update references to end to end examples, use s3 for langchain exampl… (#133)

docs/src/notebooks/code_qa_bot.ipynb

@@ -72,6 +72,8 @@
     "import lancedb\n",
     "import re\n",
     "import pickle\n",
+    "import requests\n",
+    "import zipfile\n",
     "from pathlib import Path\n",
     "\n",
     "from langchain.document_loaders import UnstructuredHTMLLoader\n",
@@ -85,10 +87,25 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "6ccf9b2b",
+   "id": "56cc6d50",
    "metadata": {},
    "source": [
-    "You can download the Pandas documentation from https://pandas.pydata.org/docs/. To make sure we're not littering our repo with docs, we won't include it in the LanceDB repo, so download this and store it locally first."
+    "To make this easier, we've downloaded Pandas documentation and stored the raw HTML files for you to download. We'll download them and then use LangChain's HTML document readers to parse them and store them in LanceDB as a vector store, along with relevant metadata."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7da77e75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pandas_docs = requests.get(\"https://eto-public.s3.us-west-2.amazonaws.com/datasets/pandas_docs/pandas.documentation.zip\")\n",
+    "with open('/tmp/pandas.documentation.zip', 'wb') as f:\n",
+    "    f.write(pandas_docs.content)\n",
+    "\n",
+    "file = zipfile.ZipFile(\"/tmp/pandas.documentation.zip\")\n",
+    "file.extractall(path=\"/tmp/pandas_docs\")"
    ]
   },
   {
@@ -137,7 +154,8 @@
     "docs = []\n",
     "\n",
     "if not docs_path.exists():\n",
-    "    for p in Path(\"./pandas.documentation\").rglob(\"*.html\"):\n",
+    "    for p in Path(\"/tmp/pandas_docs/pandas.documentation\").rglob(\"*.html\"):\n",
+    "        print(p)\n",
     "        if p.is_dir():\n",
     "            continue\n",
     "        loader = UnstructuredHTMLLoader(p)\n",