From a550f171287576ddf65df4e1e238b34cab31cd49 Mon Sep 17 00:00:00 2001
From: Yang Yang <yyy@meta.com>
Date: Tue, 18 Mar 2025 10:40:41 -0700
Subject: [PATCH] rebase onto new dataset schema

---
 .../templates/open-benchmark/open_benchmark.py    | 13 ++++---------
 llama_stack/templates/open-benchmark/run.yaml     | 15 +++++----------
 2 files changed, 9 insertions(+), 19 deletions(-)

diff --git a/llama_stack/templates/open-benchmark/open_benchmark.py b/llama_stack/templates/open-benchmark/open_benchmark.py
index 6dbc65495..b019b2e4f 100644
--- a/llama_stack/templates/open-benchmark/open_benchmark.py
+++ b/llama_stack/templates/open-benchmark/open_benchmark.py
@@ -206,15 +206,10 @@ def get_distribution_template() -> DistributionTemplate:
         DatasetInput(
             dataset_id="docvqa",
             provider_id="huggingface",
-            url=URL(uri="https://huggingface.co/datasets/llamastack/docvqa"),
-            metadata={
-                "path": "llamastack/docvqa",
-                "split": "val",
-            },
-            dataset_schema={
-                "chat_completion_input": {"type": "string"},
-                "expected_answer": {"type": "string"},
-            },
+            purpose=DatasetPurpose.eval_messages_answer,
+            source=URIDataSource(
+                uri="huggingface://datasets/llamastack/docvqa?split=val",
+            ),
         ),
     ]
 
diff --git a/llama_stack/templates/open-benchmark/run.yaml b/llama_stack/templates/open-benchmark/run.yaml
index 29c2ffb4f..4233bc4f5 100644
--- a/llama_stack/templates/open-benchmark/run.yaml
+++ b/llama_stack/templates/open-benchmark/run.yaml
@@ -191,16 +191,11 @@ datasets:
 <<<<<<< HEAD
 =======
   provider_id: huggingface
-- dataset_schema:
-    chat_completion_input:
-      type: string
-    expected_answer:
-      type: string
-  url:
-    uri: https://huggingface.co/datasets/llamastack/docvqa
-  metadata:
-    path: llamastack/docvqa
-    split: val
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/docvqa?split=val
+  metadata: {}
   dataset_id: docvqa
   provider_id: huggingface
 >>>>>>> 81df5a4e (add DocVQA scoring)