id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
9f838025c411-8 | > Finished chain.
'{"message__text": "Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]", "message__permalink": "https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629", "channel": "D04TKF5BBHU", "message__bot_profile__name": "Zapier", "message__team": "T04F8K3FZB5", "message__bot_id": "B04TRV4R74K", "message__bot_profile__deleted": "false", "message__bot_profile__app_id": "A024R9PQM", "ts_time": "2023-03-15T05:59:28Z", "message__blocks[]block_id": "p7i", "message__blocks[]elements[]elements[]type": "[[\'text\']]", "message__blocks[]elements[]type": "[\'rich_text_section\']"}'
previous
YouTubeSearchTool
next
Agents
Contents
Zapier Natural Language Actions API
Example with Agent
Example with SimpleSequentialChain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/zapier.html |
c4e4a3f3681f-0 | .ipynb
.pdf
GraphQL tool
GraphQL tool#
This Jupyter Notebook demonstrates how to use the BaseGraphQLTool component with an Agent.
GraphQL is a query language for APIs and a runtime for executing those queries against your data. GraphQL provides a complete and understandable description of the data in your API, gives clients the power to ask for exactly what they need and nothing more, makes it easier to evolve APIs over time, and enables powerful developer tools.
By including a BaseGraphQLTool in the list of tools provided to an Agent, you can grant your Agent the ability to query data from GraphQL APIs for any purposes you need.
In this example, we’ll be using the public Star Wars GraphQL API available at the following endpoint: https://swapi-graphql.netlify.app/.netlify/functions/index.
First, you need to install httpx and gql Python packages.
pip install httpx gql > /dev/null
Now, let’s create a BaseGraphQLTool instance with the specified Star Wars API endpoint and initialize an Agent with the tool.
from langchain import OpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
from langchain.utilities import GraphQLAPIWrapper
llm = OpenAI(temperature=0)
tools = load_tools(["graphql"], graphql_endpoint="https://swapi-graphql.netlify.app/.netlify/functions/index", llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
Now, we can use the Agent to run queries against the Star Wars GraphQL API. Let’s ask the Agent to list all the Star Wars films and their release dates.
graphql_fields = """allFilms {
films {
title
director
releaseDate
speciesConnection {
species {
name
classification
homeworld {
name
} | https://python.langchain.com/en/latest/modules/agents/tools/examples/graphql.html |
c4e4a3f3681f-1 | species {
name
classification
homeworld {
name
}
}
}
}
}
"""
suffix = "Search for the titles of all the stawars films stored in the graphql database that has this schema "
agent.run(suffix + graphql_fields)
> Entering new AgentExecutor chain...
I need to query the graphql database to get the titles of all the star wars films
Action: query_graphql
Action Input: query { allFilms { films { title } } }
Observation: "{\n \"allFilms\": {\n \"films\": [\n {\n \"title\": \"A New Hope\"\n },\n {\n \"title\": \"The Empire Strikes Back\"\n },\n {\n \"title\": \"Return of the Jedi\"\n },\n {\n \"title\": \"The Phantom Menace\"\n },\n {\n \"title\": \"Attack of the Clones\"\n },\n {\n \"title\": \"Revenge of the Sith\"\n }\n ]\n }\n}"
Thought: I now know the titles of all the star wars films
Final Answer: The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.
> Finished chain.
'The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.'
previous
Gradio Tools
next
HuggingFace Tools
By Harrison Chase
© Copyright 2023, Harrison Chase. | https://python.langchain.com/en/latest/modules/agents/tools/examples/graphql.html |
c4e4a3f3681f-2 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/graphql.html |
7febab29377f-0 | .ipynb
.pdf
Gradio Tools
Contents
Using a tool
Using within an agent
Gradio Tools#
There are many 1000s of Gradio apps on Hugging Face Spaces. This library puts them at the tips of your LLM’s fingers 🦾
Specifically, gradio-tools is a Python library for converting Gradio apps into tools that can be leveraged by a large language model (LLM)-based agent to complete its task. For example, an LLM could use a Gradio tool to transcribe a voice recording it finds online and then summarize it for you. Or it could use a different Gradio tool to apply OCR to a document on your Google Drive and then answer questions about it.
It’s very easy to create you own tool if you want to use a space that’s not one of the pre-built tools. Please see this section of the gradio-tools documentation for information on how to do that. All contributions are welcome!
