arize-trace

INVOKE THIS SKILL when downloading or exporting Arize traces and spans. Covers exporting traces by ID, sessions by ID, and debugging LLM application issues using the ax CLI.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "arize-trace" with this command: npx skills add arize-ai/arize-skills/arize-ai-arize-skills-arize-trace

Arize Trace Skill

Concepts

  • Trace = a tree of spans sharing a context.trace_id, rooted at a span with parent_id = null
  • Span = a single operation (LLM call, tool call, retriever, chain, agent)
  • Session = a group of traces sharing attributes.session.id (e.g., a multi-turn conversation)

Use ax spans export to download trace data. This is the only supported command for retrieving spans.

Resolving project for export: The PROJECT positional argument accepts either a project name or a base64 project ID. When using a name, --space-id is required. If you hit limit errors or 401 Unauthorized when using a project name, resolve it to a base64 ID: run ax projects list --space-id SPACE_ID -l 100 -o json, find the project by name, and use its id as PROJECT.

Exploratory export rule: When exporting spans or traces without a specific --trace-id, --span-id, or --session-id (i.e., browsing/exploring a project), always start with -l 50 to pull a small sample first. Summarize what you find, then pull more data only if the user asks or the task requires it. This avoids slow queries and overwhelming output on large projects.

Default output directory: Always use --output-dir .arize-tmp-traces on every ax spans export call. The CLI automatically creates the directory and adds it to .gitignore.

Prerequisites

Three things are needed: ax CLI, an API key (env var or profile), and a space ID. A project name or ID is also needed but usually comes from the user's message.

Install ax

Verify ax is installed and working before proceeding:

  1. Check if ax is on PATH: command -v ax (Unix) or where ax (Windows)
  2. If not found, check common install locations:
    • macOS/Linux: test -x ~/.local/bin/ax && export PATH="$HOME/.local/bin:$PATH"
    • Windows: check %APPDATA%\Python\Scripts\ax.exe or %LOCALAPPDATA%\Programs\Python\Scripts\ax.exe
  3. If still not found, install it (requires shell access to install packages):
    • Preferred: uv tool install arize-ax-cli
    • Alternative: pipx install arize-ax-cli
    • Fallback: pip install arize-ax-cli
  4. After install, if ax is not on PATH:
    • macOS/Linux: export PATH="$HOME/.local/bin:$PATH"
    • Windows (PowerShell): $env:PATH = "$env:APPDATA\Python\Scripts;$env:PATH"
  5. If ax --version fails with an SSL/certificate error:
    • macOS: export SSL_CERT_FILE=/etc/ssl/cert.pem
    • Linux: export SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
    • Windows (PowerShell): $env:SSL_CERT_FILE = "C:\Program Files\Common Files\SSL\cert.pem" (or use python -c "import certifi; print(certifi.where())" to find the cert bundle)
  6. ax --version must succeed before proceeding. If it doesn't, stop and ask the user for help.

Verify environment

Run a quick check for credentials:

macOS/Linux (bash):

ax --version && echo "--- env ---" && if [ -n "$ARIZE_API_KEY" ]; then echo "ARIZE_API_KEY: (set)"; else echo "ARIZE_API_KEY: (not set)"; fi && echo "ARIZE_SPACE_ID: ${ARIZE_SPACE_ID:-(not set)}" && echo "--- profiles ---" && ax profiles show 2>&1

Windows (PowerShell):

ax --version; Write-Host "--- env ---"; Write-Host "ARIZE_API_KEY: $(if ($env:ARIZE_API_KEY) { '(set)' } else { '(not set)' })"; Write-Host "ARIZE_SPACE_ID: $env:ARIZE_SPACE_ID"; Write-Host "--- profiles ---"; ax profiles show 2>&1

Read the output and proceed immediately if either the env var or the profile has an API key. Only ask the user if both are missing. Resolve failures:

  • No API key in env and no profile → AskQuestion: "Arize API key (https://app.arize.com/admin > API Keys)"
  • Space ID unknown → AskQuestion, or run ax projects list -o json --limit 100 --space-id $ARIZE_SPACE_ID and present as selectable options
  • Project unclear → ask, or run ax projects list -o json --limit 100 and search for a match

IMPORTANT: --space-id is required when using a human-readable project name as the PROJECT positional argument. It is not needed when using a base64-encoded project ID. If you hit 401 Unauthorized or limit errors when using a project name, resolve it to a base64 ID first (see "Resolving project for export" in Concepts).

Export Spans: ax spans export

The primary command for downloading trace data to a file.

