Update app.py

app.py

@@ -1,67 +1,170 @@
 import gradio as gr
-import pandas as pd
+import json
 from typing import List, Dict
 
-from ingest.loader import ingest_documents
-from semantic import build_faiss_index, semantic_search
 from entity_graph import build_entity_graph
+from audit import log_event, export_audit_log
+from collaboration import add_collaboration_note, get_collaboration_dataset
 
-# ----------------------
-# CONFIG
-# ----------------------
-ENABLE_SCRAPING = False  # HF SAFE DEFAULT
-
-# ----------------------
-# BASE DATA
-# ----------------------
-DOCUMENTS = [
-    {"title": "MKULTRA Overview", "agency": "CIA", "date": "1977", "content": "MKULTRA program"},
-    {"title": "UAP Report", "agency": "DoD", "date": "2021", "content": "UAP assessment"}
+# ---------------------------------------------------------
+# DEMO DATA (PUBLIC, UNCLASSIFIED, PREVIOUSLY RELEASED)
+# ---------------------------------------------------------
+
+DOCUMENTS: List[Dict] = [
+    {
+        "title": "AATIP Summary Memorandum",
+        "agency": "DoD",
+        "date": "2019-05-01",
+        "content": "AATIP ADVANCED AEROSPACE THREAT IDENTIFICATION PROGRAM"
+    },
+    {
+        "title": "UAP Sensor Analysis",
+        "agency": "NRO",
+        "date": "2021-06-25",
+        "content": "UAP SENSOR SATELLITE ORBIT ANALYSIS"
+    }
 ]
 
-DOCUMENTS += ingest_documents(ENABLE_SCRAPING)
+# ---------------------------------------------------------
+# D3 GRAPH RENDERER (INLINE, CLIENT-SIDE ONLY)
+# ---------------------------------------------------------
+
+def render_d3_graph(graph_json: Dict) -> str:
+    return f"""
+<div id="graph"></div>
+<script src="https://d3js.org/d3.v7.min.js"></script>
+<script>
+const data = {json.dumps(graph_json)};
+
+const width = 650, height = 420;
+
+const svg = d3.select("#graph")
+  .append("svg")
+  .attr("width", width)
+  .attr("height", height);
+
+const simulation = d3.forceSimulation(data.nodes)
+  .force("link", d3.forceLink(data.links).id(d => d.id).distance(90))
+  .force("charge", d3.forceManyBody().strength(-250))
+  .force("center", d3.forceCenter(width / 2, height / 2));
+
+const link = svg.append("g")
+  .selectAll("line")
+  .data(data.links)
+  .enter().append("line")
+  .style("stroke", "#aaa");
+
+const node = svg.append("g")
+  .selectAll("circle")
+  .data(data.nodes)
+  .enter().append("circle")
+  .attr("r", 6)
+  .style("fill", d => d.group === "agency" ? "#ff7f0e" : "#1f77b4")
+  .call(d3.drag()
+    .on("start", dragstarted)
+    .on("drag", dragged)
+    .on("end", dragended));
+
+node.append("title").text(d => d.id);
+
+simulation.on("tick", () => {{
+  link
+    .attr("x1", d => d.source.x)
+    .attr("y1", d => d.source.y)
+    .attr("x2", d => d.target.x)
+    .attr("y2", d => d.target.y);
+
+  node
+    .attr("cx", d => d.x)
+    .attr("cy", d => d.y);
+}});
+
+function dragstarted(event, d) {{
+  if (!event.active) simulation.alphaTarget(0.3).restart();
+  d.fx = d.x;
+  d.fy = d.y;
+}}
 
-FAISS_INDEX, _ = build_faiss_index(DOCUMENTS)
+function dragged(event, d) {{
+  d.fx = event.x;
+  d.fy = event.y;
+}}
 
-# ----------------------
-# SEARCH
-# ----------------------
-def search(query, agencies):
-    results = []
+function dragended(event, d) {{
+  if (!event.active) simulation.alphaTarget(0);
+  d.fx = null;
+  d.fy = null;
+}}
+</script>
+"""
+
+# ---------------------------------------------------------
+# SEARCH LOGIC
+# ---------------------------------------------------------
+
+def run_search(query: str, agencies: List[str]):
+    log_event("search", {"query": query, "agencies": agencies})
+
+    rows = []
     for d in DOCUMENTS:
-        if agencies and d["agency"] not in agencies:
-            continue
         if query.lower() in d["content"].lower():
-            results.append(d)
-    return pd.DataFrame(results)
+            if not agencies or d["agency"] in agencies:
+                rows.append([d["title"], d["agency"], d["date"]])
+    return rows
 
-def semantic(query):
-    return pd.DataFrame(semantic_search(query, DOCUMENTS, FAISS_INDEX))
+# ---------------------------------------------------------
+# UI
+# ---------------------------------------------------------
 
-def entity_graph_json():
-    return build_entity_graph(DOCUMENTS)
+with gr.Blocks(title="FOIA Declassified Document Search") as app:
 
-# ----------------------
-# UI
-# ----------------------
-with gr.Blocks() as app:
-    gr.Markdown("# 🗂️ FOIA Declassified Document Search (Advanced)")
+    gr.Markdown("""
+# 🗂️ FOIA Declassified Document Search
+
+⚠️ **Demo Mode – Public FOIA samples only**
+
+This tool analyzes *mentions*, not facts.  
+No classified material. No live government systems.
+""")
+
+    with gr.Tab("🔍 Search"):
+        query = gr.Textbox(label="Search query")
+        agency_filter = gr.CheckboxGroup(
+            ["CIA", "DoD", "DIA", "FBI", "NRO", "NSA", "Unknown"],
+            label="Filter by agency"
+        )
+        output = gr.Dataframe(
+            headers=["Title", "Agency", "Date"],
+            interactive=False
+        )
+        gr.Button("Search").click(run_search, [query, agency_filter], output)
+
+    with gr.Tab("🧠 Entity Graph"):
+        graph = build_entity_graph(DOCUMENTS)
+        gr.HTML(render_d3_graph(graph))
+
+    with gr.Tab("🤝 Collaboration"):
+        doc = gr.Textbox(label="Document title")
+        note = gr.Textbox(label="Note")
+        collab_out = gr.Dataframe()
 
-    with gr.Row():
-        q = gr.Textbox(label="Search")
-        agency = gr.CheckboxGroup(["CIA", "DoD", "FBI", "NSA", "NRO", "USAF"], label="Agency")
+        def add_note_ui(d, n):
+            log_event("collaboration_note", {"document": d})
+            add_collaboration_note(d, n)
+            return get_collaboration_dataset().to_pandas()
 
-    gr.Button("Keyword Search").click(search, [q, agency], gr.Dataframe())
-    gr.Button("Semantic Search").click(semantic, q, gr.Dataframe())
+        gr.Button("Add note").click(add_note_ui, [doc, note], collab_out)
 
-    gr.Markdown("### Entity Graph (JSON)")
-    gr.JSON(entity_graph_json)
+    with gr.Tab("🧾 Audit Log"):
+        gr.JSON(export_audit_log)
 
     gr.Markdown("""
-    ### Dataset Provenance
-    - Public FOIA releases only
-    - Demo + optional ingestion
-    - No intelligence claims
-    """)
+### Dataset Provenance
+- Sources: Public FOIA releases (FBI Vault, CIA Reading Room, DoD FOIA)
+- Status: Previously released, unclassified
+- Scope: Demo subset only
+- Curation: Manual sampling for demonstration
+- Verification: No claims beyond document text
+""")
 
 app.launch()