Add ColQwen2 notebook example

vespa-engine · Oct 1, 2024 · 0d17124 · 0d17124
1 parent 22be413
commit 0d17124
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 19 deletions.
diff --git a/docs/sphinx/source/examples/colpali-document-retrieval-vision-language-models-cloud.ipynb b/docs/sphinx/source/examples/colpali-document-retrieval-vision-language-models-cloud.ipynb
@@ -50,6 +50,9 @@
                 "\n",
                 "For a simpler example where we use one vespa document = One PDF page, see [simplified-retrieval-with-colpali](https://pyvespa.readthedocs.io/en/latest/examples/simplified-retrieval-with-colpali-vlm_Vespa-cloud.html).\n",
                 "\n",
+                "Consider following the [ColQWen2](https://pyvespa.readthedocs.io/en/latest/examples/pdf-retrieval-with-ColQwen2-vlm_Vespa-cloud.html) notebook instead as it\n",
+                "use a better model with improved performance (Both accuracy and speed).\n",
+                "\n",
                 "We also store the base64 encoded image, and page meta data like title and url so that we can display it in the result page, but also\n",
                 "use it for RAG with powerful LLMs with vision capabilities. \n",
                 "\n",

diff --git a/docs/sphinx/source/examples/pdf-retrieval-with-ColQwen2-vlm_Vespa-cloud.ipynb b/docs/sphinx/source/examples/pdf-retrieval-with-ColQwen2-vlm_Vespa-cloud.ipynb
@@ -796,32 +796,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Setting application...\n",
-      "Running: vespa config set application samples.visionrag5\n",
-      "Setting target cloud...\n",
-      "Running: vespa config set target cloud\n",
-      "\n",
-      "No api-key found for control plane access. Using access token.\n",
-      "Checking for access token in auth.json...\n",
-      "Successfully obtained access token for control plane access.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from vespa.deployment import VespaCloud\n",
     "import os\n",
     "\n",
     "os.environ['TOKENIZERS_PARALLELISM'] = \"false\"\n",
     "\n",
     "# Replace with your tenant name from the Vespa Cloud Console\n",
-    "tenant_name = \"samples\" \n",
+    "tenant_name = \"vespa-team\" \n",
     "\n",
     "key = os.getenv(\"VESPA_TEAM_API_KEY\", None)\n",
     "if key is not None:\n",

diff --git a/docs/sphinx/source/examples/simplified-retrieval-with-colpali-vlm_Vespa-cloud.ipynb b/docs/sphinx/source/examples/simplified-retrieval-with-colpali-vlm_Vespa-cloud.ipynb
@@ -17,6 +17,9 @@
     "This notebook demonstrates how to represent [ColPali](https://huggingface.co/vidore/colpali) in Vespa\n",
     "and to scale to large collections. Also see the blog post: [Scaling ColPali to billions of PDFs with Vespa](https://blog.vespa.ai/scaling-colpali-to-billions/)\n",
     "\n",
+    "Consider following the [ColQWen2](https://pyvespa.readthedocs.io/en/latest/examples/pdf-retrieval-with-ColQwen2-vlm_Vespa-cloud.html) notebook instead as it\n",
+    "use a better model with improved performance (Both accuracy and speed).\n",
+    "\n",
     "ColPali is a powerful visual language model that can generate embeddings for images (screenshots of PDF pages) and text queries.\n",
     "\n",
     "In this notebook, we will use ColPali to generate embeddings for images of PDF _pages_ and store the embeddings in Vespa. \n",
@@ -1276,7 +1279,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.10"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {