mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-31 18:38:48 +00:00
docs: add anchorbrowser (#32494)
# Description This PR updates the docs for the [langchain-anchorbrowser](https://pypi.org/project/langchain-anchorbrowser/) package. It adds a few tools [Anchor Browser](https://anchorbrowser.io/?utm=langchain) is the platform for AI Agentic browser automation, which solves the challenge of automating workflows for web applications that lack APIs or have limited API coverage. It simplifies the creation, deployment, and management of browser-based automations, transforming complex web interactions into simple API endpoints. --------- Co-authored-by: Mason Daugherty <mason@langchain.dev> Co-authored-by: Mason Daugherty <github@mdrxy.com>
This commit is contained in:
GDanksAnchor
GitHub
38
docs/docs/integrations/providers/anchor_browser.mdx
Normal file
38
docs/docs/integrations/providers/anchor_browser.mdx
Normal file
@@ -0,0 +1,38 @@
|
||||
# Anchor Browser
|
||||
|
||||
[Anchor](https://anchorbrowser.io?utm=langchain) is the platform for AI Agentic browser automation, which solves the challenge of automating workflows for web applications that lack APIs or have limited API coverage. It simplifies the creation, deployment, and management of browser-based automations, transforming complex web interactions into simple API endpoints.
|
||||
|
||||
`langchain-anchorbrowser` provides 3 main tools:
|
||||
- `AnchorContentTool` - For web content extractions in Markdown or HTML format.
|
||||
- `AnchorScreenshotTool` - For web page screenshots.
|
||||
- `AnchorWebTaskTools` - To perform web tasks.
|
||||
|
||||
## Quickstart
|
||||
|
||||
### Installation
|
||||
|
||||
Install the package:
|
||||
|
||||
```bash
|
||||
pip install langchain-anchorbrowser
|
||||
```
|
||||
|
||||
### Usage
|
||||
|
||||
Import and utilize your intended tool. The full list of Anchor Browser available tools see **Tool Features** table in [Anchor Browser tool page](/docs/integrations/tools/anchor_browser)
|
||||
|
||||
```python
|
||||
from langchain_anchorbrowser import AnchorContentTool
|
||||
|
||||
# Get Markdown Content for https://www.anchorbrowser.io
|
||||
AnchorContentTool().invoke(
|
||||
{"url": "https://www.anchorbrowser.io", "format": "markdown"}
|
||||
)
|
||||
```
|
||||
|
||||
## Additional Resources
|
||||
|
||||
- [PyPi](https://pypi.org/project/langchain-anchorbrowser)
|
||||
- [Github](https://github.com/anchorbrowser/langchain-anchorbrowser)
|
||||
- [Anchor Browser Docs](https://docs.anchorbrowser.io/introduction?utm=langchain)
|
||||
- [Anchor Browser API Reference](https://docs.anchorbrowser.io/api-reference/ai-tools/perform-web-task?utm=langchain)
|
||||
307
docs/docs/integrations/tools/anchor_browser.ipynb
Normal file
307
docs/docs/integrations/tools/anchor_browser.ipynb
Normal file
@@ -0,0 +1,307 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "2ce4bdbc",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "raw"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_label: anchor_browser\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a6f91f20",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Anchor Browser\n",
|
||||
"\n",
|
||||
"Anchor is a platform for AI Agentic browser automation, which solves the challenge of automating workflows for web applications that lack APIs or have limited API coverage. It simplifies the creation, deployment, and management of browser-based automations, transforming complex web interactions into simple API endpoints.\n",
|
||||
"\n",
|
||||
"This notebook provides a quick overview for getting started with Anchor Browser tools. For more information of Anchor Browser visit [Anchorbrowser.io](https://anchorbrowser.io?utm=langchain) or the [Anchor Browser Docs](https://docs.anchorbrowser.io?utm=langchain)\n",
|
||||
"\n",
|
||||
"## Overview\n",
|
||||
"\n",
|
||||
"### Integration details\n",
|
||||
"\n",
|
||||
"Anchor Browser package for LangChain is [langchain-anchorbrowser](https://pypi.org/project/langchain-anchorbrowser), and the current latest version is .\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"### Tool features\n",
|
||||
"| Tool Name | Package | Description | Parameters |\n",
|
||||
"| :--- | :--- | :--- | :---|\n",
|
||||
