minor fixes to notebooks

Signed-off-by: Fotis Nikolaidis <[email protected]>
superduper-io · Dec 3, 2023 · 1f9af17 · 1f9af17
1 parent 6fd8f74
commit 1f9af17
Show file tree

Hide file tree

Showing 5 changed files with 106 additions and 64 deletions.
diff --git a/Makefile b/Makefile
@@ -162,7 +162,7 @@ test_notebooks: ## Test notebooks (argument: NOTEBOOKS=<test|dir>)
 	@echo "Notebook Path: $(NOTEBOOKS)"
 
 	@if [ -n "${NOTEBOOKS}" ]; then	\
-		pytest --nbval ${NOTEBOOKS}; 	\
+		pytest --nbval-lax ${NOTEBOOKS}; 	\
 	fi
 
 

diff --git a/examples/multimodal_image_search_clip.ipynb b/examples/multimodal_image_search_clip.ipynb
@@ -24,10 +24,7 @@
    "cell_type": "markdown",
    "id": "40272d6a2681c8e8",
    "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
+    "collapsed": false
    },
    "source": [
     "## Prerequisites\n",
@@ -104,7 +101,7 @@
    "outputs": [],
    "source": [
     "!curl -O https://superduperdb-public.s3.eu-west-1.amazonaws.com/coco_sample.zip\n",
-    "!unzip coco_sample.zip"
+    "!unzip -f coco_sample.zip"
    ]
   },
   {
@@ -117,7 +114,6 @@
     "from superduperdb import Document\n",
     "from superduperdb.ext.pillow import pil_image as i\n",
     "import glob\n",
-    "import random\n",
     "\n",
     "# Use glob to get a list of image file paths in the 'images_small' directory\n",
     "images = glob.glob('images_tiny/*.jpg')\n",

diff --git a/examples/question_the_docs.ipynb b/examples/question_the_docs.ipynb
diff --git a/examples/sandbox-example.ipynb b/examples/sandbox-example.ipynb
@@ -85,10 +85,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "5355a5ac-6452-4a89-b0d9-fe18cb993fdd",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-12-03T00:13:57.783125835Z",
+     "start_time": "2023-12-03T00:13:56.700300107Z"
+    }
+   },
+   "outputs": [
+    {
+     "ename": "AssertionError",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mAssertionError\u001B[0m                            Traceback (most recent call last)",
+      "Cell \u001B[0;32mIn[1], line 9\u001B[0m\n\u001B[1;32m      6\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01msuperduperdb\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m CFG\n\u001B[1;32m      8\u001B[0m \u001B[38;5;66;03m# check that config has been properly set-up\u001B[39;00m\n\u001B[0;32m----> 9\u001B[0m \u001B[38;5;28;01massert\u001B[39;00m CFG\u001B[38;5;241m.\u001B[39mdata_backend \u001B[38;5;241m==\u001B[39m \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mmongodb://superduper:superduper@mongodb:27017/test_db\u001B[39m\u001B[38;5;124m'\u001B[39m\n",
+      "\u001B[0;31mAssertionError\u001B[0m: "
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "\n",
@@ -113,7 +130,12 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ed9bfd66-6771-476e-ae44-360c05aa69ed",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-12-03T00:13:57.784130263Z",
+     "start_time": "2023-12-03T00:13:57.783877029Z"
+    }
+   },
    "outputs": [],
    "source": [
     "from superduperdb.backends.mongodb import Collection\n",
@@ -136,7 +158,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "bae34017-6259-42df-beae-1191ea0f6374",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.784872242Z"
+    }
+   },
    "outputs": [],
    "source": [
     "!curl -O https://superduperdb-public.s3.eu-west-1.amazonaws.com/pymongo.json\n",
@@ -161,7 +187,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "726143ee-61f1-4353-806b-a9c9384b569d",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.785785759Z"
+    }
+   },
    "outputs": [],
    "source": [
     "from superduperdb import Document\n",
@@ -184,7 +214,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "e6847b06-cf2e-4134-89df-9651f7fc8604",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.786751582Z"
+    }
+   },
    "outputs": [],
    "source": [
     "import sentence_transformers\n",
@@ -212,7 +246,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "fdcbcc3f-f817-49dc-912c-aeb7c0f1916d",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.787530354Z"
+    }
+   },
    "outputs": [],
    "source": [
     "from superduperdb import Listener, VectorIndex\n",
@@ -243,7 +281,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "fbd3d575-709f-4b8a-bdda-dad21799a65b",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.788284643Z"
+    }
+   },
    "outputs": [],
    "source": [
     "jobs[0].watch()"
@@ -261,7 +303,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "98ec7560-99d9-401b-971c-e87bcde48e78",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.789613615Z"
+    }
+   },
    "outputs": [],
    "source": [
     "db.execute(doc_collection.find_one())"
@@ -282,7 +328,10 @@
    "execution_count": null,
    "id": "d4b96bdb-2b99-4a09-82a0-ad9f337d2d41",
    "metadata": {
-    "scrolled": true
+    "scrolled": true,
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.789633296Z"
+    }
    },
    "outputs": [],
    "source": [
@@ -326,7 +375,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "5bc61e63-abd9-4556-90a4-cdcbf5b10978",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.830389175Z"
+    }
+   },
    "outputs": [],
    "source": [
     "import pymongo\n",
@@ -366,7 +419,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "b2df24bb-b394-4c14-99bf-c1dde1a486c0",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.830461965Z"
+    }
+   },
    "outputs": [],
    "source": [
     "db.metadata.show_jobs()"
@@ -385,7 +442,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "2dd970cd-f01e-4105-85d6-1f39682c1e02",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2023-12-03T00:13:57.830491870Z"
+    }
+   },
    "outputs": [],
    "source": [
     "db.execute(doc_collection.count_documents({'_outputs': {'$exists': 1}}))"

diff --git a/examples/sql-example.ipynb b/examples/sql-example.ipynb
@@ -118,7 +118,7 @@
     "!curl -O https://superduperdb-public.s3.eu-west-1.amazonaws.com/captions_tiny.json\n",
     "\n",
     "# Unzip the contents of coco_sample.zip\n",
-    "!unzip coco_sample.zip\n",
+    "!unzip -f coco_sample.zip\n",
     "\n",
     "# Create a directory named 'data/coco'\n",
     "!mkdir -p data/coco\n",