> ## Documentation Index
> Fetch the complete documentation index at: https://docs.latitude.so/llms.txt
> Use this file to discover all available pages before exploring further.
# Overview
> Backfill traces from Langfuse, LangSmith, or Braintrust into a Latitude project.
## Overview
Latitude can import the traces you already have in another observability platform, so you
do not start from an empty project when you switch. Imports run from **Project settings →
Imports** and finish in the background — you can close the tab.
Importing is for **history**. Data produced from now on should arrive through
[live tracing](/telemetry/start-tracing), which is what powers evaluations, monitors and
signals in real time.
Pick your platform to get started:
Langfuse Cloud, using your public and secret keys.
Runs from a LangSmith project, with configurable session grouping.
Project logs, queried through BTQL.
***
## How an import runs
Pick the platform and the region your account is in, then enter its credentials.
Latitude tests them before continuing and discards them once the import finishes.
Choose the source project, the time range and how many traces to import. Latitude
shows a sample of what will come through before anything is written.
The import runs in the background. Progress, counts and any errors appear in the
imports table, which refreshes while it runs.
Every platform is imported from its **cloud** offering — you pick a region, never a URL.
Self-hosted deployments are not supported yet.
***
## What gets imported
| Imported | Not imported |
| ------------------------------------------ | ---------------------------------------------------- |
| Traces and spans | Scores and annotations |
| Session and user identity | Datasets and evaluations |
| Tags and metadata | Prompt registries (references land in span metadata) |
| Messages, tool calls, token usage and cost | |
Imported spans carry `import.*` metadata (platform, source project, and the original trace
and span ids), so you can always tell imported history from live telemetry. If your
organization has a **PII redaction policy**, it applies to imported traces exactly as it
does to live ones.
An imported trace goes through the same pipeline as one that arrives live: it is grouped
into sessions, embedded for semantic search, indexed, and evaluated by flaggers. Because of
that it is **billed the same way: one credit per trace**. Re-importing the same trace does
not charge twice.
***
## Limits
| Limit | How it is set |
| ----------------------- | ---------------------------------------------------------------------------- |
| Traces per import | Defaults to your plan's remaining usage for the period; hard ceiling 100,000 |
| Time range | Defaults to the last 90 days, bounded by your plan's span retention |
| Imports running at once | One per organization |
Traces are imported **newest first**, so an import that stops early — it reached your trace
limit or your plan's remaining usage — keeps the most recent history rather than an
arbitrary slice. A stopped import is marked **capped**, everything imported stays, and
**Continue** resumes it from where it stopped.
***
## Retrying
Imports are **idempotent**: every imported span gets a deterministic id derived from its
source ids, so importing the same range twice updates the same spans instead of duplicating
them. If an import fails or is cancelled, **Retry** resumes from where it stopped — you
will be asked for credentials again, because Latitude never keeps them after an import
ends.