diff --git a/langchain/README.md b/langchain/README.md
index bdc3d32..6e2ddc9 100644
--- a/langchain/README.md
+++ b/langchain/README.md
@@ -1,2 +1,28 @@
 # langchain-vectorize
 
+This package contains the LangChain integrations for using Vectorize.
+
+## Installation and Setup
+
+Installation of this package:
+
+```bash
+pip install langchain-vectorize
+```
+
+## Integrations overview
+
+### Retriever
+
+See the [LangChain Retriever documentation](https://python.langchain.com/docs/concepts/retrievers/) for more information.
+```python
+from langchain_vectorize import VectorizeRetriever
+
+retriever = VectorizeRetriever(
+    api_token="...",
+    organization="...",
+    pipeline_id="...",
+)
+retriever.invoke("query")
+```
+See an example notebook [here](https://github.com/vectorize-io/integrations-python/tree/main/notebooks/langchain_retriever.ipynb).
\ No newline at end of file
diff --git a/langchain/langchain_vectorize/__init__.py b/langchain/langchain_vectorize/__init__.py
index 2351eb0..f1b520b 100644
--- a/langchain/langchain_vectorize/__init__.py
+++ b/langchain/langchain_vectorize/__init__.py
@@ -1 +1,5 @@
 """Vectorize integrations with LangChain."""
+
+from langchain_vectorize.retrievers import VectorizeRetriever
+
+__all__ = ["VectorizeRetriever"]
diff --git a/langchain/langchain_vectorize/retrievers.py b/langchain/langchain_vectorize/retrievers.py
index 54d1ed7..3559f42 100644
--- a/langchain/langchain_vectorize/retrievers.py
+++ b/langchain/langchain_vectorize/retrievers.py
@@ -36,7 +36,76 @@
 
 
 class VectorizeRetriever(BaseRetriever):
-    """Vectorize retriever."""
+    """Vectorize retriever.
+
+    Setup:
+        Install package ``langchain-vectorize``
+
+        .. code-block:: bash
+
+            pip install -U langchain-vectorize
+
+    Init args:
+        api_token: str
+            The Vectorize API token.
+        environment: Literal["prod", "dev", "local", "staging"]
+            The Vectorize API environment. Defaults to "prod".
+        organization: Optional[str]
+            The Vectorize organization ID. Defaults to None.
+        pipeline_id: Optional[str]
+            The Vectorize pipeline ID. Defaults to None.
+        num_results: int
+            Number of documents to return. Defaults to 5.
+        rerank: bool
+            Whether to rerank the results. Defaults to False.
+        metadata_filters: list[dict[str, Any]]
+            The metadata filters to apply when retrieving the documents. Defaults to [].
+
+    Instantiate:
+        .. code-block:: python
+
+            from langchain_vectorize import VectorizeRetriever
+
+            retriever = VectorizeRetriever(
+                api_token="xxxxx", "organization"="1234", "pipeline_id"="5678"
+            )
+
+    Usage:
+        .. code-block:: python
+
+            query = "what year was breath of the wild released?"
+            retriever.invoke(query)
+
+    Use within a chain:
+        .. code-block:: python
+
+            from langchain_core.output_parsers import StrOutputParser
+            from langchain_core.prompts import ChatPromptTemplate
+            from langchain_core.runnables import RunnablePassthrough
+            from langchain_openai import ChatOpenAI
+
+            prompt = ChatPromptTemplate.from_template(
+                \"\"\"Answer the question based only on the context provided.
+
+            Context: {context}
+
+            Question: {question}\"\"\"
+            )
+
+            llm = ChatOpenAI(model="gpt-4o")
+
+            def format_docs(docs):
+                return "\n\n".join(doc.page_content for doc in docs)
+
+            chain = (
+                {"context": retriever | format_docs, "question": RunnablePassthrough()}
+                | prompt
+                | llm
+                | StrOutputParser()
+            )
+
+            chain.invoke("how many units did breath of the wild sell in 2020")
+    """  # noqa: D301
 
     api_token: str
     """The Vectorize API token."""
@@ -146,7 +215,8 @@ def invoke(
 
