phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix security update
All checks were successful
Build and Push playground container / build-playground (push) Successful in 1m57s
Details
Build and Push container / build (push) Successful in 4m33s
Details

Browse source
This commit is contained in:
Angel Nunez Mencias 2025-06-03 20:07:06 +02:00
parent 8943b283e9
commit b174effe05
Signed by: angel.nunez
SSH key fingerprint: SHA256:z1nFAg1v1AfbhEHrgBetByUJUwziv2R2f4VyN75opcg
14 changed files with 45 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/distribution/ui/page/evaluations/native_eval.py
View file

@ -9,13 +9,13 @@ import json
import pandas as pd
import streamlit as st
from llama_stack.distribution.ui.modules.api import llama_stack_api
from llama_stack.distribution.ui.modules.api import LlamaStackApi
def select_benchmark_1():
# Select Benchmarks
st.subheader("1. Choose An Eval Task")
benchmarks = llama_stack_api.client.benchmarks.list()
benchmarks = LlamaStackApi().client.benchmarks.list()
benchmarks = {et.identifier: et for et in benchmarks}
benchmarks_names = list(benchmarks.keys())
selected_benchmark = st.selectbox(
@ -47,7 +47,7 @@ def define_eval_candidate_2():
# Define Eval Candidate
candidate_type = st.radio("Candidate Type", ["model", "agent"])
available_models = llama_stack_api.client.models.list()
available_models = LlamaStackApi().client.models.list()
available_models = [model.identifier for model in available_models]
selected_model = st.selectbox(
"Choose a model",
@ -167,7 +167,7 @@ def run_evaluation_3():
eval_candidate = st.session_state["eval_candidate"]
dataset_id = benchmarks[selected_benchmark].dataset_id
rows = llama_stack_api.client.datasets.iterrows(
rows = LlamaStackApi().client.datasets.iterrows(
dataset_id=dataset_id,
)
total_rows = len(rows.data)
@ -208,7 +208,7 @@ def run_evaluation_3():
progress = i / len(rows)
progress_bar.progress(progress, text=progress_text)
# Run evaluation for current row
eval_res = llama_stack_api.client.eval.evaluate_rows(
eval_res = LlamaStackApi().client.eval.evaluate_rows(
benchmark_id=selected_benchmark,
input_rows=[r],
scoring_functions=benchmarks[selected_benchmark].scoring_functions,