Reduce complexity for cd test for now (#662)

docs/sphinx/source/examples/arxiv-search-streaming-dataset-cloud.ipynb

@@ -18,7 +18,9 @@
     "and feed it to a Vespa instance. The dataset comprises of English language arXiv papers from the Cornell/arXiv dataset, with two new columns added: title-embeddings and abstract-embeddings. Embeddings generated using the [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embeddings model. \n",
     "\n",
     "In this notebook, we use Vespa's embedder functionality to include the  [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embedding\n",
-    "model into Vespa for query serving. "
+    "model into Vespa for query serving. \n",
+    "\n",
+    "This is work in progress - we want to demonstrate more query examples. "
    ]
   },
   {
@@ -432,7 +434,7 @@
     "# app:Vespa = vespa_cloud.deploy()\n",
     "\n",
     "from datasets import load_dataset\n",
-    "dataset = load_dataset(\"somewheresystems/dataclysm-arxiv\", split=\"train\", streaming=True)\n",
+    "dataset = load_dataset(\"somewheresystems/dataclysm-arxiv\", split=\"train\", streaming=True).take(100)\n",
     "vespa_feed = dataset.map(lambda x: \n",
     "{\n",
     "    \"id\": x[\"id\"],\n",
@@ -454,8 +456,10 @@
     "def callback(response:VespaResponse, id:str):\n",
     "    if not response.is_successful():\n",
     "        print(f\"Document {id} failed to feed with status code {response.status_code}, url={response.url} response={response.json}\")\n",
+    "    else:\n",
+    "        print(f\"Document {id} success.\")\n",
     "\n",
-    "app.feed_iterable(schema=\"paper\", iter=vespa_feed, callback=callback, max_connections=12, max_workers=64, max_queue_size=10000)\n"
+    "app.feed_iterable(schema=\"paper\", iter=vespa_feed, callback=callback, max_connections=12, max_workers=14, max_queue_size=10000)\n"
    ]
   },
   {