Create app.py

app.py

@@ -0,0 +1,42 @@
+import chromadb
+from sentence_transformers import SentenceTransformer
+import gradio as gr
+
+# Load embedding model
+EMBED_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
+model = SentenceTransformer(EMBED_MODEL)
+
+# Load existing ChromaDB
+client = chromadb.Client(persist_directory=".chromadb")
+collection_name = "semantic_docs"
+collection = client.get_collection(collection_name)
+
+# Semantic search function
+def semantic_search(query, top_k=3):
+    q_emb = model.encode([query], convert_to_numpy=True)[0].tolist()
+    results = collection.query(
+        query_embeddings=[q_emb],
+        n_results=top_k,
+        include=["documents", "metadatas", "distances"]
+    )
+    docs = results.get("documents", [[]])[0]
+    metas = results.get("metadatas", [[]])[0]
+    dists = results.get("distances", [[]])[0]
+    out = []
+    for doc, meta, dist in zip(docs, metas, dists):
+        out.append(f"#{meta['chunk_id']} (dist={dist:.4f})\nSource: {meta['source']}\n{doc}\n")
+    return "\n\n".join(out)
+
+# Gradio UI
+def gr_search(query, top_k=3):
+    return semantic_search(query, top_k=top_k)
+
+demo = gr.Interface(
+    fn=gr_search,
+    inputs=[gr.Textbox(lines=1, placeholder="Enter query here"), gr.Slider(1, 10, value=3, label="Top K")],
+    outputs=gr.Textbox(label="Top Matches"),
+    title="Semantic Search Demo"
+)
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)