fix

docs/evaluation/how_to_guides/evaluation/custom_evaluator.mdx

@@ -40,8 +40,8 @@ These functions can be passed directly into [evaluate()](https://langsmith-sdk.r
       import type { EvaluationResult } from "langsmith/evaluation";
       import type { Run, Example } from "langsmith/schemas";
 
-      function correct(rootRun: Run, example: Example): EvaluationResult {
-        const score = rootRun.outputs?.output === example.outputs?.output;
+      function correct(run: Run, example: Example): EvaluationResult {
+        const score = run.outputs?.output === example.outputs?.output;
         return { key: "correct", score };
       }
     `,

docs/evaluation/how_to_guides/evaluation/metric_type.mdx

@@ -6,22 +6,16 @@ import {
 
 # How to return categorical vs numerical metrics
 
-:::info Key concepts
-
-- Metrics
-
-:::
-
 LangSmith supports both categorical and numerical metrics, and you can return either when writing a [custom evaluator](../../how_to_guides/evaluation/custom_evaluator).
 
 For an evaluator result to be logged as a numerical metric, it must returned as:
 
-- an `int`, `float`, or `bool`
+- (Python only) an `int`, `float`, or `bool`
 - a dict of the form `{"key": "metric_name", "score": int | float | bool}`
 
 For an evaluator result to be logged as a categorical metric, it must be returned as:
 
-- a `str`
+- (Python only) a `str`
 - a dict of the form `{"key": "metric_name", "value": str | int | float | bool}`
 
 Here are some examples:
@@ -58,15 +52,14 @@ Here are some examples:
     })`
       import type { Run, Example } from "langsmith/schemas";
 
-      function multipleScores(rootRun: Run, example: Example) {
+      function numericalMetric(run: Run, example: Example) {
+        // Your evaluation logic here
+        return { key: "numerical_metric", score: 0.8};
+      }
+
+      function categoricalMetric(run: Run, example: Example) {
         // Your evaluation logic here
-        return {
-            results: [
-                { key: "precision", score: 0.8 },
-                { key: "recall", score: 0.9 },
-                { key: "f1", score: 0.85 },
-            ],
-        };
+        return { key: "categorical_metric", value: "english"};
       }
     `,
 

vercel.json

@@ -187,8 +187,8 @@
       "destination": "/prompt_engineering/tutorials/optimize_classifier"
     },
     {
-        "source": "evaluation/how_to_guides/evaluation/evaluate_llm_application#evaluate-on-a-particular-version-of-a-dataset",
-        "destination": "evaluation/how_to_guides/evaluation/dataset_version"
+        "source": "/evaluation/how_to_guides/evaluation/evaluate_llm_application#evaluate-on-a-particular-version-of-a-dataset",
+        "destination": "/evaluation/how_to_guides/evaluation/dataset_version"
     }
   ],
   "builds": [