             .. code-block:: python
 
-                retriever.invoke("query")
+                query = "what year was breath of the wild released?"
+                docs = retriever.invoke(query, num_results=2)
         """
         kwargs = {}
         if organization:
diff --git a/notebooks/langchain_retriever.ipynb b/notebooks/langchain_retriever.ipynb
new file mode 100644
index 0000000..32eaa44
--- /dev/null
+++ b/notebooks/langchain_retriever.ipynb
@@ -0,0 +1,287 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Langchain Vectorize Retriever\n",
+    "\n",
+    "This notebook shows how to use the LangChain Vectorize retriever."
+   ],
+   "metadata": {
+    "id": "zvHrM3wa7IE1"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Setup\n",
+    "\n",
+    "In the following steps, we'll setup the Vectorize environment and create a RAG pipeline.\n"
+   ],
+   "metadata": {
+    "id": "r-RswOO5o4K_"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Create a Vectorize Account & Get Your Access Token\n",
+    "\n",
+    "Sign up for a free Vectorize account [here](https://platform.vectorize.io/)\n",
+    "Generate an access token in the [Access Token](https://docs.vectorize.io/rag-pipelines/retrieval-endpoint#access-tokens) section\n",
+    "Gather your organization ID. From the browser url, extract the UUID from the URL after /organization/"
+   ],
+   "metadata": {
+    "id": "FhvmvFKh4Rlh"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Install langchain_vectorize"
+   ],
+   "metadata": {
+    "id": "JdZ5vlzjoDVr"
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IJFmtvDLn5R3"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install -qU langchain-vectorize"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Configure token and organization ID\n",
+    "\n"
+   ],
+   "metadata": {
+    "id": "L2SULMfWpWFX"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "VECTORIZE_ORG_ID = getpass.getpass(\"Enter Vectorize organization ID: \")\n",
+    "VECTORIZE_API_TOKEN = getpass.getpass(\"Enter Vectorize API Token: \")"
+   ],
+   "metadata": {
+    "id": "BnF8KoDZpg2O"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Download a PDF file"
+   ],
+   "metadata": {
+    "id": "Oj10Moznpz67"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "! wget \"https://raw.githubusercontent.com/vectorize-io/vectorize-clients/refs/tags/python-0.1.3/tests/python/tests/research.pdf\""
+   ],
+   "metadata": {
+    "id": "eLbbTPytrgNw"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Initialize the vectorize client"
+   ],
+   "metadata": {
+    "id": "7g54J6awtshs"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "import vectorize_client as v\n",
+    "\n",
+    "api = v.ApiClient(v.Configuration(access_token=VECTORIZE_API_TOKEN))"
+   ],
+   "metadata": {
+    "id": "9Fr4yz5CrFWP"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Create a File Upload Source Connector"
+   ],
+   "metadata": {
+    "id": "wPDoeqETxJrS"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "import urllib3, json, os\n",
+    "\n",
+    "connectors_api = v.ConnectorsApi(api)\n",
+    "response = connectors_api.create_source_connector(VECTORIZE_ORG_ID, [{\n",
+    "        \"type\": \"FILE_UPLOAD\",\n",
+    "        \"name\": \"From API\"\n",
+    "    }])\n",
+    "source_connector_id = response.connectors[0].id"
+   ],
+   "metadata": {
+    "id": "9yEARIcFue5N"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Upload the PDF file"
+   ],
+   "metadata": {
+    "id": "yU3lS6dpxZnQ"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "file_path = \"research.pdf\"\n",
+    "\n",
+    "http = urllib3.PoolManager()\n",
+    "uploads_api = v.UploadsApi(api)\n",
+    "metadata = {\"created-from-api\": True}\n",
+    "\n",
+    "upload_response = uploads_api.start_file_upload_to_connector(\n",
+    "        VECTORIZE_ORG_ID, source_connector_id, v.StartFileUploadToConnectorRequest(\n",
+    "            name=file_path.split(\"/\")[-1],\n",
+    "            content_type=\"application/pdf\",\n",
+    "            # add additional metadata that will be stored along with each chunk in the vector database\n",
+    "            metadata=json.dumps(metadata))\n",
+    ")\n",
+    "\n",
+    "with open(file_path, \"rb\") as f:\n",
+    "    response = http.request(\"PUT\", upload_response.upload_url, body=f, headers={\"Content-Type\": \"application/pdf\", \"Content-Length\": str(os.path.getsize(file_path))})\n",
+    "\n",
+    "if response.status != 200:\n",
+    "    print(\"Upload failed: \", response.data)\n",
+    "else:\n",
+    "    print(\"Upload successful\")"
+   ],
+   "metadata": {
+    "id": "OIiMIZ8ZxUYF"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Connect to the AI Platform and Vector Database"
+   ],
+   "metadata": {
+    "id": "PdJJfOhfxiIo"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "ai_platforms = connectors_api.get_ai_platform_connectors(VECTORIZE_ORG_ID)\n",
+    "builtin_ai_platform = [c.id for c in ai_platforms.ai_platform_connectors if c.type == \"VECTORIZE\"][0]\n",
+    "\n",
+    "vector_databases = connectors_api.get_destination_connectors(VECTORIZE_ORG_ID)\n",
+    "builtin_vector_db = [c.id for c in vector_databases.destination_connectors if c.type == \"VECTORIZE\"][0]"
+   ],
+   "metadata": {
+    "id": "0ZSGhXJfxjBb"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Configure and Deploy the Pipeline"
+   ],
+   "metadata": {
+    "id": "JWoL-kqQxs5H"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "pipelines = v.PipelinesApi(api)\n",
+    "response = pipelines.create_pipeline(VECTORIZE_ORG_ID, v.PipelineConfigurationSchema(\n",
+    "    source_connectors=[v.SourceConnectorSchema(id=source_connector_id, type=\"FILE_UPLOAD\", config={})],\n",
+    "    destination_connector=v.DestinationConnectorSchema(id=builtin_vector_db, type=\"VECTORIZE\", config={}),\n",
+    "    ai_platform=v.AIPlatformSchema(id=builtin_ai_platform, type=\"VECTORIZE\", config={}),\n",
+    "    pipeline_name=\"My Pipeline From API\",\n",
+    "    schedule=v.ScheduleSchema(type=\"manual\")\n",
+    "))\n",
+    "pipeline_id = response.data.id"
+   ],
+   "metadata": {
+    "id": "hze9vJbQxvqA"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Use the LangChain Vectorize retriever"
+   ],
+   "metadata": {
+    "id": "5ULion9wyj6T"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "from langchain_vectorize.retrievers import VectorizeRetriever\n",
+    "\n",
+    "retriever = VectorizeRetriever(\n",
+    "    api_token=VECTORIZE_API_TOKEN,\n",
+    "    organization=VECTORIZE_ORG_ID,\n",
+    "    pipeline_id=pipeline_id,\n",
+    ")\n",
+    "\n",
+    "retriever.invoke(\"Apple Shareholders equity\", num_results=2)\n"
+   ],
+   "metadata": {
+    "id": "9D-QfiW7yoe0"
+   },
+   "execution_count": null,
+   "outputs": []
+  }
+ ]
+}