# !pip install gradio_tools
Using a tool#
from gradio_tools.tools import StableDiffusionTool
local_file_path = StableDiffusionTool().langchain.run("Please create a photo of a dog riding a skateboard")
local_file_path
Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔
Job Status: Status.STARTING eta: None
'/Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/examples/b61c1dd9-47e2-46f1-a47c-20d27640993d/tmp4ap48vnm.jpg'
from PIL import Image
im = Image.open(local_file_path)
display(im)
Using within an agent#
from langchain.agents import initialize_agent
from langchain.llms import OpenAI | https://python.langchain.com/en/latest/modules/agents/tools/examples/gradio_tools.html |
7febab29377f-1 | from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from gradio_tools.tools import (StableDiffusionTool, ImageCaptioningTool, StableDiffusionPromptGeneratorTool,
TextToVideoTool)
from langchain.memory import ConversationBufferMemory
llm = OpenAI(temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history")
tools = [StableDiffusionTool().langchain, ImageCaptioningTool().langchain,
StableDiffusionPromptGeneratorTool().langchain, TextToVideoTool().langchain]
agent = initialize_agent(tools, llm, memory=memory, agent="conversational-react-description", verbose=True)
output = agent.run(input=("Please create a photo of a dog riding a skateboard "
"but improve my prompt prior to using an image generator."
"Please caption the generated image and create a video for it using the improved prompt."))
Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔
Loaded as API: https://taesiri-blip-2.hf.space ✔
Loaded as API: https://microsoft-promptist.hf.space ✔
Loaded as API: https://damo-vilab-modelscope-text-to-video-synthesis.hf.space ✔
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: StableDiffusionPromptGenerator
Action Input: A dog riding a skateboard
Job Status: Status.STARTING eta: None
Observation: A dog riding a skateboard, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha
Thought: Do I need to use a tool? Yes
Action: StableDiffusion | https://python.langchain.com/en/latest/modules/agents/tools/examples/gradio_tools.html |
7febab29377f-2 | Thought: Do I need to use a tool? Yes
Action: StableDiffusion
Action Input: A dog riding a skateboard, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha
Job Status: Status.STARTING eta: None
Job Status: Status.PROCESSING eta: None
Observation: /Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/examples/2e280ce4-4974-4420-8680-450825c31601/tmpfmiz2g1c.jpg
Thought: Do I need to use a tool? Yes
Action: ImageCaptioner
Action Input: /Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/examples/2e280ce4-4974-4420-8680-450825c31601/tmpfmiz2g1c.jpg
Job Status: Status.STARTING eta: None
Observation: a painting of a dog sitting on a skateboard
Thought: Do I need to use a tool? Yes
Action: TextToVideo
Action Input: a painting of a dog sitting on a skateboard
Job Status: Status.STARTING eta: None
Due to heavy traffic on this app, the prediction will take approximately 73 seconds.For faster predictions without waiting in queue, you may duplicate the space using: Client.duplicate(damo-vilab/modelscope-text-to-video-synthesis)
Job Status: Status.IN_QUEUE eta: 73.89824726581574
Due to heavy traffic on this app, the prediction will take approximately 42 seconds.For faster predictions without waiting in queue, you may duplicate the space using: Client.duplicate(damo-vilab/modelscope-text-to-video-synthesis)
Job Status: Status.IN_QUEUE eta: 42.49370198879602 | https://python.langchain.com/en/latest/modules/agents/tools/examples/gradio_tools.html |
7febab29377f-3 | Job Status: Status.IN_QUEUE eta: 42.49370198879602
Job Status: Status.IN_QUEUE eta: 21.314297944849187
Observation: /var/folders/bm/ylzhm36n075cslb9fvvbgq640000gn/T/tmp5snj_nmzf20_cb3m.mp4
Thought: Do I need to use a tool? No
AI: Here is a video of a painting of a dog sitting on a skateboard.
> Finished chain.
previous
Google Serper API
next
GraphQL tool
Contents
Using a tool
Using within an agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/gradio_tools.html |
9e1b85753294-0 | .ipynb
.pdf
IFTTT WebHooks
Contents
Creating a webhook
Configuring the “If This”
Configuring the “Then That”
Finishing up
IFTTT WebHooks#
This notebook shows how to use IFTTT Webhooks.
From https://github.com/SidU/teams-langchain-js/wiki/Connecting-IFTTT-Services.
Creating a webhook#
Go to https://ifttt.com/create
Configuring the “If This”#
Click on the “If This” button in the IFTTT interface.
Search for “Webhooks” in the search bar.
Choose the first option for “Receive a web request with a JSON payload.”
Choose an Event Name that is specific to the service you plan to connect to.
