experiment with app.py

app.py

@@ -1,35 +1,247 @@
 import gradio as gr
-from gradio_leaderboard import Leaderboard, SelectColumns, ColumnFilter
-from pathlib import Path
+from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 import pandas as pd
+from apscheduler.schedulers.background import BackgroundScheduler
+from huggingface_hub import snapshot_download
+from pathlib import Path  # ⬅️ for local JSON
 
-abs_path = Path(__file__).parent
-df = pd.read_json(abs_path / "leaderboard_data.json")
+from src.about import (
+    CITATION_BUTTON_LABEL,
+    CITATION_BUTTON_TEXT,
+    EVALUATION_QUEUE_TEXT,
+    INTRODUCTION_TEXT,
+    LLM_BENCHMARKS_TEXT,
+    TITLE,
+)
+from src.display.css_html_js import custom_css
+from src.display.utils import (
+    BENCHMARK_COLS,
+    COLS,
+    EVAL_COLS,
+    EVAL_TYPES,
+    AutoEvalColumn,
+    ModelType,
+    fields,
+    WeightType,
+    Precision
+)
+from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
+from src.populate import get_evaluation_queue_df, get_leaderboard_df
+from src.submission.submit import add_new_eval
 
-with gr.Blocks() as demo:
-    gr.Markdown("# 🏆 Model Leaderboard")
 
-    Leaderboard(
-        value=df,
-        # choose what shows by default (must match your column names)
+def restart_space():
+    API.restart_space(repo_id=REPO_ID)
+
+### Space initialisation (pull queue/results datasets like before)
+try:
+    print(EVAL_REQUESTS_PATH)
+    snapshot_download(
+        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+    )
+except Exception:
+    restart_space()
+try:
+    print(EVAL_RESULTS_PATH)
+    snapshot_download(
+        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+    )
+except Exception:
+    restart_space()
+
+# Original leaderboard (unchanged)
+LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
+
+(
+    finished_eval_queue_df,
+    running_eval_queue_df,
+    pending_eval_queue_df,
+) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
+
+def init_leaderboard(dataframe):
+    if dataframe is None or dataframe.empty:
+        raise ValueError("Leaderboard DataFrame is empty or None.")
+    return Leaderboard(
+        value=dataframe,
+        datatype=[c.type for c in fields(AutoEvalColumn)],
         select_columns=SelectColumns(
-            default_selection=["Model", "Average ⬆️", "ARC", "HellaSwag", "MMLU", "TruthfulQA", "Winogrande", "GSM8K"],
-            cant_deselect=["Model"],
-            label="Select columns to display:",
+            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
+            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
+            label="Select Columns to Display:",
         ),
-        # enable search across useful fields (primary first)
-        search_columns=["Model", "Type"],
-        # hide helper columns that are only for search/filtering
-        hide_columns=["model_name_for_query"],
-        # add quick filters; auto-picks widget types unless you specify
+        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
+        hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
         filter_columns=[
-            "Type",
-            ColumnFilter("Precision", type="dropdown"),
-            ColumnFilter("#Params (B)", type="slider", min=0, max=300),
+            ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
+            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
+            ColumnFilter(
+                AutoEvalColumn.params.name,
+                type="slider",
+                min=0.01,
+                max=150,
+                label="Select the number of parameters (B)",
+            ),
+            ColumnFilter(
+                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
+            ),
         ],
-        # optional: tell the component which columns are numbers/markdown/etc.
-        datatype=["str","number","number","number","number","number","number","number"]
+        bool_checkboxgroup_label="Hide models",
+        interactive=False,
+    )
+
+# -----------------------------
+# NEW: Load your local JSON and a simple leaderboard (no AutoEvalColumn coupling)
+# -----------------------------
+USER_JSON = Path(__file__).parent / "leaderboard_data.json"
+try:
+    USER_DF = pd.read_json(USER_JSON)
+except Exception as e:
+    # Create an empty DF with the expected columns if file missing, so Space still builds.
+    USER_DF = pd.DataFrame(columns=["Model", "Average", "Assistant Traits", "Relationship & Intimacy", "Emotional Investment", "User Vulnerabilities"])
+
+# Ensure types (Model=str, others=float) and clean column order
+if "Model" in USER_DF.columns:
+    USER_DF["Model"] = USER_DF["Model"].astype(str)
+for col in USER_DF.columns:
+    if col != "Model":
+        USER_DF[col] = pd.to_numeric(USER_DF[col], errors="coerce")
+
+def init_simple_leaderboard(df: pd.DataFrame):
+    # Show Model + up to first 6 metric columns by default
+    metrics = [c for c in df.columns if c != "Model"]
+    default_cols = ["Model"] + metrics[:6] if "Model" in df.columns else list(df.columns)[:7]
+    cant_hide = ["Model"] if "Model" in df.columns else []
+
+    return Leaderboard(
+        value=df,
+        select_columns=SelectColumns(
+            default_selection=default_cols if default_cols else list(df.columns),
+            cant_deselect=cant_hide,
+            label="Select Columns to Display:",
+        ),
+        search_columns=["Model"] if "Model" in df.columns else [],
+        hide_columns=[],   # keep everything visible
+        filter_columns=[], # no filters for now
+        interactive=False,
     )
 
