Full-Text Search

Full-text search lets you find all occurrences of a specific keyword or phrase across the inputs, outputs, and metadata of your traces and observations. This is especially useful when debugging complex applications where you remember a piece of content but not which trace it belongs to.

Search in the UI

Use the search bar above the traces and observations tables to search across input and output content. Matching traces and observations are returned so you can quickly locate the run you are looking for and combine search with the existing filters and time range selectors.

Performance

Search uses ClickHouse full-text search. Text indexes let Langfuse skip over data that cannot match a query before reading full observation payloads, which keeps search fast even for large projects with high-volume traces. You can read more in the ClickHouse GA announcement.

Search via the API

The Observations API v2 supports a matches operator for token-based full-text search on input, output, and string metadata filters.

When building filters on /api/public/v2/observations, prefer = when you know the exact value and matches when you want token-based search:

• matches is case-insensitive for input and output, so refund failed can match Refund Failed.
• For metadata filters, matches is case-sensitive and applies to the string metadata value of the selected key.
• Substring operators such as contains, starts with, and ends with are rejected with 400 on input and output filters because they would require slow full-content scans. Use matches for token search on these fields instead.

Example matches filter for observation output:

[
  {
    "type": "string",
    "column": "output",
    "operator": "matches",
    "value": "refund failed"
  }
]

Example exact metadata filter:

[
  {
    "type": "stringObject",
    "column": "metadata",
    "key": "environment",
    "operator": "=",
    "value": "production"
  }
]

Pass the JSON array as the URL-encoded filter query parameter on GET /api/public/v2/observations. See the Observations API v2 docs and the API reference for the full filter schema.

GitHub Discussions