From 1cdb813196b1c9da4de782a4ff011031cb1db7a2 Mon Sep 17 00:00:00 2001
From: William FH <13333726+hinthornw@users.noreply.github.com>
Date: Sun, 3 Mar 2024 18:31:15 -0800
Subject: [PATCH] Improve notebook wording (#18472)

---
 docs/docs/langsmith/walkthrough.ipynb | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/docs/langsmith/walkthrough.ipynb b/docs/docs/langsmith/walkthrough.ipynb
index 0e9b6c5004f..155a4418b7b 100644
--- a/docs/docs/langsmith/walkthrough.ipynb
+++ b/docs/docs/langsmith/walkthrough.ipynb
@@ -400,12 +400,12 @@
    "id": "1cc51d0a-4982-4ff9-89c1-b294d5cce8f6",
    "metadata": {},
    "source": [
-    "#### Aggregate Evaluators\n",
+    "#### Batch Evaluators\n",
     "\n",
-    "Some metrics are only performed in aggregate or full \"test session\" level. These could be simple \n",
-    "classification metrics like Precision, Recall, or AUC, or other custom metrics.\n",
+    "Some metrics are aggregated over a full \"test\" without being assigned to an individual runs/examples. These could be as simple \n",
+    "as common classification metrics like Precision, Recall, or AUC, or it could be another custom aggregate metric.\n",
     "\n",
-    "You can define any custom metric on an aggregate level using a callable that accepts a list of Runs (system traces) and list of Examples (dataset records)."
+    "You can define any batch metric on a full test level by defining a function (or any callable) that accepts a list of Runs (system traces) and list of Examples (dataset records)."
    ]
   },
   {
@@ -476,7 +476,7 @@
     "            normalize_by=10,\n",
     "        ),\n",
     "    ],\n",
-    "    aggregate_evaluators=[max_pred_length],\n",
+    "    batch_evaluators=[max_pred_length],\n",
     ")"
    ]
   },