Skip to content

[MLOB] document metadata for custom evaluations #30530

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+17 −2
Open

[MLOB] document metadata for custom evaluations #30530

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
86c77fc
document metadata
lievan Jul 17, 2025
ea76fe2
Merge branch 'master' into evan.li/eval-metadat
lievan Jul 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion content/en/llm_observability/sdk/_index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1234,6 +1234,10 @@ The `LLMObs.submit_evaluation_for()` method accepts the following arguments:
`tags`
: optional - _dictionary_
<br />A dictionary of string key-value pairs that users can add as tags regarding the evaluation. For more information about tags, see [Getting Started with Tags][2].

`metadata`
: optional - _dictionary_
<br />A JSON serializable dictionary of key-value metadata pairs relevant to the evaluation metric.
{{% /collapse-content %}}

#### Example
Expand Down Expand Up @@ -1262,6 +1266,7 @@ def llm_call():
metric_type="score",
value=10,
tags={"evaluation_provider": "ragas"},
metadata={"flagged_segments": ["harmful part of output", "some other harmful part of output"]}
)

# joining an evaluation to a span via span ID and trace ID
Expand All @@ -1273,6 +1278,7 @@ def llm_call():
metric_type="score",
value=10,
tags={"evaluation_provider": "ragas"},
metadata={"flagged_segments": ["harmful part of output", "some other harmful part of output"]}
)
return completion
{{< /code-block >}}
Expand Down Expand Up @@ -1314,6 +1320,10 @@ The `evaluationOptions` object can contain the following:
`tags`
: optional - _dictionary_
<br />A dictionary of string key-value pairs that users can add as tags regarding the evaluation. For more information about tags, see [Getting Started with Tags][1].

`metadata`
: optional - _dictionary_
<br />A JSON serializable dictionary of key-value metadata pairs relevant to the evaluation metric.
{{% /collapse-content %}}

#### Example
Expand All @@ -1326,7 +1336,8 @@ function llmCall () {
label: "harmfulness",
metricType: "score",
value: 10,
tags: { evaluationProvider: "ragas" }
tags: { evaluationProvider: "ragas" },
metadata: { flaggedSegments: ["harmful part of output", "some other harmful part of output"] }
})
return completion
}
Expand Down
6 changes: 5 additions & 1 deletion content/en/llm_observability/setup/api.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,7 +348,10 @@ Evaluations must be joined to a unique span. You can identify the target span us
"timestamp_ms": 1609479200,
"metric_type": "score",
"label": "Accuracy",
"score_value": 3
"score_value": 3,
"metadata": {
"flagged_segments": ["harmful part of output", "some other harmful part of output"]
}
}
]
}
Expand Down Expand Up @@ -380,6 +383,7 @@ Evaluations must be joined to a unique span. You can identify the target span us
| categorical_value [*required if the metric_type is "categorical"*] | string | A string representing the category that the evaluation belongs to. |
| score_value [*required if the metric_type is "score"*] | number | A score value of the evaluation. |
| tags | [[Tag](#tag)] | A list of tags to apply to this particular evaluation metric. |
| metadata | Dict | Additional data relevant to the evaluation. |

#### JoinOn

Expand Down
Loading