Additional resources and tips

week5/day4.5.ipynb

@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "ba2779af-84ef-4227-9e9e-6eaf0df87e77",
    "metadata": {},
    "outputs": [],
@@ -29,7 +29,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "802137aa-8a74-45e0-a487-d1974927d7ca",
    "metadata": {},
    "outputs": [],
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "58c85082-e417-4708-9efe-81a5d55d1424",
    "metadata": {},
    "outputs": [],
@@ -64,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "ee78efcb-60fe-449e-a944-40bab26261af",
    "metadata": {},
    "outputs": [],
@@ -77,7 +77,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "730711a9-6ffe-4eee-8f48-d6cfb7314905",
    "metadata": {},
    "outputs": [],
@@ -104,18 +104,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "7310c9c8-03c1-4efc-a104-5e89aec6db1a",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Created a chunk of size 1088, which is longer than the specified 1000\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
     "chunks = text_splitter.split_documents(documents)"
@@ -123,39 +115,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "cd06e02f-6d9b-44cc-a43d-e1faa8acc7bb",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "123"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "len(chunks)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "2c54b4b6-06da-463d-bee7-4dd456c2b887",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Document types found: company, employees, contracts, products\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "doc_types = set(chunk.metadata['doc_type'] for chunk in chunks)\n",
     "print(f\"Document types found: {', '.join(doc_types)}\")"
@@ -184,18 +157,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "There are 123 vectors with 1,536 dimensions in the vector store\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
     "# Chroma is a popular open source Vector Database based on SQLLite\n",