Create ingest/cluster.py

ingest/cluster.py

@@ -1,20 +1,29 @@
 from sentence_transformers import SentenceTransformer
-import faiss
-import numpy as np
+import faiss, numpy as np
+import plotly.graph_objects as go
 
 model = SentenceTransformer("all-MiniLM-L6-v2")
 
-def semantic_cluster(results):
+def semantic_cluster_plot(results):
     texts = [r["title"] + " " + r["snippet"] for r in results]
     if not texts:
-        return None
+        return go.Figure()
 
     embeddings = model.encode(texts)
     dim = embeddings.shape[1]
     index = faiss.IndexFlatL2(dim)
     index.add(np.array(embeddings))
 
-    return {
-        "points": embeddings.tolist(),
-        "labels": list(range(len(results)))
-    }
+    # simple 2D projection (first 2 dims for HF safety)
+    x, y = embeddings[:,0], embeddings[:,1]
+
+    fig = go.Figure(
+        data=go.Scatter(
+            x=x, y=y,
+            mode="markers",
+            text=[r["title"] for r in results],
+            marker=dict(size=8)
+        )
+    )
+    fig.update_layout(title="Semantic Document Clusters")
+    return fig