From b8d0403671e4ee9d40a21209387cd87d69e9f802 Mon Sep 17 00:00:00 2001
From: Simonas Jakubonis <20096648+simjak@users.noreply.github.com>
Date: Sat, 3 May 2025 23:02:21 +0300
Subject: [PATCH] docs: updated pinecone example notebook (#30993)

- **Description:** Update Pinecone notebook example
  - **Issue:** N\A
  - **Dependencies:** N\A
  - **Twitter handle:** N\A


- [ x ] **Add tests and docs**: Just notebook updates


If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
---
 .../integrations/vectorstores/pinecone.ipynb  | 111 ++++--------------
 1 file changed, 22 insertions(+), 89 deletions(-)

diff --git a/docs/docs/integrations/vectorstores/pinecone.ipynb b/docs/docs/integrations/vectorstores/pinecone.ipynb
index fb511e574ea..da997c3b19e 100644
--- a/docs/docs/integrations/vectorstores/pinecone.ipynb
+++ b/docs/docs/integrations/vectorstores/pinecone.ipynb
@@ -26,7 +26,7 @@
    },
    "outputs": [],
    "source": [
-    "pip install -qU langchain-pinecone pinecone-notebooks"
+    "pip install -qU langchain langchain-pinecone langchain-openai"
    ]
   },
   {
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "eb554814",
    "metadata": {},
    "outputs": [],
@@ -57,7 +57,7 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "from pinecone import Pinecone, ServerlessSpec\n",
+    "from pinecone import Pinecone\n",
     "\n",
     "if not os.getenv(\"PINECONE_API_KEY\"):\n",
     "    os.environ[\"PINECONE_API_KEY\"] = getpass.getpass(\"Enter your Pinecone API key: \")\n",
@@ -98,59 +98,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 4,
    "id": "276a06dd",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import time\n",
+    "from pinecone import ServerlessSpec\n",
     "\n",
     "index_name = \"langchain-test-index\"  # change if desired\n",
     "\n",
-    "existing_indexes = [index_info[\"name\"] for index_info in pc.list_indexes()]\n",
-    "\n",
-    "if index_name not in existing_indexes:\n",
+    "if not pc.has_index(index_name):\n",
     "    pc.create_index(\n",
     "        name=index_name,\n",
-    "        dimension=3072,\n",
+    "        dimension=1536,\n",
     "        metric=\"cosine\",\n",
     "        spec=ServerlessSpec(cloud=\"aws\", region=\"us-east-1\"),\n",
     "    )\n",
-    "    while not pc.describe_index(index_name).status[\"ready\"]:\n",
-    "        time.sleep(1)\n",
     "\n",
     "index = pc.Index(index_name)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a4d377f",
-   "metadata": {},
-   "source": [
-    "Now that our Pinecone index is setup, we can initialize our vector store. \n",
-    "\n",
-    "import EmbeddingTabs from \"@theme/EmbeddingTabs\";\n",
-    "\n",
-    "<EmbeddingTabs/>\n"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 5,
    "id": "1485db56",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
-    "embeddings = OpenAIEmbeddings(model=\"text-embedding-3-large\")"
+    "embeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 6,
    "id": "6e104aee",
    "metadata": {},
    "outputs": [],
@@ -176,30 +158,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "70e688f4",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['167b8681-5974-467f-adcb-6e987a18df01',\n",
-       " 'd16010fd-41f8-4d49-9c22-c66d5555a3fe',\n",
-       " 'ffcacfb3-2bc2-44c3-a039-c2256a905c0e',\n",
-       " 'cf3bfc9f-5dc7-4f5e-bb41-edb957394126',\n",
-       " 'e99b07eb-fdff-4cb9-baa8-619fd8efeed3',\n",
-       " '68c93033-a24f-40bd-8492-92fa26b631a4',\n",
-       " 'b27a4ecb-b505-4c5d-89ff-526e3d103558',\n",
-       " '4868a9e6-e6fb-4079-b400-4a1dfbf0d4c4',\n",
-       " '921c0e9c-0550-4eb5-9a6c-ed44410788b2',\n",
-       " 'c446fc23-64e8-47e7-8c19-ecf985e9411e']"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from uuid import uuid4\n",
     "\n",
@@ -268,7 +230,6 @@
     "    document_10,\n",
     "]\n",
     "uuids = [str(uuid4()) for _ in range(len(documents))]\n",
-    "\n",
     "vector_store.add_documents(documents=documents, ids=uuids)"
    ]
   },
@@ -282,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 8,
    "id": "5b8437cd",
    "metadata": {},
    "outputs": [],
@@ -306,19 +267,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 9,
    "id": "ffbcb3fb",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]\n",
-      "* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "results = vector_store.similarity_search(\n",
     "    \"LangChain provides abstractions to make working with LLMs easy\",\n",
@@ -341,18 +293,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "id": "5fb24583",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "* [SIM=0.553187] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "results = vector_store.similarity_search_with_score(\n",
     "    \"Will it be hot tomorrow?\", k=1, filter={\"source\": \"news\"}\n",
@@ -377,25 +321,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "id": "78140e87",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(metadata={'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "retriever = vector_store.as_retriever(\n",
     "    search_type=\"similarity_score_threshold\",\n",
-    "    search_kwargs={\"k\": 1, \"score_threshold\": 0.5},\n",
+    "    search_kwargs={\"k\": 1, \"score_threshold\": 0.4},\n",
     ")\n",
     "retriever.invoke(\"Stealing from the bank is a crime\", filter={\"source\": \"news\"})"
    ]
@@ -427,7 +360,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -441,7 +374,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.15"
   }
  },
  "nbformat": 4,