This will make it easier for you to manage the webhook URL.
For example, if you’re connecting to Spotify, you could use “Spotify” as your
Event Name.
Click the “Create Trigger” button to save your settings and create your webhook.
Configuring the “Then That”#
Tap on the “Then That” button in the IFTTT interface.
Search for the service you want to connect, such as Spotify.
Choose an action from the service, such as “Add track to a playlist”.
Configure the action by specifying the necessary details, such as the playlist name,
e.g., “Songs from AI”.
Reference the JSON Payload received by the Webhook in your action. For the Spotify
scenario, choose “{{JsonPayload}}” as your search query.
Tap the “Create Action” button to save your action settings.
Once you have finished configuring your action, click the “Finish” button to
complete the setup.
Congratulations! You have successfully connected the Webhook to the desired
service, and you’re ready to start receiving data and triggering actions 🎉 | https://python.langchain.com/en/latest/modules/agents/tools/examples/ifttt.html |
9e1b85753294-1 | service, and you’re ready to start receiving data and triggering actions 🎉
Finishing up#
To get your webhook URL go to https://ifttt.com/maker_webhooks/settings
Copy the IFTTT key value from there. The URL is of the form
https://maker.ifttt.com/use/YOUR_IFTTT_KEY. Grab the YOUR_IFTTT_KEY value.
from langchain.tools.ifttt import IFTTTWebhook
import os
key = os.environ["IFTTTKey"]
url = f"https://maker.ifttt.com/trigger/spotify/json/with/key/{key}"
tool = IFTTTWebhook(name="Spotify", description="Add a song to spotify playlist", url=url)
tool.run("taylor swift")
"Congratulations! You've fired the spotify JSON event"
previous
Human as a tool
next
Metaphor Search
Contents
Creating a webhook
Configuring the “If This”
Configuring the “Then That”
Finishing up
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/ifttt.html |
05d1d44da6ec-0 | .ipynb
.pdf
Wolfram Alpha
Wolfram Alpha#
This notebook goes over how to use the wolfram alpha component.
First, you need to set up your Wolfram Alpha developer account and get your APP ID:
Go to wolfram alpha and sign up for a developer account here
Create an app and get your APP ID
pip install wolframalpha
Then we will need to set some environment variables:
Save your APP ID into WOLFRAM_ALPHA_APPID env variable
pip install wolframalpha
import os
os.environ["WOLFRAM_ALPHA_APPID"] = ""
from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
wolfram = WolframAlphaAPIWrapper()
wolfram.run("What is 2x+5 = -3x + 7?")
'x = 2/5'
previous
Wikipedia
next
YouTubeSearchTool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/wolfram_alpha.html |
3dc541531329-0 | .ipynb
.pdf
YouTubeSearchTool
YouTubeSearchTool#
This notebook shows how to use a tool to search YouTube
Adapted from venuv/langchain_yt_tools
#! pip install youtube_search
from langchain.tools import YouTubeSearchTool
tool = YouTubeSearchTool()
tool.run("lex friedman")
"['/watch?v=VcVfceTsD0A&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=gPfriiHBBek&pp=ygUMbGV4IGZyaWVkbWFu']"
You can also specify the number of results that are returned
tool.run("lex friedman,5")
"['/watch?v=VcVfceTsD0A&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=YVJ8gTnDC4Y&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=Udh22kuLebg&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=gPfriiHBBek&pp=ygUMbGV4IGZyaWVkbWFu', '/watch?v=L_Guz73e6fw&pp=ygUMbGV4IGZyaWVkbWFu']"
previous
Wolfram Alpha
next
Zapier Natural Language Actions API
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/youtube.html |
19c273635673-0 | .ipynb
.pdf
Python REPL
Python REPL#
Sometimes, for complex calculations, rather than have an LLM generate the answer directly, it can be better to have the LLM generate code to calculate the answer, and then run that code to get the answer. In order to easily do that, we provide a simple Python REPL to execute commands in.
This interface will only return things that are printed - therefore, if you want to use it to calculate an answer, make sure to have it print out the answer.
from langchain.agents import Tool
from langchain.utilities import PythonREPL
python_repl = PythonREPL()
python_repl.run("print(1+1)")
'2\n'
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=python_repl.run
)
previous
OpenWeatherMap API
next
Requests
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/python.html |
7a96c084c9cc-0 | .ipynb
.pdf
DuckDuckGo Search
DuckDuckGo Search#
This notebook goes over how to use the duck-duck-go search component.
