pinecone[patch], docs: PineconeVectorStore, release 0.0.3 (#17896)

docs/docs/integrations/providers/pinecone.mdx

@@ -18,7 +18,7 @@ There exists a wrapper around Pinecone indexes, allowing you to use it as a vect
 whether for semantic search or example selection.
 
 ```python
-from langchain_community.vectorstores import Pinecone
+from langchain_pinecone import PineconeVectorStore
 ```
 
 For a more detailed walkthrough of the Pinecone vectorstore, see [this notebook](/docs/integrations/vectorstores/pinecone)

docs/docs/integrations/retrievers/pinecone_hybrid_search.ipynb

@@ -119,13 +119,8 @@
     "import pinecone\n",
     "\n",
     "api_key = os.getenv(\"PINECONE_API_KEY\") or \"PINECONE_API_KEY\"\n",
-    "# find environment next to your API key in the Pinecone console\n",
-    "env = os.getenv(\"PINECONE_ENVIRONMENT\") or \"PINECONE_ENVIRONMENT\"\n",
     "\n",
-    "index_name = \"langchain-pinecone-hybrid-search\"\n",
-    "\n",
-    "pinecone.init(api_key=api_key, environment=env)\n",
-    "pinecone.whoami()"
+    "index_name = \"langchain-pinecone-hybrid-search\""
    ]
   },
   {

docs/docs/integrations/retrievers/self_query/pinecone.ipynb

@@ -78,8 +78,8 @@
    "outputs": [],
    "source": [
     "from langchain.schema import Document\n",
-    "from langchain_community.vectorstores import Pinecone\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_pinecone import PineconeVectorStore\n",
     "\n",
     "embeddings = OpenAIEmbeddings()\n",
     "# create new index\n",
@@ -124,7 +124,7 @@
     "        },\n",
     "    ),\n",
     "]\n",
-    "vectorstore = Pinecone.from_documents(\n",
+    "vectorstore = PineconeVectorStore.from_documents(\n",
     "    docs, embeddings, index_name=\"langchain-self-retriever-demo\"\n",
     ")"
    ]

docs/docs/integrations/vectorstores/pinecone.ipynb

@@ -71,7 +71,7 @@
    "source": [
     "Now let's assume you have your Pinecone index set up with `dimension=1536`.\n",
     "\n",
-    "We can connect to our Pinecone index and insert those chunked docs as contents with `Pinecone.from_documents`."
+    "We can connect to our Pinecone index and insert those chunked docs as contents with `PineconeVectorStore.from_documents`."
    ]
   },
   {
@@ -81,11 +81,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_pinecone import Pinecone\n",
+    "from langchain_pinecone import PineconeVectorStore\n",
     "\n",
     "index_name = \"langchain-test-index\"\n",
     "\n",
-    "docsearch = Pinecone.from_documents(docs, embeddings, index_name=index_name)"
+    "docsearch = PineconeVectorStore.from_documents(docs, embeddings, index_name=index_name)"
    ]
   },
   {
@@ -143,7 +143,7 @@
     }
    ],
    "source": [
-    "vectorstore = Pinecone(index_name=index_name, embedding=embeddings)\n",
+    "vectorstore = PineconeVectorStore(index_name=index_name, embedding=embeddings)\n",
     "\n",
     "vectorstore.add_texts([\"More text!\"])"
    ]

docs/docs/use_cases/question_answering/per_user.ipynb

@@ -35,28 +35,22 @@
     "\n",
     "## Code Example\n",
     "\n",
-    "Let's see a concrete example of what this looks like in code. We will use Pinecone for this example."
+    "Let's see a concrete example of what this looks like in code. We will use Pinecone for this example.\n",
+    "\n",
+    "To configure Pinecone, set the following environment variable:\n",
+    "\n",
+    "- `PINECONE_API_KEY`: Your Pinecone API key"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "75823b2d",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/harrisonchase/.pyenv/versions/3.10.1/envs/langchain/lib/python3.10/site-packages/pinecone/index.py:4: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n",
-      "  from tqdm.autonotebook import tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "import pinecone\n",
-    "from langchain_community.vectorstores import Pinecone\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_pinecone import PineconeVectorStore"
    ]
   },
   {
@@ -77,12 +71,8 @@
     }
    ],
    "source": [
-    "# The environment should be the one specified next to the API key\n",
-    "# in your Pinecone console\n",
-    "pinecone.init(api_key=\"...\", environment=\"...\")\n",
-    "index = pinecone.Index(\"test-example\")\n",
     "embeddings = OpenAIEmbeddings()\n",
-    "vectorstore = Pinecone(index, embeddings, \"text\")\n",
+    "vectorstore = PineconeVectorStore(index_name=\"test-example\", embedding=embeddings)\n",
     "\n",
     "vectorstore.add_texts([\"i worked at kensho\"], namespace=\"harrison\")\n",
     "vectorstore.add_texts([\"i worked at facebook\"], namespace=\"ankush\")"
@@ -301,15 +291,16 @@
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "For more vectorstore implementations for multi-user, please refer to specific pages, such as [Milvus](/docs/integrations/vectorstores/milvus)."
-   ],
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {
     "collapsed": false,
     "pycharm": {
      "name": "#%% md\n"
     }
-   }
+   },
+   "source": [
+    "For more vectorstore implementations for multi-user, please refer to specific pages, such as [Milvus](/docs/integrations/vectorstores/milvus)."
+   ]
   }
  ],
  "metadata": {
@@ -333,4 +324,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}