AI Agent

client.aiAgent (TypeScript) / client.ai_agent (Python) 提供聊天串流、嵌入管理、parquet 生成與 AI 代理的分散式追蹤。

如需逐步指南，請參閱 SDK 指南中的 AI Agent。

---

Schema

StreamChatBody

初始化串流聊天會話的參數。

Field	Type	Required	說明
assistant_id	string	✓	要聊天的 AI 代理 ID
messages	array	✓	對話歷史記錄（role + content 成對）
id	string		要繼續的現有聊天會話 ID
model_id	string		覆寫代理的預設 LLM 模型
provider_id	string		覆寫代理的預設 LLM 提供者
user_id	string		外部使用者識別碼

StreamSubAgentChatBody

Field	Type	Required	說明
assistant_id	string	✓	AI 代理 ID
session_id	string	✓	父會話 ID
chat_id	string	✓	會話中的聊天 ID
messages	array	✓	對話訊息

---

Methods

Method	TypeScript	Python	說明
Stream chat	streamChat	stream_chat	與 AI 代理開始串流聊天會話
Stream sub-agent chat	streamSubAgentChat	stream_sub_agent_chat	在子代理會話範圍內進行串流聊天
Get sub-agent history	getSubAgentHistory	get_sub_agent_history	擷取子代理聊天的訊息歷史
List chats	listChats	list_chats	列出組織的聊天會話
Get chat	getChat	get_chat	取得單一聊天會話
Delete chat	deleteChat	delete_chat	刪除聊天會話
Prompt suggestions	getAgentPromptSuggestion	get_agent_prompt_suggestion	取得代理的建議提示
Classify file	classifyFile	classify_file	將檔案分類至類別
Suggest field types	suggestFieldTypes	suggest_field_types	從範例文件建議 JSON 結構
Process embedding	processEmbedding	process_embedding	將檔案嵌入知識庫
List embedding files	listEmbeddingFiles	list_embedding_files	列出所有已嵌入的檔案
Get embedding file	getEmbeddingFile	get_embedding_file	取得單一已嵌入的檔案
Preview embedding file	previewEmbeddingFile	preview_embedding_file	預覽已嵌入的內容
Update embedding status	updateEmbeddingFileStatus	update_embedding_file_status	更新檔案嵌入狀態
Delete embedding file	deleteEmbeddingFile	delete_embedding_file	從知識庫移除檔案
Generate parquet	generateParquet	generate_parquet	將資料陣列轉換為 parquet 檔案
List parquet files	listParquetFiles	list_parquet_files	列出已生成的 parquet 檔案
Delete parquet file	deleteParquetFile	delete_parquet_file	依名稱刪除 parquet 檔案
Get traces	getTraces	get_traces	查詢分散式追蹤
Get trace	getTrace	get_trace	依 ID 取得單一追蹤
Get trace services	getTraceServices	get_trace_services	列出發出追蹤的服務

---

streamChat / stream_chat

與 AI 代理開始串流聊天。傳回原始 HTTP 回應 — 迭代串流以讀取 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

在父會話內對子代理進行範圍限定串流聊天。

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

將檔案嵌入代理的知識庫。

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

根據檔案內容將其分類至預定義類別。

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

分析範例文件並建議用於文件擷取的 JSON 結構與欄位類型。

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

在處理前預覽已嵌入檔案的內容。

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

更新嵌入檔案的處理狀態。

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

將記錄陣列轉換為 parquet 檔案以進行結構化資料導入。

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

查詢分散式追蹤以進行除錯和可觀測性。

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",
)