Phoenix
TypeScript APIPython APICommunityGitHubPhoenix Cloud
English
  • Documentation
  • Self-Hosting
  • Cookbooks
  • Learn
  • Integrations
  • SDK and API Reference
  • Release Notes
English
  • Arize Phoenix
  • Quickstarts
  • User Guide
  • Environments
  • Phoenix Demo
  • 🔭Tracing
    • Overview: Tracing
    • Quickstart: Tracing
      • Quickstart: Tracing (Python)
      • Quickstart: Tracing (TS)
    • Features: Tracing
      • Projects
      • Annotations
      • Sessions
    • Integrations: Tracing
    • How-to: Tracing
      • Setup Tracing
        • Setup using Phoenix OTEL
        • Setup using base OTEL
        • Using Phoenix Decorators
        • Setup Tracing (TS)
        • Setup Projects
        • Setup Sessions
      • Add Metadata
        • Add Attributes, Metadata, Users
        • Instrument Prompt Templates and Prompt Variables
      • Annotate Traces
        • Annotating in the UI
        • Annotating via the Client
        • Running Evals on Traces
        • Log Evaluation Results
      • Importing & Exporting Traces
        • Import Existing Traces
        • Export Data & Query Spans
        • Exporting Annotated Spans
      • Advanced
        • Mask Span Attributes
        • Suppress Tracing
        • Filter Spans to Export
        • Capture Multimodal Traces
    • Concepts: Tracing
      • How Tracing Works
      • What are Traces
      • Concepts: Annotations
      • FAQs: Tracing
  • 📃Prompt Engineering
    • Overview: Prompts
      • Prompt Management
      • Prompt Playground
      • Span Replay
      • Prompts in Code
    • Quickstart: Prompts
      • Quickstart: Prompts (UI)
      • Quickstart: Prompts (Python)
      • Quickstart: Prompts (TS)
    • How to: Prompts
      • Configure AI Providers
      • Using the Playground
      • Create a prompt
      • Test a prompt
      • Tag a prompt
      • Using a prompt
    • Concepts: Prompts
  • 🗄️Datasets & Experiments
    • Overview: Datasets & Experiments
    • Quickstart: Datasets & Experiments
    • How-to: Datasets
      • Creating Datasets
      • Exporting Datasets
    • Concepts: Datasets
    • How-to: Experiments
      • Run Experiments
      • Using Evaluators
  • 🧠Evaluation
    • Overview: Evals
      • Agent Evaluation
    • Quickstart: Evals
    • How to: Evals
      • Pre-Built Evals
        • Hallucinations
        • Q&A on Retrieved Data
        • Retrieval (RAG) Relevance
        • Summarization
        • Code Generation
        • Toxicity
        • AI vs Human (Groundtruth)
        • Reference (citation) Link
        • User Frustration
        • SQL Generation Eval
        • Agent Function Calling Eval
        • Agent Path Convergence
        • Agent Planning
        • Agent Reflection
        • Audio Emotion Detection
      • Eval Models
      • Build an Eval
      • Build a Multimodal Eval
      • Online Evals
      • Evals API Reference
    • Concepts: Evals
      • LLM as a Judge
      • Eval Data Types
      • Evals With Explanations
      • Evaluators
      • Custom Task Evaluation
  • 🔍Retrieval
    • Overview: Retrieval
    • Quickstart: Retrieval
    • Concepts: Retrieval
      • Retrieval with Embeddings
      • Benchmarking Retrieval
      • Retrieval Evals on Document Chunks
  • 🌌inferences
    • Quickstart: Inferences
    • How-to: Inferences
      • Import Your Data
        • Prompt and Response (LLM)
        • Retrieval (RAG)
        • Corpus Data
      • Export Data
      • Generate Embeddings
      • Manage the App
      • Use Example Inferences
    • Concepts: Inferences
    • API: Inferences
    • Use-Cases: Inferences
      • Embeddings Analysis
  • ⚙️Settings
    • Access Control (RBAC)
    • API Keys
    • Data Retention
Powered by GitBook

Platform

  • Tracing
  • Prompts
  • Datasets and Experiments
  • Evals

Software

  • Python Client
  • TypeScript Client
  • Phoenix Evals
  • Phoenix Otel

Resources

  • Container Images
  • X
  • Blue Sky
  • Blog

Integrations

  • OpenTelemetry
  • AI Providers

© 2025 Arize AI

On this page
  • Project Retention Policies
  • Deleting Traces Manually

Was this helpful?

Edit on GitHub
  1. Settings

Data Retention

PreviousAPI Keys

Last updated 9 days ago

Was this helpful?

By default Phoenix will store and preserve all your data and data retention is entirely under your control. However in production environments there might be good reasons to purge older data. Similar to data retention being infinite by default, Phoenix also does not gate the deletion of the data. If you no longer need certain projects, traces, datasets, experiments, or prompts, you can delete these resources through the UI as well as through the REST API.

Project Retention Policies

In Phoenix 9.0 or greater you will can automatically purge traces from projects by configuring a retention policy. Retention policies can be either time based or trace count based.

A retention policy starts deleting traces that are outside of the retention window

By default Phoenix comes with 1 project retention policy called Default . Every project in your instance is associated to this retention policy unless specified otherwise. The Default policy also specifies 0 days, which is equal to "Indefinite" retention.

If you simply want to preserve a static set amount of traces per project, you can simply adjust the max days traces will be stored in Phoenix and this will be applied to all current and future projects that get created. In some cases you might want to specify a different retention policy to a particular project (e.x. you might want to age out your playground spans quicker than spans from an actual application). In this case you can navigate to the Data Retention tab and create a new policy.

A policy is made up of:

  • name - a human friendly name for others to understand it (e.x. "one week")

  • rule - number of max days and or number of traces that will cause traces to be purged

  • schedule - a CRON schedule for when the policy will be enforced. It's recommended to do it during non-business hours for the least amount of discruption (if there is any)

Once you have created a policy you can go to the project config and associate the policy to the project. You must be an admin to perform this action.

Deleting Traces Manually

You can either delete traces by time or individually. To delete traces older than a certain date, click on the action button on a project an select remove data

By default phoenix retains all the data you send it
Create a new retention policy to associate with projects
Select your new policy in the project config tab
Click Remove Data. You will be able do delete traces older than a certain date.
Select a date. Traces older than the given date will be purged.
⚙️
How to configure retention policies