native eval

llama_stack/distribution/ui/app.py

@@ -11,7 +11,13 @@ def main():
     application_evaluation_page = st.Page(
         "page/evaluations/app_eval.py",
         title="Application Evaluation",
-        icon="🦙",
+        icon="📊",
+        default=False,
+    )
+    native_evaluation_page = st.Page(
+        "page/evaluations/native_eval.py",
+        title="Native Evaluation",
+        icon="📊",
         default=False,
     )
 
@@ -28,7 +34,7 @@ def main():
 
     pg = st.navigation(
         {
-            "Evaluations": [application_evaluation_page],
+            "Evaluations": [application_evaluation_page, native_evaluation_page],
             "Playground": [chat_page, rag_page],
             "Distribution": [distribution_page],
         }

llama_stack/distribution/ui/page/evaluations/app_eval.py

@@ -16,7 +16,7 @@ from modules.utils import process_dataset
 def application_evaluation_page():
 
     st.set_page_config(page_title="Application Evaluation", page_icon="🦙")
-    st.title("🦙 Llama Stack Evaluations")
+    st.title("🦙 Llama Stack Application Evaluations")
 
     # File uploader
     uploaded_file = st.file_uploader("Upload Dataset", type=["csv", "xlsx", "xls"])

llama_stack/distribution/ui/page/evaluations/native_eval.py

@@ -0,0 +1,33 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+import streamlit as st
+
+from modules.api import llama_stack_api
+
+
+def native_evaluation_page():
+
+    st.set_page_config(page_title="Native Evaluations", page_icon="🦙")
+    st.title("🦙 Llama Stack Native Evaluations")
+
+    # Select Eval Tasks
+    st.subheader("Select Eval Tasks")
+    eval_tasks = llama_stack_api.client.eval_tasks.list()
+    eval_tasks = {et.identifier: et for et in eval_tasks}
+    eval_tasks_names = list(eval_tasks.keys())
+    selected_eval_task = st.selectbox(
+        "Choose an eval task.",
+        options=eval_tasks_names,
+        help="Choose an eval task. Each eval task is parameterized by a dataset, and list of scoring functions.",
+    )
+    st.json(eval_tasks[selected_eval_task], expanded=True)
+
+    # Define Eval Candidate
+    st.subheader("Define Eval Candidate")
+    # eval_candidate = {}
+
+
+native_evaluation_page()

llama_stack/distribution/ui/page/playground/rag.py

@@ -15,7 +15,7 @@ from modules.utils import data_url_from_file
 
 
 def rag_chat_page():
-    st.title("RAG")
+    st.title("🦙 RAG")
 
     with st.sidebar:
         # File/Directory Upload Section