Spaces:
Running
Running
| import gradio as gr | |
| import pandas as pd | |
| DATA_URL = "https://huggingface.co/datasets/aeriesec/orgforge/resolve/main/leaderboard/leaderboard.csv" | |
| # Define column groups to keep things organized | |
| CORE_COLS = ["retriever", "generator", "answer_score", "mrr_at_10", "recall_at_10", "accuracy"] | |
| # Mapping of friendly names to the technical column pairs | |
| DETAIL_MAP = { | |
| "Causal": ["mrr_CAUSAL", "score_CAUSAL"], | |
| "Escalation": ["mrr_ESCALATION", "score_ESCALATION"], | |
| "Gap Detection": ["mrr_GAP_DETECTION", "score_GAP_DETECTION"], | |
| "Planning": ["mrr_PLAN", "score_PLAN"], | |
| "Retrieval Detail": ["mrr_RETRIEVAL", "score_RETRIEVAL"], | |
| "Routing": ["mrr_ROUTING", "score_ROUTING"], | |
| "Temporal": ["mrr_TEMPORAL", "score_TEMPORAL"] | |
| } | |
| def load_and_filter(search_query, selected_details, tier_type): | |
| try: | |
| df = pd.read_csv(DATA_URL) | |
| df = df[df["tier"] == tier_type] | |
| # 1. Search Filter | |
| if search_query: | |
| df = df[df["generator"].str.contains(search_query, case=False) | | |
| df["retriever"].str.contains(search_query, case=False)] | |
| # 2. Column Selection | |
| cols_to_show = CORE_COLS.copy() | |
| for detail in selected_details: | |
| cols_to_show.extend(DETAIL_MAP[detail]) | |
| # 3. Final Formatting | |
| display_df = df[cols_to_show].sort_values(by="answer_score", ascending=False) | |
| return display_df.round(3) | |
| except Exception as e: | |
| return pd.DataFrame({"Error": [str(e)]}) | |
| with gr.Blocks(title="OrgForge RAG Leaderboard") as demo: | |
| gr.Markdown("# 🏆 OrgForge Enterprise RAG Benchmark") | |
| with gr.Row(): | |
| search_bar = gr.Textbox( | |
| placeholder="Search models (e.g., 'Claude', 'Llama')...", | |
| label="Filter by Model Name", | |
| scale=2 | |
| ) | |
| column_filter = gr.CheckboxGroup( | |
| choices=list(DETAIL_MAP.keys()), | |
| label="Show Detailed Category Scores", | |
| scale=3 | |
| ) | |
| with gr.Tabs(): | |
| with gr.Tab("🎯 Tier 1+2 (Full RAG)"): | |
| out_t2 = gr.Dataframe( | |
| value=load_and_filter("", [], "1+2"), | |
| interactive=False, | |
| max_height=600 | |
| ) | |
| with gr.Tab("🔍 Tier 1 (Retrieval Only)"): | |
| out_t1 = gr.Dataframe( | |
| value=load_and_filter("", [], "1"), | |
| interactive=False, | |
| max_height=600 | |
| ) | |
| def refresh(search, cols): | |
| return load_and_filter(search, cols, "1+2"), load_and_filter(search, cols, "1") | |
| inputs = [search_bar, column_filter] | |
| search_bar.change(fn=refresh, inputs=inputs, outputs=[out_t2, out_t1]) | |
| column_filter.change(fn=refresh, inputs=inputs, outputs=[out_t2, out_t1]) | |
| demo.launch() |