# !pip install duckduckgo-search
from langchain.tools import DuckDuckGoSearchRun
search = DuckDuckGoSearchRun()
search.run("Obama's first name?") | https://python.langchain.com/en/latest/modules/agents/tools/examples/ddg.html |
7a96c084c9cc-1 | 'Barack Obama, in full Barack Hussein Obama II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009-17) and the first African American to hold the office. Before winning the presidency, Obama represented Illinois in the U.S. Senate (2005-08). Barack Hussein Obama II (/ b ə ˈ r ɑː k h uː ˈ s eɪ n oʊ ˈ b ɑː m ə / bə-RAHK hoo-SAYN oh-BAH-mə; born August 4, 1961) is an American former politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, he was the first African-American president of the United States. Obama previously served as a U.S. senator representing ... Barack Obama was the first African American president of the United States (2009-17). He oversaw the recovery of the U.S. economy (from the Great Recession of 2008-09) and the enactment of landmark health care reform (the Patient Protection and Affordable Care Act ). In 2009 he was awarded the Nobel Peace Prize. His birth certificate lists his first name as Barack: That\'s how Obama has spelled his name throughout his life. His name derives from a Hebrew name which means "lightning.". The Hebrew word has been transliterated into English in various spellings, including Barak, Buraq, Burack, and Barack. Most common names of U.S. presidents 1789-2021. Published by. Aaron O\'Neill , Jun 21, 2022. The most common first name for a U.S. president is James, followed by John and then William. Six U.S ...'
previous
ChatGPT Plugins | https://python.langchain.com/en/latest/modules/agents/tools/examples/ddg.html |
7a96c084c9cc-2 | previous
ChatGPT Plugins
next
File System Tools
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/ddg.html |
7dbcc1b20010-0 | .ipynb
.pdf
Search Tools
Contents
Google Serper API Wrapper
SerpAPI
GoogleSearchAPIWrapper
SearxNG Meta Search Engine
Search Tools#
This notebook shows off usage of various search tools.
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
Google Serper API Wrapper#
First, let’s try to use the Google Serper API tool.
tools = load_tools(["google-serper"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I should look up the current weather conditions.
Action: Search
Action Input: "weather in Pomfret"
Observation: 37°F
Thought: I now know the current temperature in Pomfret.
Final Answer: The current temperature in Pomfret is 37°F.
> Finished chain.
'The current temperature in Pomfret is 37°F.'
SerpAPI#
Now, let’s use the SerpAPI tool.
tools = load_tools(["serpapi"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I need to find out what the current weather is in Pomfret.
Action: Search
Action Input: "weather in Pomfret" | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
7dbcc1b20010-1 | Action: Search
Action Input: "weather in Pomfret"
Observation: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 ...
Thought: I now know the current weather in Pomfret.
Final Answer: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.
> Finished chain.
'Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.'
GoogleSearchAPIWrapper#
Now, let’s use the official Google Search API Wrapper.
tools = load_tools(["google-search"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I should look up the current weather conditions.
Action: Google Search
Action Input: "weather in Pomfret" | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
7dbcc1b20010-2 | Action: Google Search
Action Input: "weather in Pomfret"
Observation: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Hourly Weather-Pomfret, CT. As of 12:52 am EST. Special Weather Statement +2 ... Hazardous Weather Conditions. Special Weather Statement ... Pomfret CT. Tonight ... National Digital Forecast Database Maximum Temperature Forecast. Pomfret Center Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Pomfret, CT 12 hour by hour weather forecast includes precipitation, temperatures, sky conditions, rain chance, dew-point, relative humidity, wind direction ... North Pomfret Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Today's Weather - Pomfret, CT. Dec 31, 2022 4:00 PM. Putnam MS. --. Weather forecast icon. Feels like --. Hi --. Lo --. Pomfret, CT temperature trend for the next 14 Days. Find daytime highs and nighttime lows from TheWeatherNetwork.com. Pomfret, MD Weather Forecast Date: 332 PM EST Wed Dec 28 2022. The area/counties/county of: Charles, including the cites of: St. Charles and Waldorf.
Thought: I now know the current weather conditions in Pomfret.
Final Answer: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
7dbcc1b20010-3 | > Finished AgentExecutor chain.
'Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.'
SearxNG Meta Search Engine#
Here we will be using a self hosted SearxNG meta search engine.
tools = load_tools(["searx-search"], searx_host="http://localhost:8888", llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret")
> Entering new AgentExecutor chain...
I should look up the current weather
Action: SearX Search
Action Input: "weather in Pomfret"
Observation: Mainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.
10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....