"| `AnchorContentTool` | langchain-anchorbrowser | Extract text content from web pages | `url`, `format` |\n",
|
||||
"| `AnchorScreenshotTool` | langchain-anchorbrowser | Take screenshots of web pages | `url`, `width`, `height`, `image_quality`, `wait`, `scroll_all_content`, `capture_full_height`, `s3_target_address` |\n",
|
||||
"| `AnchorWebTaskToolKit` | langchain-anchorbrowser | Perform intelligent web tasks using AI (Simple & Advanced modes) | see below |\n",
|
||||
"\n",
|
||||
"The parameters allowed in `langchain-anchorbrowser` are only a subset of those listed in the Anchor Browser API reference respectively: [Get Webpage Content](https://docs.anchorbrowser.io/sdk-reference/tools/get-webpage-content?utm=langchain), [Screenshot Webpage](https://docs.anchorbrowser.io/sdk-reference/tools/screenshot-webpage?utm=langchain), and [Perform Web Task](https://docs.anchorbrowser.io/sdk-reference/ai-tools/perform-web-task?utm=langchain).\n",
|
||||
"\n",
|
||||
"**Info:** Anchor currently implements `SimpleAnchorWebTaskTool` and `AdvancedAnchorWebTaskTool` tools for langchain with `browser_use` agent. For \n",
|
||||
"\n",
|
||||
"#### AnchorWebTaskToolKit Tools\n",
|
||||
"\n",
|
||||
"The difference between each tool in this toolkit is the pydantic configuration structure.\n",
|
||||
"| Tool Name | Package | Parameters |\n",
|
||||
"| :--- | :--- | :--- |\n",
|
||||
"| `SimpleAnchorWebTaskTool` | langchain-anchorbrowser | prompt, url |\n",
|
||||
"| `AdvancedAnchorWebTaskTool` | langchain-anchorbrowser | prompt, url, output_schema |\n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"The integration lives in the `langchain-anchorbrowser` package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f85b4089",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --quiet -U langchain-anchorbrowser"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b15e9266",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Credentials\n",
|
||||
"\n",
|
||||
"Use your Anchor Browser Credentials. Get them on Anchor Browser [API Keys page](https://app.anchorbrowser.io/api-keys?utm=langchain) as needed."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "e0b178a2-8816-40ca-b57c-ccdd86dde9c9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"if not os.environ.get(\"ANCHORBROWSER_API_KEY\"):\n",
|
||||
" os.environ[\"ANCHORBROWSER_API_KEY\"] = getpass.getpass(\"ANCHORBROWSER API key:\\n\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1c97218f-f366-479d-8bf7-fe9f2f6df73f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Instantiation\n",
|
||||
"\n",
|
||||
"Instantiace easily Anchor Browser tools instances."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8b3ddfe9-ca79-494c-a7ab-1f56d9407a64",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_anchorbrowser import (\n",
|
||||
" AnchorContentTool,\n",
|
||||
" AnchorScreenshotTool,\n",
|
||||
" AdvancedAnchorWebTaskTool,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"anchor_content_tool = AnchorContentTool()\n",
|
||||
"anchor_screenshot_tool = AnchorScreenshotTool()\n",
|
||||
"anchor_advanced_web_task_tool = AdvancedAnchorWebTaskTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "74147a1a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Invocation\n",
|
||||
"\n",
|
||||
"### [Invoke directly with args](/docs/concepts/tools/#use-the-tool-directly)\n",
|
||||
"\n",
|
||||
"The full available argument list appear above in the tool features table."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get Markdown Content for https://www.anchorbrowser.io\n",
|
||||
"anchor_content_tool.invoke(\n",
|
||||
" {\"url\": \"https://www.anchorbrowser.io\", \"format\": \"markdown\"}\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Get a Screenshot for https://docs.anchorbrowser.io\n",
|
||||
"anchor_screenshot_tool.invoke(\n",
|
||||
" {\"url\": \"https://docs.anchorbrowser.io\", \"width\": 1280, \"height\": 720}\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Get a Screenshot for https://docs.anchorbrowser.io\n",
|
||||
"anchor_advanced_web_task_tool.invoke(\n",
|
||||
" {\n",
|
||||
" \"prompt\": \"Collect the node names and their CPU average %\",\n",
|
||||
" \"url\": \"https://play.grafana.org/a/grafana-k8s-app/navigation/nodes?from=now-1h&to=now&refresh=1m\",\n",
