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.
This notebook provides a quick overview for getting started with Anchor Browser tools. For more information of Anchor Browser visit Anchorbrowser.io or the Anchor Browser Docs
Overview Integration detailsAnchor Browser package for LangChain is langchain-anchorbrowser, and the current latest version is .
Tool features Tool Name Package Description ParametersAnchorContentTool langchain-anchorbrowser Extract text content from web pages url, format AnchorScreenshotTool langchain-anchorbrowser Take screenshots of web pages url, width, height, image_quality, wait, scroll_all_content, capture_full_height, s3_target_address AnchorWebTaskToolKit langchain-anchorbrowser Perform intelligent web tasks using AI (Simple & Advanced modes) see below
The parameters allowed in langchain-anchorbrowser are only a subset of those listed in the Anchor Browser API reference respectively: Get Webpage Content, Screenshot Webpage, and Perform Web Task.
Info: Anchor currently implements SimpleAnchorWebTaskTool and AdvancedAnchorWebTaskTool tools for langchain with browser_use agent. For
The difference between each tool in this toolkit is the pydantic configuration structure.
Tool Name Package ParametersSimpleAnchorWebTaskTool langchain-anchorbrowser prompt, url AdvancedAnchorWebTaskTool langchain-anchorbrowser prompt, url, output_schema Setup
The integration lives in the langchain-anchorbrowser package.
%pip install --quiet -U langchain-anchorbrowser
Use your Anchor Browser Credentials. Get them on Anchor Browser API Keys page as needed.
import getpass
import os
if not os.environ.get("ANCHORBROWSER_API_KEY"):
os.environ["ANCHORBROWSER_API_KEY"] = getpass.getpass("ANCHORBROWSER API key:\n")
Instantiace easily Anchor Browser tools instances.
from langchain_anchorbrowser import (
AnchorContentTool,
AnchorScreenshotTool,
AdvancedAnchorWebTaskTool,
)
anchor_content_tool = AnchorContentTool()
anchor_screenshot_tool = AnchorScreenshotTool()
anchor_advanced_web_task_tool = AdvancedAnchorWebTaskTool()
The full available argument list appear above in the tool features table.
anchor_content_tool.invoke(
{"url": "https://www.anchorbrowser.io", "format": "markdown"}
)
anchor_screenshot_tool.invoke(
{"url": "https://docs.anchorbrowser.io", "width": 1280, "height": 720}
)
anchor_advanced_web_task_tool.invoke(
{
"prompt": "Collect the node names and their CPU average %",
"url": "https://play.grafana.org/a/grafana-k8s-app/navigation/nodes?from=now-1h&to=now&refresh=1m",
"output_schema": {
"nodes_cpu_usage": [
{"node": "string", "cluster": "string", "cpu_avg_percentage": "number"}
]
},
}
)
We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:
model_generated_tool_call = {
"args": {"url": "https://www.anchorbrowser.io", "format": "markdown"},
"id": "1",
"name": anchor_content_tool.name,
"type": "tool_call",
}
anchor_content_tool.invoke(model_generated_tool_call)
We can use our tool in a chain by first binding it to a tool-calling model and then calling it:
Use within an agent%pip install -qU langchain langchain-openai
from langchain.chat_models import init_chat_model
llm = init_chat_model(model="gpt-4o", model_provider="openai")
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("OPENAI API key:\n")
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableConfig, chain
prompt = ChatPromptTemplate(
[
("system", "You are a helpful assistant."),
("human", "{user_input}"),
("placeholder", "{messages}"),
]
)
llm_with_tools = llm.bind_tools(
[anchor_content_tool], tool_choice=anchor_content_tool.name
)
llm_chain = prompt | llm_with_tools
@chain
def tool_chain(user_input: str, config: RunnableConfig):
input_ = {"user_input": user_input}
ai_msg = llm_chain.invoke(input_, config=config)
tool_msgs = anchor_content_tool.batch(ai_msg.tool_calls, config=config)
return llm_chain.invoke({**input_, "messages": [ai_msg, *tool_msgs]}, config=config)
tool_chain.invoke(input())
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4