By trace ID

ax spans export PROJECT_ID --trace-id TRACE_ID --output-dir .arize-tmp-traces

By span ID

ax spans export PROJECT_ID --span-id SPAN_ID --output-dir .arize-tmp-traces

By session ID

ax spans export PROJECT_ID --session-id SESSION_ID --output-dir .arize-tmp-traces

Flags

FlagTypeRequiredDescription
--trace-idstringmutexFilter: context.trace_id = 'X'
--span-idstringmutexFilter: context.span_id = 'X'
--session-idstringmutexFilter: attributes.session.id = 'X'
PROJECTstring (positional)yes (or $ARIZE_DEFAULT_PROJECT)Project name or base64 ID (positional arg, not a flag)
--space-idstringyes (when PROJECT is a name)Space ID; required to resolve project names. Not needed when using a base64 project ID. Also required when using --all (Arrow Flight).
--daysintnoLookback window (default: 30)
--start-timestringnoOverride start (ISO 8601)
--end-timestringnoOverride end (ISO 8601)
--output-dirstringnoOutput directory (default: .arize-tmp-traces; ensure it is gitignored — see above)
--stdoutboolnoPrint JSON to stdout instead of file
--allboolnoUse Arrow Flight for bulk export (see below)

Exactly one of --trace-id, --span-id, --session-id is required.

Output is a JSON array of span objects. File naming: {type}_{id}_{timestamp}/spans.json.

Bulk export with --all (Arrow Flight)

By default, ax spans export uses the REST API which is limited to 500 spans per page and capped by --limit. Pass --all to switch to Arrow Flight for streaming bulk export with no span limit.

ax spans export PROJECT_ID --space-id SPACE_ID --filter "status_code = 'ERROR'" --all --output-dir .arize-tmp-traces

REST vs Flight trade-offs:

  • REST (default): Lower friction -- no Arrow/Flight dependency needed, uses standard HTTPS ports, works through any corporate proxy or firewall. Limited to 500 spans per page.
  • Flight (--all): Required for bulk export beyond 500 spans. Uses gRPC+TLS on a separate host/port which some corporate networks may block.

When to use --all:

  • Exporting more than 500 spans
  • Downloading full traces with many child spans
  • Large time-range exports

Agent auto-escalation rule: If a REST export returns exactly the number of spans requested by -l (or 500 if no limit was set), the result is likely truncated. Increase -l or re-run with --all to get the full dataset — but only when the user asks or the task requires more data.

Requirements for --all:

  • --space-id is required (Flight uses space_id + project_name, not project_id)
  • --limit is ignored when --all is set

Networking notes for --all: Arrow Flight connects to flight.arize.com:443 via gRPC+TLS -- this is a different host from the REST API (api.arize.com). On internal or private networks, the Flight endpoint may use a different host/port. Configure via:

  • ax profile: flight_host, flight_port, flight_scheme
  • Environment variables: ARIZE_FLIGHT_HOST, ARIZE_FLIGHT_PORT, ARIZE_FLIGHT_SCHEME

The --all flag is also available on ax traces export, ax datasets export, and ax experiments export with the same behavior (REST by default, Flight with --all).

Export Traces: ax traces export

Export full traces -- all spans belonging to traces that match a filter. Uses a two-phase approach:

  1. Phase 1: Find spans matching --filter (up to --limit via REST, or all via Flight with --all)
  2. Phase 2: Extract unique trace IDs, then fetch every span for those traces
# Explore recent traces (start small with -l 50, pull more if needed)
ax traces export PROJECT_ID -l 50 --output-dir .arize-tmp-traces

# Export traces with error spans (REST, up to 500 spans in phase 1)
ax traces export PROJECT_ID --filter "status_code = 'ERROR'" --stdout

# Export all traces matching a filter via Flight (no limit)
ax traces export PROJECT_ID --space-id SPACE_ID --filter "status_code = 'ERROR'" --all

Flags

FlagTypeDefaultDescription
PROJECTstringrequiredProject name or base64 ID (positional arg)
--filterstringnoneFilter expression for phase-1 span lookup
--space-idstringnoneSpace ID; required when PROJECT is a name or when using --all (Arrow Flight)
--limit, -lint50Max number of traces to export
--daysint30Lookback window in days
--start-timestringnoneOverride start (ISO 8601)
--end-timestringnoneOverride end (ISO 8601)
--output-dirstring.Output directory
--stdoutboolfalsePrint JSON to stdout instead of file
--allboolfalseUse Arrow Flight for both phases (see spans --all docs above)
-p, --profilestringdefaultConfiguration profile

How it differs from ax spans export

  • ax spans export exports individual spans matching a filter
  • ax traces export exports complete traces -- it finds spans matching the filter, then pulls ALL spans for those traces (including siblings and children that may not match the filter)

Filter Syntax Reference

SQL-like expressions passed to --filter.

