Update app.py

app.py

@@ -1,20 +1,22 @@
 """
 Federal FOIA Intelligence Search
 Public Electronic Reading Rooms Only
-HF Spaces compatible
 """
 
 import asyncio
-import time
 import gradio as gr
-from typing import List, Dict
+import plotly.graph_objects as go
+from datetime import datetime
 
 from ingest.registry import get_enabled_adapters
-from ingest.health import get_health_snapshot
 from ingest.cluster import build_embeddings, cluster_embeddings
-from ingest.export import export_journalist_zip
-from ingest.utils import highlight_terms, classify_foia_exemptions, format_citation
+from ingest.health import get_health_snapshot
 from ingest.coverage import build_coverage_heatmap
+from ingest.export import export_journalist_zip, export_pdf_report
+from ingest.utils import highlight_terms, classify_foia_exemptions, format_citation
+from ingest.timeline import build_timeline_figure
+from ingest.graph import build_cluster_graph
+
 
 TITLE = "🏛️ Federal FOIA Intelligence Search"
 SUBTITLE = "Public Electronic Reading Rooms Only"
@@ -27,35 +29,47 @@ async def _run_search(query: str, enable_live: bool, hide_stub: bool):
     tasks = [a.search(query) for a in adapters]
     responses = await asyncio.gather(*tasks, return_exceptions=True)
 
-    results: List[Dict] = []
-    per_agency_counts: Dict[str, int] = {}
+    results = []
+    per_agency_counts = {}
 
     for adapter, resp in zip(adapters, responses):
         if isinstance(resp, Exception):
             continue
         if hide_stub and adapter.is_stub:
             continue
+
         per_agency_counts[adapter.source_name] = len(resp)
+
         for r in resp:
             r["source"] = adapter.source_name
             r["latency"] = adapter.last_latency
             r["exemptions"] = classify_foia_exemptions(r.get("snippet", ""))
             r["citation"] = format_citation(r)
+            r["date"] = r.get("date", datetime.utcnow().isoformat())
             results.append(r)
 
-    # Embeddings + clustering
     embeddings = build_embeddings(results)
     clusters = cluster_embeddings(results, embeddings)
 
     coverage = build_coverage_heatmap(per_agency_counts)
+    cluster_graph = build_cluster_graph(results, clusters)
+    timeline_fig = build_timeline_figure(results)
 
-    return results, clusters, per_agency_counts, coverage
+    return results, clusters, per_agency_counts, coverage, cluster_graph, timeline_fig
 
 
 def search_ui(query, enable_live, hide_stub):
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
-    results, clusters, counts, coverage = loop.run_until_complete(
+
+    (
+        results,
+        clusters,
+        counts,
+        coverage,
+        cluster_graph,
+        timeline_fig
+    ) = loop.run_until_complete(
         _run_search(query, enable_live, hide_stub)
     )
 
@@ -70,7 +84,7 @@ def search_ui(query, enable_live, hide_stub):
             f"{r.get('latency', 0):.2f}s"
         ])
 
-    return table, clusters, counts, coverage
+    return table, counts, coverage, cluster_graph, timeline_fig
 
 
 # ---------------- UI ----------------
@@ -80,8 +94,8 @@ with gr.Blocks(title="Federal FOIA Intelligence Search") as demo:
     gr.Markdown(f"### {SUBTITLE}")
 
     gr.Markdown(
-        "**Terms of Use:** This application indexes only documents already released "
-        "to the public via official FOIA Electronic Reading Rooms."
+        "**Terms of Use:** Indexes only documents already released "
+        "via official FOIA Electronic Reading Rooms."
     )
 
     with gr.Row():
@@ -94,32 +108,50 @@ with gr.Blocks(title="Federal FOIA Intelligence Search") as demo:
 
     results_table = gr.Dataframe(
         headers=["Agency", "Title", "URL", "Snippet", "FOIA Exemptions", "Latency"],
-        interactive=False,
         wrap=True
     )
 
-    clusters_box = gr.JSON(label="Semantic Clusters (Interactive Graph Data)")
-    counts_box = gr.JSON(label="Per-Agency Result Counts")
-    coverage_box = gr.JSON(label="Coverage Heatmap Data")
+    with gr.Tabs():
+        with gr.Tab("📊 Coverage Heatmap"):
+            coverage_box = gr.JSON()
 
-    health_box = gr.JSON(
-        value=get_health_snapshot(),
-        label="Agency Health / Latency"
-    )
+        with gr.Tab("🧠 Semantic Cluster Graph"):
+            cluster_plot = gr.Plot()
+
+        with gr.Tab("🗓️ Timeline View"):
+            timeline_plot = gr.Plot()
+
+        with gr.Tab("🏥 Agency Health"):
+            health_box = gr.JSON(value=get_health_snapshot())
+
+    with gr.Row():
+        export_zip_btn = gr.Button("🧾 Journalist ZIP Export")
+        export_pdf_btn = gr.Button("📄 PDF Transparency Report")
 
-    export_btn = gr.Button("Export → Journalist ZIP")
     export_status = gr.Textbox(label="Export Status")
 
     search_btn.click(
         fn=search_ui,
         inputs=[query, enable_live, hide_stub],
-        outputs=[results_table, clusters_box, counts_box, coverage_box]
+        outputs=[
+            results_table,
+            coverage_box,
+            coverage_box,
+            cluster_plot,
+            timeline_plot
+        ]
     )
 
-    export_btn.click(
+    export_zip_btn.click(
         fn=export_journalist_zip,
         inputs=[results_table],
         outputs=[export_status]
     )
 
+    export_pdf_btn.click(
+        fn=export_pdf_report,
+        inputs=[results_table],
+        outputs=[export_status]
+    )
+
 demo.queue().launch()