You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/docs/modules/agents/tools/examples/metaphor_search.ipynb

247 lines
10 KiB
Plaintext

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Metaphor Search"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook goes over how to use Metaphor search.\n",
"\n",
"First, you need to set up the proper API keys and environment variables. Request an API key [here](Sign up for early access here).\n",
"\n",
"Then enter your API key as an environment variable."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"METAPHOR_API_KEY\"] = \"\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities import MetaphorSearchAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"search = MetaphorSearchAPIWrapper()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Call the API\n",
"`results` takes in a Metaphor-optimized search query and a number of results (up to 500). It returns a list of results with title, url, author, and creation date."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'results': [{'url': 'https://www.anthropic.com/index/core-views-on-ai-safety', 'title': 'Core Views on AI Safety: When, Why, What, and How', 'dateCreated': '2023-03-08', 'author': None, 'score': 0.1998831331729889}, {'url': 'https://aisafety.wordpress.com/', 'title': 'Extinction Risk from Artificial Intelligence', 'dateCreated': '2013-10-08', 'author': None, 'score': 0.19801370799541473}, {'url': 'https://www.lesswrong.com/posts/WhNxG4r774bK32GcH/the-simple-picture-on-ai-safety', 'title': 'The simple picture on AI safety - LessWrong', 'dateCreated': '2018-05-27', 'author': 'Alex Flint', 'score': 0.19735534489154816}, {'url': 'https://slatestarcodex.com/2015/05/29/no-time-like-the-present-for-ai-safety-work/', 'title': 'No Time Like The Present For AI Safety Work', 'dateCreated': '2015-05-29', 'author': None, 'score': 0.19408763945102692}, {'url': 'https://www.lesswrong.com/posts/5BJvusxdwNXYQ4L9L/so-you-want-to-save-the-world', 'title': 'So You Want to Save the World - LessWrong', 'dateCreated': '2012-01-01', 'author': 'Lukeprog', 'score': 0.18853715062141418}, {'url': 'https://openai.com/blog/planning-for-agi-and-beyond', 'title': 'Planning for AGI and beyond', 'dateCreated': '2023-02-24', 'author': 'Authors', 'score': 0.18665121495723724}, {'url': 'https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html', 'title': 'The Artificial Intelligence Revolution: Part 1 - Wait But Why', 'dateCreated': '2015-01-22', 'author': 'Tim Urban', 'score': 0.18604731559753418}, {'url': 'https://forum.effectivealtruism.org/posts/uGDCaPFaPkuxAowmH/anthropic-core-views-on-ai-safety-when-why-what-and-how', 'title': 'Anthropic: Core Views on AI Safety: When, Why, What, and How - EA Forum', 'dateCreated': '2023-03-09', 'author': 'Jonmenaster', 'score': 0.18415069580078125}, {'url': 'https://www.lesswrong.com/posts/xBrpph9knzWdtMWeQ/the-proof-of-doom', 'title': 'The Proof of Doom - LessWrong', 'dateCreated': '2022-03-09', 'author': 'Johnlawrenceaspden', 'score': 0.18159329891204834}, {'url': 'https://intelligence.org/why-ai-safety/', 'title': 'Why AI Safety? - Machine Intelligence Research Institute', 'dateCreated': '2017-03-01', 'author': None, 'score': 0.1814115345478058}]}\n"
]
},
{
"data": {
"text/plain": [
"[{'title': 'Core Views on AI Safety: When, Why, What, and How',\n",
" 'url': 'https://www.anthropic.com/index/core-views-on-ai-safety',\n",
" 'author': None,\n",
" 'date_created': '2023-03-08'},\n",
" {'title': 'Extinction Risk from Artificial Intelligence',\n",
" 'url': 'https://aisafety.wordpress.com/',\n",
" 'author': None,\n",
" 'date_created': '2013-10-08'},\n",
" {'title': 'The simple picture on AI safety - LessWrong',\n",
" 'url': 'https://www.lesswrong.com/posts/WhNxG4r774bK32GcH/the-simple-picture-on-ai-safety',\n",
" 'author': 'Alex Flint',\n",
" 'date_created': '2018-05-27'},\n",
" {'title': 'No Time Like The Present For AI Safety Work',\n",
