curl -X POST "https://{workspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/indices/rag/app/get" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"agent_id": "aid-8f3a1b2c4d5e6f70",
"agent_version": "beta"
}'{
"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"
}
}
]
}
}
]
}
}agent_version is not passed, all version details are returned.
"release" as agent_version is not supported.Authorizations
DashScope API Key, obtained from the API Key page in the console.
Body
application/jsonResponse
Unique request identifier. Provide this ID when troubleshooting issues.
HTTP status code.
Response code. Success on success.
Informational message.
Request status: SUCCESS or FAILED.
Whether the request succeeded.
Show child attributes
Show child attributes
Agent ID.
Agent name.
Agent description.
Agent scene: chat or search.
Agent status.
Creation time (ISO 8601).
Modification time (ISO 8601).
List of Agent version details. Returns all versions when agent_version is not specified.
Show child attributes
Show child attributes
Version number, beta or a number (e.g. 1, 2).
Version description.
Publish time (ISO 8601). Not present for the beta version.
Agent configuration object. If not provided, default configuration is used.
Show child attributes
Show child attributes
Model name used by the agent, e.g. qwen3.7-plus, qwen3.6-plus.
Agent policy, e.g. agentic.
Whether to enable the anti-leak feature, true or false.
Whether to enable citation annotations, true or false.
Whether to enable the refusal feature, true or false.
Whether to enable rich text output, true or false.
Whether to enable the session file feature, true or false.
Global fusion rerank config (search scene).
Show child attributes
Show child attributes
Fusion rerank model code. For VL knowledge bases, only multimodal models are supported; otherwise all rerank models are supported.
Fusion rerank mode: qa, similar, or custom. rerank_instruct is automatically cleared when not in custom mode.
Custom fusion rerank instruction, only effective when rerank_mode is custom. Max 500 characters.
List of knowledge base retrieval configurations.
Show child attributes
Show child attributes
Knowledge base credibility level, e.g. high, medium, low.
Top-K quantity returned by dense retrieval.
Associated knowledge base Pipeline ID.
Reranking configuration.
Show child attributes
Show child attributes
Reranking model name, e.g. gte-rerank-hybrid.
Custom rerank instruction, only effective when rerank_mode is custom. Max 500 characters.
Rerank mode: qa (question answering), similar (similarity), or custom (custom instruction). rerank_instruct is automatically cleared when not in custom mode.
Minimum rerank score threshold. Chunks with a score below this value are filtered out.
Top-N quantity retained after reranking.
Retrieval filter conditions, validated against the knowledge base schema.
Sparse retrieval Top K. Range [1, 100].
Knowledge base weight.
Knowledge Base name.
Knowledge Base description.
Whether query rewriting is enabled for this Knowledge Base.
Maximum generation tokens. Must be >= 1.
Maximum number of LLM calls for the agent.
Fusion rerank Top N (search scene). Range [1, 20].
Maximum parsing length for session files. Must be less than the model's max_context_length.
Model sampling temperature, range [0, 2].
Anti-leak prompt.
Refusal prompt.
Credibility prompt.
Whether thinking mode is enabled.
Whether a custom temperature is applied.
Whether credibility checking is enabled.
Whether the max completion tokens limit is applied.
Parsing mode for session files.
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.
User who published the version.