|
||||
" \"output_schema\": {\n",
|
||||
" \"nodes_cpu_usage\": [\n",
|
||||
" {\"node\": \"string\", \"cluster\": \"string\", \"cpu_avg_percentage\": \"number\"}\n",
|
||||
" ]\n",
|
||||
" },\n",
|
||||
" }\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d6e73897",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### [Invoke with ToolCall](/docs/concepts/tool_calling/#tool-execution)\n",
|
||||
"\n",
|
||||
"We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f90e33a7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
|
||||
"model_generated_tool_call = {\n",
|
||||
" \"args\": {\"url\": \"https://www.anchorbrowser.io\", \"format\": \"markdown\"},\n",
|
||||
" \"id\": \"1\",\n",
|
||||
" \"name\": anchor_content_tool.name,\n",
|
||||
" \"type\": \"tool_call\",\n",
|
||||
"}\n",
|
||||
"anchor_content_tool.invoke(model_generated_tool_call)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "659f9fbd-6fcf-445f-aa8c-72d8e60154bd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chaining\n",
|
||||
"\n",
|
||||
"We can use our tool in a chain by first binding it to a [tool-calling model](/docs/how_to/tool_calling/) and then calling it:\n",
|
||||
"## Use within an agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c67bfd54",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -qU langchain langchain-openai"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "af3123ad-7a02-40e5-b58e-7d56e23e5830",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import init_chat_model\n",
|
||||
"\n",
|
||||
"llm = init_chat_model(model=\"gpt-4o\", model_provider=\"openai\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "210511c8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.environ.get(\"OPENAI_API_KEY\"):\n",
|
||||
" os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OPENAI API key:\\n\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fdbf35b5-3aaf-4947-9ec6-48c21533fb95",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"from langchain_core.runnables import RunnableConfig, chain\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate(\n",
|
||||
" [\n",
|
||||
" (\"system\", \"You are a helpful assistant.\"),\n",
|
||||
" (\"human\", \"{user_input}\"),\n",
|
||||
" (\"placeholder\", \"{messages}\"),\n",
|
||||
" ]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# specifying tool_choice will force the model to call this tool.\n",
|
||||
"llm_with_tools = llm.bind_tools(\n",
|
||||
" [anchor_content_tool], tool_choice=anchor_content_tool.name\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"llm_chain = prompt | llm_with_tools\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@chain\n",
|
||||
"def tool_chain(user_input: str, config: RunnableConfig):\n",
|
||||
" input_ = {\"user_input\": user_input}\n",
|
||||
" ai_msg = llm_chain.invoke(input_, config=config)\n",
|
||||
" tool_msgs = anchor_content_tool.batch(ai_msg.tool_calls, config=config)\n",
|
||||
" return llm_chain.invoke({**input_, \"messages\": [ai_msg, *tool_msgs]}, config=config)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"tool_chain.invoke(input())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4ac8146c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
" - [PyPi](https://pypi.org/project/langchain-anchorbrowser)\n",
|
||||
" - [Github](https://github.com/anchorbrowser/langchain-anchorbrowser)\n",
|
||||
" - [Anchor Browser Docs](https://docs.anchorbrowser.io/introduction?utm=langchain)\n",
|
||||
" - [Anchor Browser API Reference](https://docs.anchorbrowser.io/api-reference/ai-tools/perform-web-task?utm=langchain)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "langchain",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.11"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -709,6 +709,10 @@ packages:
|
||||
repo: digitalocean/langchain-gradient
|
||||
downloads: 576
|
||||
downloads_updated_at: '2025-08-10T21:38:36.795416+00:00'
|
||||
- name: langchain-anchorbrowser
|
||||
provider_page: anchor_browser
|
||||
path: .
|
||||
repo: anchorbrowser/langchain-anchorbrowser
|
||||
- name: toolbox-langchain
|
||||
repo: googleapis/mcp-toolbox-sdk-python
|
||||
path: packages/toolbox-langchain
|
||||
|
||||
Reference in New Issue
Block a user