Skip to content

The agent engineering platform.

docs: Add Oxylabs integration (#30591)

oxy-tg38807871ec11
diff --git a/docs/docs/integrations/providers/oxylabs.mdx b/docs/docs/integrations/providers/oxylabs.mdx
new file mode 100644
index 0000000000..30b2093336
--- /dev/null
+++ b/docs/docs/integrations/providers/oxylabs.mdx
@@ -0,0 +1,18 @@
+# Oxylabs
+
+[Oxylabs](https://oxylabs.io/) is a market-leading web intelligence collection platform, driven by the highest business,
+ethics, and compliance standards, enabling companies worldwide to unlock data-driven insights.
+
+[langchain-oxylabs](https://pypi.org/project/langchain-oxylabs/) implements
+tools enabling LLMs to interact with Oxylabs Web Scraper API.
+
+
+## Installation and Setup
+
+```bash
+pip install langchain-oxylabs
+```
+
+## Tools
+
+See details on available tools [here](/docs/integrations/tools/oxylabs/).
diff --git a/docs/docs/integrations/tools/oxylabs.ipynb b/docs/docs/integrations/tools/oxylabs.ipynb
new file mode 100644
index 0000000000..2c459682dc
--- /dev/null
+++ b/docs/docs/integrations/tools/oxylabs.ipynb
@@ -0,0 +1,298 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "65142ccb18a6add5",
+ "metadata": {},
+ "source": "# Oxylabs"
+ },
+ {
+ "cell_type": "markdown",
+ "id": "19976df355f9c461",
+ "metadata": {},
+ "source": [
+ ">[Oxylabs](https://oxylabs.io/) is a market-leading web intelligence collection platform, driven by the highest business, ethics, and compliance standards, enabling companies worldwide to unlock data-driven insights.\n",
+ "\n",
+ "## Overview\n",
+ "\n",
+ "This package contains the LangChain integration with Oxylabs, providing tools to scrape Google search results with Oxylabs Web Scraper API using LangChain's framework.\n",
+ "\n",
+ "The following classes are provided by this package:\n",
+ "- `OxylabsSearchRun` - A tool that returns scraped Google search results in a formatted text\n",
+ "- `OxylabsSearchResults` - A tool that returns scraped Google search results in a JSON format\n",
+ "- `OxylabsSearchAPIWrapper` - An API wrapper for initializing Oxylabs API"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "76e6d8030199710d",
+ "metadata": {},
+ "source": [
+ "| Pricing |\n",
+ "|:-------------------------------:|\n",
+ "| ✅ Free 5,000 results for 1 week |"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "eb59c5f3051be9d4",
+ "metadata": {},
+ "source": "## Setup"
+ },
+ {
+ "cell_type": "markdown",
+ "id": "45951d881c460419",
+ "metadata": {},
+ "source": "Install the required dependencies."
+ },
+ {
+ "cell_type": "code",
+ "id": "576e08c41f16ceda",
+ "metadata": {},
+ "source": [
+ "%pip install -qU langchain-oxylabs"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "ce19bb3a52a3ab60",
+ "metadata": {},
+ "source": "### Credentials"
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b8330dfd5861482e",
+ "metadata": {},
+ "source": "Set up the proper API keys and environment variables. Create your API user credentials: Sign up for a free trial or purchase the product in the [Oxylabs dashboard](https://dashboard.oxylabs.io/en/registration) to create your API user credentials (OXYLABS_USERNAME and OXYLABS_PASSWORD)."
+ },
+ {
+ "cell_type": "code",
+ "id": "474b6eaf6e35efda",
+ "metadata": {},
+ "source": [
+ "import getpass\n",
+ "import os\n",
+ "\n",
+ "os.environ[\"OXYLABS_USERNAME\"] = getpass.getpass(\"Enter your Oxylabs username: \")\n",
+ "os.environ[\"OXYLABS_PASSWORD\"] = getpass.getpass(\"Enter your Oxylabs password: \")"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "ae310f86b113bd78",
+ "metadata": {},
+ "source": "## Instantiation"
+ },
+ {
+ "cell_type": "code",
+ "id": "69ea8139f6152b48",
+ "metadata": {},
+ "source": [
+ "from langchain_oxylabs import OxylabsSearchAPIWrapper, OxylabsSearchRun\n",
+ "\n",
+ "oxylabs_wrapper = OxylabsSearchAPIWrapper()\n",
+ "tool_ = OxylabsSearchRun(wrapper=oxylabs_wrapper)"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "636efff6267b9bc1",
+ "metadata": {},
+ "source": "## Invocation"
+ },
+ {
+ "cell_type": "markdown",
+ "id": "272f5fdaed5fa000",
+ "metadata": {},
+ "source": "### Invoke directly with args"
+ },
+ {
+ "cell_type": "markdown",
+ "id": "3c26724911f6cfdf",
+ "metadata": {},
