POST "$BASE_URL/api/v1/indices/rag/app/get" \
  -H "Authorization: Bearer $BAILIAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "aid-8f3a1b2c4d5e6f70",
    "agent_version": "beta"
}'

BASE_URL is https://{workspace_id}.cn-beijing.maas.aliyuncs.com ({workspace_id} is the workspace ID), and BAILIAN_API_KEY is your Alibaba Cloud Model Studio API Key.

Response example

Returns 200 on success.

{
  "request_id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
  "status_code": 200,
  "code": "Success",
  "message": "",
  "status": "SUCCESS",
  "success": true,
  "data": {
    "agent_id": "aid-8f3a1b2c4d5e6f70",
    "agent_name": "Customer Service Q&A Assistant",
    "agent_desc": "Intelligent customer service Q&A agent based on product documentation",
    "agent_scene": "chat",
    "agent_status": "deployed",
    "create_time": "2026-07-10T14:30:00",
    "modify_time": "2026-07-15T09:15:00",
    "agent_details": [
      {
        "agent_version": "beta",
        "agent_version_desc": "Draft version",
        "publish_time": null,
        "agent_config": {
          "agent_policy": "agentic",
          "agent_model": "qwen3.7-plus",
          "enable_session_file": "false",
          "enable_refusal": "true",
          "enable_anti_leak": "false",
          "enable_rich_text": "false",
          "enable_citation": "true",
          "temperature": 0.5,
          "kb_search_configs": [
            {
              "id": "pipeline-xxxxxx",
              "weight": 1,
              "credibility_level": "high",
              "dense_similarity_top_k": 10,
              "rerank_top_n": 5,
              "rerank_min_score": 0.3,
              "rerank": {
                "model_name": "gte-rerank-hybrid",
                "rerank_mode": "qa"
              }
            }
          ]
        }
      }
    ]
  }
}

Response fields

Field	Type	Description
request_id	string	Unique request identifier. Provide this ID when troubleshooting issues.
status_code	integer	HTTP status code.
code	string	Response code. Success on success.
message	string	Informational message.
status	string	Request status: SUCCESS or FAILED.
success	boolean	Whether the request succeeded.
data.agent_id	string	Agent ID.
data.agent_name	string	Agent name.
data.agent_desc	string	Agent description.
data.agent_scene	string	Agent scene: chat or search.
data.agent_status	string	Agent status.
data.create_time	string	Creation time (ISO 8601).
data.modify_time	string	Modification time (ISO 8601).
data.agent_details	array<object>	List of Agent version details. Returns all versions when agent_version is not specified. See the element table below.

data.agent_details[] elements

Field	Type	Description
agent_version	string	Version number, beta or a number (e.g. 1, 2).
agent_version_desc	string	Version description.
publish_time	string	Publish time (ISO 8601). Not present for the beta version.
agent_config	object	Agent configuration. See the sub-field table below.
publish_user	string	User who published the version.

agent_config sub-fields

Field	Type	Description
agent_model	string	Model name used by the agent, e.g. qwen3.7-plus, qwen3.6-plus.
agent_policy	string	Agent policy, e.g. agentic.
enable_anti_leak	boolean	Whether to enable the anti-leak feature, true or false.
enable_citation	boolean	Whether to enable citation annotations, true or false.
enable_refusal	boolean	Whether to enable the refusal feature, true or false.
enable_rich_text	boolean	Whether to enable rich text output, true or false.
enable_session_file	boolean	Whether to enable the session file feature, true or false.
hybrid_rerank	object	Global fusion rerank config (search scene). See the sub-field table below.
kb_search_configs	array<object>	List of knowledge base retrieval configurations. See the element table below.
max_completion_tokens	integer	Maximum generation tokens. Must be >= 1.
max_num_llm_calls	integer	Maximum number of LLM calls for the agent.
rerank_top_n	integer	Fusion rerank Top N (search scene). Range [1, 20].
session_file_max_parse_length	integer	Maximum parsing length for session files. Must be less than the model's max_context_length.
temperature	number	Model sampling temperature, range [0, 2].
anti_leak_prompt	string	Anti-leak prompt.
refusal_prompt	string	Refusal prompt.
credibility_prompt	string	Credibility prompt.
enable_thinking	boolean	Whether thinking mode is enabled.
enable_temperature	boolean	Whether a custom temperature is applied.
enable_credibility	boolean	Whether credibility checking is enabled.
enable_max_completion_tokens	boolean	Whether the max completion tokens limit is applied.
session_file_parse_mode	string	Parsing mode for session files.
user_system_prompt	string	Custom system prompt for the chat scene. Place it at the top level of agent_config; it is passed through without validation, and its length and effect are determined by the downstream runtime. Note the field name is user_system_prompt, not system_prompt.

agent_config.kb_search_configs[] elements

Field	Type	Description
credibility_level	string	Knowledge base credibility level, e.g. high, medium, low.
dense_similarity_top_k	integer	Top-K quantity returned by dense retrieval.
id	string	Associated knowledge base Pipeline ID.
rerank	object	Reranking configuration. See the sub-field table below.
rerank_min_score	number	Minimum rerank score threshold. Chunks with a score below this value are filtered out.
rerank_top_n	integer	Top-N quantity retained after reranking.
search_filters	array	Retrieval filter conditions, validated against the knowledge base schema.
sparse_similarity_top_k	integer	Sparse retrieval Top K. Range [1, 100].
weight	number	Knowledge base weight.
name	string	Knowledge Base name.
desc	string	Knowledge Base description.
enable_rewrite	boolean	Whether query rewriting is enabled for this Knowledge Base.

kb_search_configs[].rerank sub-fields

Field	Type	Description
model_name	string	Reranking model name, e.g. gte-rerank-hybrid.
rerank_instruct	string	Custom rerank instruction, only effective when rerank_mode is custom. Max 500 characters.
rerank_mode	string	Rerank mode: qa (question answering), similar (similarity), or custom (custom instruction). rerank_instruct is automatically cleared when not in custom mode.

agent_config.hybrid_rerank sub-fields

Field	Type	Description
model_name	string	Fusion rerank model code. For VL knowledge bases, only multimodal models are supported; otherwise all rerank models are supported.
rerank_mode	string	Fusion rerank mode: qa, similar, or custom. rerank_instruct is automatically cleared when not in custom mode.
rerank_instruct	string	Custom fusion rerank instruction, only effective when rerank_mode is custom. Max 500 characters.

Error codes

HTTP status code	Error code	Description
400	Index.InvalidParameter	Invalid request parameters. Please check that all parameters are complete and correctly typed.

Error response example:

{
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status_code": 400,
  "code": "Index.InvalidParameter",
  "message": "Invalid request parameters. Please check that all parameters are complete and correctly typed.",
  "status": "FAILED",
  "success": false
}