-if __name__ == "__main__":
-    demo.launch()
+# -----------------------------
+# UI
+# -----------------------------
+demo = gr.Blocks(css=custom_css)
+with demo:
+    gr.HTML(TITLE)
+    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
+
+    with gr.Tabs(elem_classes="tab-buttons") as tabs:
+        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
+            leaderboard = init_leaderboard(LEADERBOARD_DF)
+
+        # NEW TAB: renders your leaderboard_data.json
+        with gr.TabItem("📊 INTIMA Leaderboard", elem_id="intima-leaderboard-tab", id=1):
+            _ = init_simple_leaderboard(USER_DF)
+
+        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
+            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
+
+        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
+            with gr.Column():
+                with gr.Row():
+                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
+
+                with gr.Column():
+                    with gr.Accordion(
+                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
+                        open=False,
+                    ):
+                        with gr.Row():
+                            finished_eval_table = gr.components.Dataframe(
+                                value=finished_eval_queue_df,
+                                headers=EVAL_COLS,
+                                datatype=EVAL_TYPES,
+                                row_count=5,
+                            )
+                    with gr.Accordion(
+                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
+                        open=False,
+                    ):
+                        with gr.Row():
+                            running_eval_table = gr.components.Dataframe(
+                                value=running_eval_queue_df,
+                                headers=EVAL_COLS,
+                                datatype=EVAL_TYPES,
+                                row_count=5,
+                            )
+
+                    with gr.Accordion(
+                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
+                        open=False,
+                    ):
+                        with gr.Row():
+                            pending_eval_table = gr.components.Dataframe(
+                                value=pending_eval_queue_df,
+                                headers=EVAL_COLS,
+                                datatype=EVAL_TYPES,
+                                row_count=5,
+                            )
+            with gr.Row():
+                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
+
+            with gr.Row():
+                with gr.Column():
+                    model_name_textbox = gr.Textbox(label="Model name")
+                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
+                    model_type = gr.Dropdown(
+                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
+                        label="Model type",
+                        multiselect=False,
+                        value=None,
+                        interactive=True,
+                    )
+
+                with gr.Column():
+                    precision = gr.Dropdown(
+                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
+                        label="Precision",
+                        multiselect=False,
+                        value="float16",
+                        interactive=True,
+                    )
+                    weight_type = gr.Dropdown(
+                        choices=[i.value.name for i in WeightType],
+                        label="Weights type",
+                        multiselect=False,
+                        value="Original",
+                        interactive=True,
+                    )
+                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
+
+            submit_button = gr.Button("Submit Eval")
+            submission_result = gr.Markdown()
+            submit_button.click(
+                add_new_eval,
+                [
+                    model_name_textbox,
+                    base_model_name_textbox,
+                    revision_name_textbox,
+                    precision,
+                    weight_type,
+                    model_type,
+                ],
+                submission_result,
+            )
+
+    with gr.Row():
+        with gr.Accordion("📙 Citation", open=False):
+            citation_button = gr.Textbox(
+                value=CITATION_BUTTON_TEXT,
+                label=CITATION_BUTTON_LABEL,
+                lines=20,
+                elem_id="citation-button",
+                show_copy_button=True,
+            )
+
+scheduler = BackgroundScheduler()
+scheduler.add_job(restart_space, "interval", seconds=1800)
+scheduler.start()
+demo.queue(default_concurrency_limit=40).launch()