" 'url': 'https://slatestarcodex.com/2015/05/29/no-time-like-the-present-for-ai-safety-work/',\n",
" 'author': None,\n",
" 'date_created': '2015-05-29'},\n",
" {'title': 'So You Want to Save the World - LessWrong',\n",
" 'url': 'https://www.lesswrong.com/posts/5BJvusxdwNXYQ4L9L/so-you-want-to-save-the-world',\n",
" 'author': 'Lukeprog',\n",
" 'date_created': '2012-01-01'},\n",
" {'title': 'Planning for AGI and beyond',\n",
" 'url': 'https://openai.com/blog/planning-for-agi-and-beyond',\n",
" 'author': 'Authors',\n",
" 'date_created': '2023-02-24'},\n",
" {'title': 'The Artificial Intelligence Revolution: Part 1 - Wait But Why',\n",
" 'url': 'https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html',\n",
" 'author': 'Tim Urban',\n",
" 'date_created': '2015-01-22'},\n",
" {'title': 'Anthropic: Core Views on AI Safety: When, Why, What, and How - EA Forum',\n",
" 'url': 'https://forum.effectivealtruism.org/posts/uGDCaPFaPkuxAowmH/anthropic-core-views-on-ai-safety-when-why-what-and-how',\n",
" 'author': 'Jonmenaster',\n",
" 'date_created': '2023-03-09'},\n",
" {'title': 'The Proof of Doom - LessWrong',\n",
" 'url': 'https://www.lesswrong.com/posts/xBrpph9knzWdtMWeQ/the-proof-of-doom',\n",
" 'author': 'Johnlawrenceaspden',\n",
" 'date_created': '2022-03-09'},\n",
" {'title': 'Why AI Safety? - Machine Intelligence Research Institute',\n",
" 'url': 'https://intelligence.org/why-ai-safety/',\n",
" 'author': None,\n",
" 'date_created': '2017-03-01'}]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search.results(\"The best blog post about AI safety is definitely this: \", 10)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Use Metaphor as a tool\n",
"Metaphor can be used as a tool that gets URLs that other tools such as browsing tools."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import PlayWrightBrowserToolkit\n",
"from langchain.tools.playwright.utils import (\n",
" create_async_playwright_browser,# A synchronous browser is available, though it isn't compatible with jupyter.\n",
")\n",
"\n",
"async_browser = create_async_playwright_browser()\n",
"toolkit = PlayWrightBrowserToolkit.from_browser(async_browser=async_browser)\n",
"tools = toolkit.get_tools()\n",
"\n",
"tools_by_name = {tool.name: tool for tool in tools}\n",
"print(tools_by_name.keys())\n",
"navigate_tool = tools_by_name[\"navigate_browser\"]\n",
"extract_text = tools_by_name[\"extract_text\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find a tweet about AI safety using Metaphor Search.\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"Metaphor Search Results JSON\",\n",
" \"action_input\": {\n",
" \"query\": \"interesting tweet AI safety\",\n",
" \"num_results\": 1\n",
" }\n",
"}\n",
"```\n",
"\u001b[0m{'results': [{'url': 'https://safe.ai/', 'title': 'Center for AI Safety', 'dateCreated': '2022-01-01', 'author': None, 'score': 0.18083244562149048}]}\n",
"\n",
"Observation: \u001b[36;1m\u001b[1;3m[{'title': 'Center for AI Safety', 'url': 'https://safe.ai/', 'author': None, 'date_created': '2022-01-01'}]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI need to navigate to the URL provided in the search results to find the tweet.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'I need to navigate to the URL provided in the search results to find the tweet.'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.agents import initialize_agent, AgentType\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.tools import MetaphorSearchResults\n",
"\n",
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.7)\n",
"\n",
"metaphor_tool = MetaphorSearchResults(api_wrapper=search)\n",
"\n",
"agent_chain = initialize_agent([metaphor_tool, extract_text, navigate_tool], llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",
"\n",
"agent_chain.run(\"find me an interesting tweet about AI safety using Metaphor, then tell me the first sentence in the post. Do not finish until able to retrieve the first sentence.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}