Back to Details

arize-link

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Arize Link

Arize链接生成

Generate deep links to the Arize UI for traces, spans, and sessions.
生成指向Arize UI中trace、span和session的深度链接。

When to Use

使用场景

  • User wants a link to a specific trace, span, or session
  • You have trace/span/session IDs from exported data or logs and need to link back to the UI
  • User asks to "open" or "view" a trace/span/session in Arize
  • 用户需要指向特定trace、span或session的链接
  • 你从导出的数据或日志中获取了trace/span/session ID，需要链接回UI界面
  • 用户要求在Arize中“打开”或“查看”某个trace/span/session

Required Inputs

必要输入信息

Collect these from the user or from context (e.g., exported trace data, parsed URLs):
  • org_id -- Base64-encoded organization ID (from URL path or user)
  • space_id -- Base64-encoded space ID (from URL path or user)
  • project_id -- Base64-encoded project/model ID (from URL path or user)
  • One of:
    • trace_id (and optionally span_id) for trace/span links
    • session_id for session links
从用户或上下文（如导出的追踪数据、解析后的URL）中收集以下信息：
  • org_id -- Base64编码的组织ID（来自URL路径或用户提供）
  • space_id -- Base64编码的空间ID（来自URL路径或用户提供）
  • project_id -- Base64编码的项目/模型ID（来自URL路径或用户提供）
  • 以下其中一项：
    • trace_id（可选搭配span_id）用于trace/span链接
    • session_id用于会话链接

URL Construction

URL构建

Base URL: 
https://app.arize.com
(override for on-prem if the user specifies a custom base URL)
基础URL：
https://app.arize.com
（如果用户指定了自定义基础URL，可替换为本地部署地址）

Trace Link

Trace链接

Opens the trace slideover showing all spans in the trace.
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm
If a span_id is also available, add 
&selectedSpanId={span_id}
to highlight that span within the trace.
打开追踪侧边栏，展示trace中的所有span。
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm
如果同时有span_id，可添加
&selectedSpanId={span_id}
以在trace中高亮该span。

Span Link

Span链接

Opens a specific span within a trace. Both trace_id and span_id are required.
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&selectedSpanId={span_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm
打开trace中的特定span。需要同时提供trace_id和span_id。
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&selectedSpanId={span_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm

Session Link

会话链接

Opens the session view for a conversation/interaction flow.
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedSessionId={session_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm
打开对话/交互流程的会话视图。
{base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedSessionId={session_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_epoch_ms}&endA={end_epoch_ms}&envA=tracing&modelType=generative_llm

Time Range

时间范围

CRITICAL: 
startA
and 
endA
are required query parameters. Without them, the Arize UI defaults to the last 7 days and will show a "Your model doesn't have any recent data" error if the trace/span falls outside that window.
  • startA: Start of the time window as epoch milliseconds
  • endA: End of the time window as epoch milliseconds
关键提示：
startA
和
endA
是必填的查询参数。如果缺少这两个参数，Arize UI会默认显示过去7天的数据，如果trace/span不在该时间范围内，会显示“你的模型没有近期数据”的错误。
  • startA：时间窗口的开始时间，以毫秒级时间戳表示
  • endA：时间窗口的结束时间，以毫秒级时间戳表示

How to Determine the Time Range

如何确定时间范围

Use these sources in priority order:
  1. User-provided URL: If the user shared an Arize URL, extract 
    startA
    and 
    endA
    from it and reuse them. This is the most reliable approach since it preserves the user's original time window.
  2. Exported span data: If you have span data (e.g., from 
    ax spans export
    ), use the span's 
    start_time
    field to calculate a range that covers the data:
    bash
    # Convert span start_time to epoch ms, then pad ±1 day
python -c "
from datetime import datetime, timedelta
t = datetime.fromisoformat('2026-03-07T05:39:15.822147Z'.replace('Z','+00:00'))
start = int((t - timedelta(days=1)).timestamp() * 1000)
end = int((t + timedelta(days=1)).timestamp() * 1000)
print(f'startA={start}&endA={end}')
"
  3. Default fallback: Use the last 90 days. Calculate:
    • startA
      : 
      (now - 90 days)
      as epoch milliseconds
    • endA
      : current time as epoch milliseconds
按以下优先级顺序获取：
  1. 用户提供的URL：如果用户分享了Arize的URL，从中提取
    startA
    和
    endA
    并复用。这是最可靠的方法，因为它保留了用户原始的时间窗口。
  2. 导出的span数据：如果你有span数据（例如来自
    ax spans export
    ），使用span的
    start_time
    字段计算覆盖该数据的时间范围：
    bash
    # 将span的start_time转换为毫秒级时间戳，然后前后各加1天的缓冲
python -c "
from datetime import datetime, timedelta
t = datetime.fromisoformat('2026-03-07T05:39:15.822147Z'.replace('Z','+00:00'))
start = int((t - timedelta(days=1)).timestamp() * 1000)
end = int((t + timedelta(days=1)).timestamp() * 1000)
print(f'startA={start}&endA={end}')
"
  3. 默认回退方案：使用过去90天的时间范围。计算方式：
    • startA
      ：当前时间减去90天的毫秒级时间戳
    • endA
      ：当前时间的毫秒级时间戳

Instructions

操作步骤

  1. Gather the required IDs from the user or from available context (URLs, exported trace data, conversation history).
  2. Determine 
    startA
    and 
    endA
    epoch milliseconds using the priority order above.
  3. Substitute values into the appropriate URL template above.
  4. Present the URL as a clickable markdown link.
  1. 从用户或可用上下文（URL、导出的追踪数据、对话历史）中收集所需的ID信息。
  2. 按照上述优先级顺序确定
    startA
    和
    endA
    的毫秒级时间戳。
  3. 将值代入上述对应的URL模板中。
  4. 将URL以可点击的Markdown链接形式呈现。

Example Output

示例输出

Given: org_id=
QWNjb3VudE9yZ2FuaXphdGlvbjoxOmFiQzE=
, space_id=
U3BhY2U6MTp4eVo5
, project_id=
TW9kZWw6MTpkZUZn
, trace_id=
0123456789abcdef0123456789abcdef
Trace link:
https://app.arize.com/organizations/QWNjb3VudE9yZ2FuaXphdGlvbjoxOmFiQzE=/spaces/U3BhY2U6MTp4eVo5/projects/TW9kZWw6MTpkZUZn?selectedTraceId=0123456789abcdef0123456789abcdef&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA=1700000000000&endA=1700086400000&envA=tracing&modelType=generative_llm
给定：org_id=
QWNjb3VudE9yZ2FuaXphdGlvbjoxOmFiQzE=
, space_id=
U3BhY2U6MTp4eVo5
, project_id=
TW9kZWw6MTpkZUZn
, trace_id=
0123456789abcdef0123456789abcdef
Trace链接：
https://app.arize.com/organizations/QWNjb3VudE9yZ2FuaXphdGlvbjoxOmFiQzE=/spaces/U3BhY2U6MTp4eVo5/projects/TW9kZWw6MTpkZUZn?selectedTraceId=0123456789abcdef0123456789abcdef&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA=1700000000000&endA=1700086400000&envA=tracing&modelType=generative_llm