Initial implementation of pgvector and Oracle 26ai vector search demo

Three FastAPI backends comparing PostgreSQL/pgvector and Oracle 26ai for
semantic image search using CLIP embeddings: Python-side embedding for both
databases, plus Oracle in-database embedding via VECTOR_EMBEDDING(CLIP_TXT).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

oravector-demo/backend/index_images_oracle.py

@@ -0,0 +1,66 @@
+import os
+import array
+from dotenv import load_dotenv
+from db_oracle import get_connection
+from embedder import embed_image
+
+load_dotenv()
+
+PHOTOS_DIR = os.getenv("PHOTOS_DIR")
+
+CREATE_TABLE = """
+CREATE TABLE images (
+    id        NUMBER GENERATED ALWAYS AS IDENTITY PRIMARY KEY,
+    filename  VARCHAR2(255) NOT NULL UNIQUE,
+    filepath  VARCHAR2(1000) NOT NULL,
+    embedding VECTOR(512, FLOAT32)
+)
+"""
+
+CREATE_INDEX = """
+CREATE VECTOR INDEX images_embedding_idx
+    ON images(embedding)
+    ORGANIZATION INMEMORY NEIGHBOR GRAPH
+    WITH DISTANCE COSINE
+    WITH TARGET ACCURACY 95
+    PARAMETERS (type HNSW, neighbors 32, efconstruction 200)
+"""
+
+INSERT = "INSERT INTO images (filename, filepath, embedding) VALUES (:1, :2, :3)"
+
+def table_exists(cur):
+    cur.execute("SELECT COUNT(*) FROM user_tables WHERE table_name = 'IMAGES'")
+    return cur.fetchone()[0] > 0
+
+def main():
+    conn = get_connection()
+    cur = conn.cursor()
+
+    if not table_exists(cur):
+        cur.execute(CREATE_TABLE)
+        cur.execute(CREATE_INDEX)
+        conn.commit()
+        print("Table and index created.")
+    else:
+        print("Table already exists, skipping creation.")
+
+    files = [f for f in os.listdir(PHOTOS_DIR) if f.lower().endswith((".jpg", ".jpeg"))]
+    print(f"Found {len(files)} photos in {PHOTOS_DIR}")
+
+    for i, filename in enumerate(files, 1):
+        filepath = os.path.join(PHOTOS_DIR, filename)
+        cur.execute("SELECT 1 FROM images WHERE filename = :1", (filename,))
+        if cur.fetchone():
+            print(f"[{i}/{len(files)}] Skipping {filename} (already indexed)")
+            continue
+        embedding = array.array("f", embed_image(filepath))
+        cur.execute(INSERT, (filename, filepath, embedding))
+        conn.commit()
+        print(f"[{i}/{len(files)}] Indexed {filename}")
+
+    cur.close()
+    conn.close()
+    print("Done.")
+
+if __name__ == "__main__":
+    main()