+ "source": "The `OxylabsSearchRun` tool takes a single \"query\" argument, which should be a natural language query and returns combined string format result:"
+ },
+ {
+ "cell_type": "code",
+ "id": "b5f4d423cb3abf",
+ "metadata": {},
+ "source": [
+ "tool_.invoke({\"query\": \"Restaurants in Paris.\"})"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "784aad18bba31062",
+ "metadata": {},
+ "source": "### Invoke with ToolCall"
+ },
+ {
+ "cell_type": "code",
+ "id": "8afd1652e2c4e7c9",
+ "metadata": {},
+ "source": [
+ "tool_ = OxylabsSearchRun(\n",
+ " wrapper=oxylabs_wrapper,\n",
+ " kwargs={\n",
+ " \"result_categories\": [\n",
+ " \"local_information\",\n",
+ " \"combined_search_result\",\n",
+ " ]\n",
+ " },\n",
+ ")"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "code",
+ "id": "1b903fb2f8272df2",
+ "metadata": {},
+ "source": [
+ "from pprint import pprint\n",
+ "\n",
+ "model_generated_tool_call = {\n",
+ " \"args\": {\n",
+ " \"query\": \"Visit restaurants in Vilnius.\",\n",
+ " \"geo_location\": \"Vilnius,Lithuania\",\n",
+ " },\n",
+ " \"id\": \"1\",\n",
+ " \"name\": \"oxylabs_search\",\n",
+ " \"type\": \"tool_call\",\n",
+ "}\n",
+ "tool_call_result = tool_.invoke(model_generated_tool_call)\n",
+ "\n",
+ "# The content is a JSON string of results\n",
+ "pprint(tool_call_result.content)"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a436fc39ce17b6da",
+ "metadata": {},
+ "source": [
+ "## Use within an agent\n",
+ "Install the required dependencies."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "id": "a6f23e65092e8d27",
+ "metadata": {},
+ "source": "%pip install -qU \"langchain[openai]\" langgraph",
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "code",
+ "id": "21078a0c265759ff",
+ "metadata": {},
+ "source": [
+ "import getpass\n",
+ "import os\n",
+ "\n",
+ "from langchain.chat_models import init_chat_model\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter API key for OpenAI: \")\n",
+ "llm = init_chat_model(\"gpt-4o-mini\", model_provider=\"openai\")"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "code",
+ "id": "396548ee2f08fb30",
+ "metadata": {},
+ "source": [
+ "from langgraph.prebuilt import create_react_agent\n",
+ "\n",
+ "# Initialize OxylabsSearchRun tool\n",
+ "tool_ = OxylabsSearchRun(wrapper=oxylabs_wrapper)\n",
+ "\n",
+ "agent = create_react_agent(llm, [tool_])\n",
+ "\n",
+ "user_input = \"What happened in the latest Burning Man floods?\"\n",
+ "\n",
+ "for step in agent.stream(\n",
+ " {\"messages\": user_input},\n",
+ " stream_mode=\"values\",\n",
+ "):\n",
+ " step[\"messages\"][-1].pretty_print()"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b10bbcf5ce299fd5",
+ "metadata": {},
+ "source": [
+ "## JSON results\n",
+ "`OxylabsSearchResults` tool can be used as an alternative to `OxylabsSearchRun` to retrieve results in a JSON format:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "id": "ef0d856f571c4938",
+ "metadata": {},
+ "source": [
+ "import json\n",
+ "\n",
+ "from langchain_oxylabs import OxylabsSearchResults\n",
+ "\n",
+ "tool_ = OxylabsSearchResults(wrapper=oxylabs_wrapper)\n",
+ "\n",
+ "response_results = tool_.invoke({\"query\": \"What are the most famous artists?\"})\n",
+ "response_results = json.loads(response_results)\n",
+ "\n",
+ "for result in response_results:\n",
+ " for key, value in result.items():\n",
+ " print(f\"{key}: {value}\")"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7f16702d224dabb2",
+ "metadata": {},
+ "source": [
+ "## API reference\n",
+ "More information about this integration package can be found here: https://github.com/oxylabs/langchain-oxylabs\n",
+ "\n",
+ "Oxylabs Web Scraper API documentation: https://developers.oxylabs.io/scraper-apis/web-scraper-api\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 2
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython2",
+ "version": "2.7.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/libs/packages.yml b/libs/packages.yml
index 23f86fd6b8..b77921a3de 100644
--- a/libs/packages.yml
+++ b/libs/packages.yml
@@ -564,4 +564,7 @@ packages:
repo: memgraph/langchain-memgraph
- name: langchain-vectara
path: libs/vectara
- repo: vectara/langchain-vectara
\ No newline at end of file
+ repo: vectara/langchain-vectara
+- name: langchain-oxylabs
+ path: .
+ repo: oxylabs/langchain-oxylabs
\ No newline at end of file