Common filterable columns

ColumnTypeDescriptionExample Values
namestringSpan name'ChatCompletion', 'retrieve_docs'
status_codestringStatus'OK', 'ERROR', 'UNSET'
latency_msnumberDuration in ms100, 5000
parent_idstringParent span IDnull for root spans
context.trace_idstringTrace ID
context.span_idstringSpan ID
attributes.session.idstringSession ID
attributes.openinference.span.kindstringSpan kind'LLM', 'CHAIN', 'TOOL', 'AGENT', 'RETRIEVER', 'RERANKER', 'EMBEDDING', 'GUARDRAIL', 'EVALUATOR'
attributes.llm.model_namestringLLM model'gpt-4o', 'claude-3'
attributes.input.valuestringSpan input
attributes.output.valuestringSpan output
attributes.error.typestringError type'ValueError', 'TimeoutError'
attributes.error.messagestringError message
event.attributesstringError tracebacksUse CONTAINS (not exact match)

Operators

=, !=, <, <=, >, >=, AND, OR, IN, CONTAINS, LIKE, IS NULL, IS NOT NULL

Examples

status_code = 'ERROR'
latency_ms > 5000
name = 'ChatCompletion' AND status_code = 'ERROR'
attributes.llm.model_name = 'gpt-4o'
attributes.openinference.span.kind IN ('LLM', 'AGENT')
attributes.error.type LIKE '%Transport%'
event.attributes CONTAINS 'TimeoutError'

Tips

  • Prefer IN over multiple OR conditions: name IN ('a', 'b', 'c') not name = 'a' OR name = 'b' OR name = 'c'
  • Start broad with LIKE, then switch to = or IN once you know exact values
  • Use CONTAINS for event.attributes (error tracebacks) -- exact match is unreliable on complex text
  • Always wrap string values in single quotes

Workflows

Debug a failing trace

  1. ax traces export PROJECT_ID --filter "status_code = 'ERROR'" -l 50 --output-dir .arize-tmp-traces
  2. Read the output file, look for spans with status_code: ERROR
  3. Check attributes.error.type and attributes.error.message on error spans

Download a conversation session

  1. ax spans export PROJECT_ID --session-id SESSION_ID --output-dir .arize-tmp-traces
  2. Spans are ordered by start_time, grouped by context.trace_id
  3. If you only have a trace_id, export that trace first, then look for attributes.session.id in the output to get the session ID

Export for offline analysis

ax spans export PROJECT_ID --trace-id TRACE_ID --output-dir .arize-tmp-traces --stdout | jq '.[]'

Span Column Reference (OpenInference Semantic Conventions)

Core Identity and Timing

ColumnDescription
nameSpan operation name (e.g., ChatCompletion, retrieve_docs)
context.trace_idTrace ID -- all spans in a trace share this
context.span_idUnique span ID
parent_idParent span ID. null for root spans (= traces)
start_timeWhen the span started (ISO 8601)
end_timeWhen the span ended
latency_msDuration in milliseconds
status_codeOK, ERROR, UNSET
status_messageOptional message (usually set on errors)
attributes.openinference.span.kindLLM, CHAIN, TOOL, AGENT, RETRIEVER, RERANKER, EMBEDDING, GUARDRAIL, EVALUATOR

Where to Find Prompts and LLM I/O

Generic input/output (all span kinds):

ColumnWhat it contains
attributes.input.valueThe input to the operation. For LLM spans, often the full prompt or serialized messages JSON. For chain/agent spans, the user's question.
attributes.input.mime_typeFormat hint: text/plain or application/json
attributes.output.valueThe output. For LLM spans, the model's response. For chain/agent spans, the final answer.
attributes.output.mime_typeFormat hint for output

LLM-specific message arrays (structured chat format):

ColumnWhat it contains
attributes.llm.input_messagesStructured input messages array (system, user, assistant, tool). Where chat prompts live in role-based format.
attributes.llm.input_messages.rolesArray of roles: system, user, assistant, tool
attributes.llm.input_messages.contentsArray of message content strings
attributes.llm.output_messagesStructured output messages from the model
attributes.llm.output_messages.contentsModel response content
attributes.llm.output_messages.tool_calls.function.namesTool calls the model wants to make
attributes.llm.output_messages.tool_calls.function.argumentsArguments for those tool calls

Prompt templates:

ColumnWhat it contains
attributes.llm.prompt_template.templateThe prompt template with variable placeholders (e.g., "Answer {question} using {context}")
attributes.llm.prompt_template.variablesTemplate variable values (JSON object)

Finding prompts by span kind:

  • LLM span: Check attributes.llm.input_messages for structured chat messages, OR attributes.input.value for serialized prompt. Check attributes.llm.prompt_template.template for the template.
  • Chain/Agent span: Check attributes.input.value for the user's question. Actual LLM prompts are on child LLM spans.
  • Tool span: Check attributes.input.value for tool input, attributes.output.value for tool result.

