AI Agent

client.aiAgent (TypeScript) / client.ai_agent (Python) 提供聊天流式传输、嵌入管理、parquet 生成和 AI 代理的分布式追踪。

如需逐步指南，请参阅 SDK 指南中的 AI Agent。

---

Schema

StreamChatBody

初始化流式聊天会话的参数。

Field	Type	Required	说明
assistant_id	string	✓	要聊天的 AI 代理 ID
messages	array	✓	对话历史记录（role + content 配对）
id	string		要继续的现有聊天会话 ID
model_id	string		覆盖代理的默认 LLM 模型
provider_id	string		覆盖代理的默认 LLM 提供商
user_id	string		外部用户标识符

StreamSubAgentChatBody

Field	Type	Required	说明
assistant_id	string	✓	AI 代理 ID
session_id	string	✓	父会话 ID
chat_id	string	✓	会话中的聊天 ID
messages	array	✓	对话消息

---

Methods

Method	TypeScript	Python	说明
Stream chat	streamChat	stream_chat	与 AI 代理开始流式聊天会话
Stream sub-agent chat	streamSubAgentChat	stream_sub_agent_chat	在子代理会话范围内进行流式聊天
Get sub-agent history	getSubAgentHistory	get_sub_agent_history	检索子代理聊天的消息历史
List chats	listChats	list_chats	列出组织的聊天会话
Get chat	getChat	get_chat	获取单个聊天会话
Delete chat	deleteChat	delete_chat	删除聊天会话
Prompt suggestions	getAgentPromptSuggestion	get_agent_prompt_suggestion	获取代理的提示建议
Classify file	classifyFile	classify_file	将文件分类到类别
Suggest field types	suggestFieldTypes	suggest_field_types	从样本文档建议 JSON schema
Process embedding	processEmbedding	process_embedding	将文件嵌入知识库
List embedding files	listEmbeddingFiles	list_embedding_files	列出所有已嵌入的文件
Get embedding file	getEmbeddingFile	get_embedding_file	获取单个已嵌入的文件
Preview embedding file	previewEmbeddingFile	preview_embedding_file	预览已嵌入的内容
Update embedding status	updateEmbeddingFileStatus	update_embedding_file_status	更新文件嵌入状态
Delete embedding file	deleteEmbeddingFile	delete_embedding_file	从知识库移除文件
Generate parquet	generateParquet	generate_parquet	将数据数组转换为 parquet 文件
List parquet files	listParquetFiles	list_parquet_files	列出已生成的 parquet 文件
Delete parquet file	deleteParquetFile	delete_parquet_file	按名称删除 parquet 文件
Get traces	getTraces	get_traces	查询分布式追踪
Get trace	getTrace	get_trace	按 ID 获取单个追踪
Get trace services	getTraceServices	get_trace_services	列出发出追踪的服务

---

streamChat / stream_chat

与 AI 代理开始流式聊天。返回原始 HTTP 响应 — 迭代流以读取 SSE chunks。

TypeScript

const response = await client.aiAgent.streamChat({
  assistant_id: "agent_id",
  messages: [{ role: "user", content: "Hello" }],
  user_id: "user_123",
});

const reader = response.body?.getReader();
const decoder = new TextDecoder();
while (reader) {
  const { done, value } = await reader.read();
  if (done) break;
  console.log(decoder.decode(value));
}

Python

response = client.ai_agent.stream_chat({
    "assistant_id": "agent_id",
    "messages": [{"role": "user", "content": "Hello"}],
    "user_id": "user_123",
})
for chunk in response.iter_lines():
    print(chunk)

---

streamSubAgentChat / stream_sub_agent_chat

在父会话内对子代理进行范围限定的流式聊天。

TypeScript

const response = await client.aiAgent.streamSubAgentChat({
  assistant_id: "agent_id",
  session_id: "session_id",
  chat_id: "chat_id",
  messages: [{ role: "user", content: "Follow-up question" }],
});

Python

response = client.ai_agent.stream_sub_agent_chat({
    "assistant_id": "agent_id",
    "session_id": "session_id",
    "chat_id": "chat_id",
    "messages": [{"role": "user", "content": "Follow-up question"}],
})

---

listChats / list_chats

TypeScript

const { data: chats } = await client.aiAgent.listChats({
  organization_id: "org_id",
  user_id: "user_123",
  limit: 20,
});

Python

result = client.ai_agent.list_chats(
    organization_id="org_id",
    user_id="user_123",
    limit=20,
)
chats = result.get("data", [])

---

getSubAgentHistory / get_sub_agent_history

TypeScript

const history = await client.aiAgent.getSubAgentHistory({
  session_id: "session_id",
  chat_id: "chat_id",
});

Python

history = client.ai_agent.get_sub_agent_history(
    session_id="session_id",
    chat_id="chat_id",
)

---

processEmbedding / process_embedding

将文件嵌入代理的知识库。

TypeScript

const result = await client.aiAgent.processEmbedding({
  fileId: "file_id",
  options: { chunk_size: 512 },
});

Python

result = client.ai_agent.process_embedding(
    file_id="file_id",
    options={"chunk_size": 512},
)

---

classifyFile / classify_file

根据文件内容将其分类到预定义类别。

TypeScript

const result = await client.aiAgent.classifyFile({ fileId: "file_id" });
console.log(result.category);

Python

result = client.ai_agent.classify_file(file_id="file_id")
print(result.get("category"))

---

suggestFieldTypes / suggest_field_types

分析样本文档并建议用于文档提取的 JSON schema 和字段类型。

TypeScript

const schema = await client.aiAgent.suggestFieldTypes({
  fileUrls: ["https://example.com/invoice.pdf"],
});
console.log(schema);

Python

schema = client.ai_agent.suggest_field_types(
    file_urls=["https://example.com/invoice.pdf"],
)
print(schema)

---

previewEmbeddingFile / preview_embedding_file

在处理前预览已嵌入文件的内容。

TypeScript

const preview = await client.aiAgent.previewEmbeddingFile({ fileId: "file_id" });
console.log(preview);

Python

preview = client.ai_agent.preview_embedding_file(file_id="file_id")
print(preview)

---

updateEmbeddingFileStatus / update_embedding_file_status

更新嵌入文件的处理状态。

TypeScript

const result = await client.aiAgent.updateEmbeddingFileStatus("file_id", "completed");
console.log(result);

Python

result = client.ai_agent.update_embedding_file_status("file_id", "completed")
print(result)

---

generateParquet / generate_parquet

将记录数组转换为 parquet 文件以进行结构化数据导入。

TypeScript

const result = await client.aiAgent.generateParquet({
  data: [{ name: "Alice", score: 95 }, { name: "Bob", score: 87 }],
  fileName: "scores",
  folderName: "results",
});

Python

result = client.ai_agent.generate_parquet(
    data=[{"name": "Alice", "score": 95}, {"name": "Bob", "score": 87}],
    file_name="scores",
    folder_name="results",
)

---

getTraces / get_traces

查询分布式追踪以进行调试和可观测性。

TypeScript

const traces = await client.aiAgent.getTraces({
  service: "ai-agent",
  limit: 50,
  timeRange: 3600,
  orgId: "org_id",
});

Python

traces = client.ai_agent.get_traces(
    service="ai-agent",
    limit=50,
    time_range=3600,
    org_id="org_id",
)