LLM Model and Cost

ColumnDescription
attributes.llm.model_nameModel identifier (e.g., gpt-4o, claude-3-opus-20240229)
attributes.llm.invocation_parametersModel parameters JSON (temperature, max_tokens, top_p, etc.)
attributes.llm.token_count.promptInput token count
attributes.llm.token_count.completionOutput token count
attributes.llm.token_count.totalTotal tokens
attributes.llm.cost.promptInput cost in USD
attributes.llm.cost.completionOutput cost in USD
attributes.llm.cost.totalTotal cost in USD

Tool Spans

ColumnDescription
attributes.tool.nameTool/function name
attributes.tool.descriptionTool description
attributes.tool.parametersTool parameter schema (JSON)

Retriever Spans

ColumnDescription
attributes.retrieval.documentsRetrieved documents array
attributes.retrieval.documents.idsDocument IDs
attributes.retrieval.documents.scoresRelevance scores
attributes.retrieval.documents.contentsDocument text content
attributes.retrieval.documents.metadatasDocument metadata

Reranker Spans

ColumnDescription
attributes.reranker.queryThe query being reranked
attributes.reranker.model_nameReranker model
attributes.reranker.top_kNumber of results
attributes.reranker.input_documents.*Input documents (ids, scores, contents, metadatas)
attributes.reranker.output_documents.*Reranked output documents

Session, User, and Custom Metadata

ColumnDescription
attributes.session.idSession/conversation ID -- groups traces into multi-turn sessions
attributes.user.idEnd-user identifier
attributes.metadata.*Custom key-value metadata. Any key under this prefix is user-defined (e.g., attributes.metadata.user_email). Filterable.

Errors and Exceptions

ColumnDescription
attributes.exception.typeException class name (e.g., ValueError, TimeoutError)
attributes.exception.messageException message text
event.attributesError tracebacks and detailed event data. Use CONTAINS for filtering.

Evaluations and Annotations

ColumnDescription
annotation.<name>.labelHuman or auto-eval label (e.g., correct, incorrect)
annotation.<name>.scoreNumeric score (e.g., 0.95)
annotation.<name>.textFreeform annotation text

Embeddings

ColumnDescription
attributes.embedding.model_nameEmbedding model name
attributes.embedding.textsText chunks that were embedded

Troubleshooting

ProblemSolution
ax: command not foundCheck ~/.local/bin/ax; if missing: uv tool install arize-ax-cli (requires shell access to install packages). Then export PATH="$HOME/.local/bin:$PATH"
SSL: CERTIFICATE_VERIFY_FAILEDmacOS: export SSL_CERT_FILE=/etc/ssl/cert.pem. Linux: export SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt. Windows: $env:SSL_CERT_FILE = (python -c "import certifi; print(certifi.where())")
No such command on a subcommand that should existThe installed ax is outdated. Reinstall from the local workspace: uv tool install --force --reinstall /path/to/arize/sdk/python/arize-ax-cli (requires shell access to install packages)
No profile foundFollow "Resolve credentials" in Prerequisites to auto-discover or prompt for the API key
401 Unauthorized with valid API keyYou are likely using a project name without --space-id. Add --space-id SPACE_ID, or resolve to a base64 project ID first: ax projects list --space-id SPACE_ID -l 100 -o json and use the project's id.
No spans foundExpand --days (default 30), verify project ID
Filter errorCheck column name spelling, wrap string values in single quotes
Timeout on large exportUse --days 7 to narrow the time range

Save Credentials

At session end, if the user manually provided an API key, space ID, or project ID (not loaded from an existing profile), offer to save them to ~/.arize/config.toml. Use AskQuestion with "Yes, save them" / "No thanks". Skip if all values were already in the profile.

Read the existing file (or create it), add/update only the new fields, and write it back:

[auth]
api_key = "THE_API_KEY"

[defaults]
space_id = "THE_SPACE_ID"
project = "THE_PROJECT_NAME"

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

arize-experiment

No summary provided by upstream source.

Repository SourceNeeds Review
General

arize-prompt-optimization

No summary provided by upstream source.

Repository SourceNeeds Review
General

arize-dataset

No summary provided by upstream source.

Repository SourceNeeds Review
General

arize-instrumentation

No summary provided by upstream source.

Repository SourceNeeds Review