10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F.... | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
7dbcc1b20010-4 | Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.
Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’s Why We Get More Colds and Flu When It’s Cold Coast-To-Coast...
Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...
Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...
Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...
12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...
Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy... | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
7dbcc1b20010-5 | Thought: I now know the final answer
Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.
> Finished chain.
'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'
previous
SceneXplain
next
SearxNG Search API
Contents
Google Serper API Wrapper
SerpAPI
GoogleSearchAPIWrapper
SearxNG Meta Search Engine
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
c77e1bfe34cb-0 | .ipynb
.pdf
OpenWeatherMap API
Contents
Use the wrapper
Use the tool
OpenWeatherMap API#
This notebook goes over how to use the OpenWeatherMap component to fetch weather information.
First, you need to sign up for an OpenWeatherMap API key:
Go to OpenWeatherMap and sign up for an API key here
pip install pyowm
Then we will need to set some environment variables:
Save your API KEY into OPENWEATHERMAP_API_KEY env variable
Use the wrapper#
from langchain.utilities import OpenWeatherMapAPIWrapper
import os
os.environ["OPENWEATHERMAP_API_KEY"] = ""
weather = OpenWeatherMapAPIWrapper()
weather_data = weather.run("London,GB")
print(weather_data)
In London,GB, the current weather is as follows:
Detailed status: broken clouds
Wind speed: 2.57 m/s, direction: 240°
Humidity: 55%
Temperature:
- Current: 20.12°C
- High: 21.75°C
- Low: 18.68°C
- Feels like: 19.62°C
Rain: {}
Heat index: None
Cloud cover: 75%
Use the tool#
from langchain.llms import OpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
import os
os.environ["OPENAI_API_KEY"] = ""
os.environ["OPENWEATHERMAP_API_KEY"] = ""
llm = OpenAI(temperature=0)
tools = load_tools(["openweathermap-api"], llm)
agent_chain = initialize_agent(
tools=tools,
llm=llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True
) | https://python.langchain.com/en/latest/modules/agents/tools/examples/openweathermap.html |
c77e1bfe34cb-1 | agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True
)
agent_chain.run("What's the weather like in London?")
> Entering new AgentExecutor chain...
I need to find out the current weather in London.
Action: OpenWeatherMap
Action Input: London,GB
Observation: In London,GB, the current weather is as follows:
Detailed status: broken clouds
Wind speed: 2.57 m/s, direction: 240°
Humidity: 56%
Temperature:
- Current: 20.11°C
- High: 21.75°C
- Low: 18.68°C
- Feels like: 19.64°C
Rain: {}
Heat index: None
Cloud cover: 75%
Thought: I now know the current weather in London.
Final Answer: The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.
> Finished chain.
'The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.'
previous
Metaphor Search
next
Python REPL
Contents
Use the wrapper
Use the tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/openweathermap.html |
189cbc865da8-0 | .ipynb
.pdf
SearxNG Search API
Contents
Custom Parameters
Obtaining results with metadata
SearxNG Search API#
This notebook goes over how to use a self hosted SearxNG search API to search the web.
You can check this link for more informations about Searx API parameters.
import pprint
from langchain.utilities import SearxSearchWrapper
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888")
For some engines, if a direct answer is available the warpper will print the answer instead of the full list of search results. You can use the results method of the wrapper if you want to obtain all the results.
search.run("What is the capital of France")
'Paris is the capital of France, the largest country of Europe with 550 000 km2 (65 millions inhabitants). Paris has 2.234 million inhabitants end 2011. She is the core of Ile de France region (12 million people).'
Custom Parameters#
SearxNG supports up to 139 search engines. You can also customize the Searx wrapper with arbitrary named parameters that will be passed to the Searx search API . In the below example we will making a more interesting use of custom search parameters from searx search api.
In this example we will be using the engines parameters to query wikipedia
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888", k=5) # k is for max number of items
search.run("large language model ", engines=['wiki']) | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-1 | search.run("large language model ", engines=['wiki'])
'Large language models (LLMs) represent a major advancement in AI, with the promise of transforming domains through learned knowledge. LLM sizes have been increasing 10X every year for the last few years, and as these models grow in complexity and size, so do their capabilities.\n\nGPT-3 can translate language, write essays, generate computer code, and more — all with limited to no supervision. In July 2020, OpenAI unveiled GPT-3, a language model that was easily the largest known at the time. Put simply, GPT-3 is trained to predict the next word in a sentence, much like how a text message autocomplete feature works.\n\nA large language model, or LLM, is a deep learning algorithm that can recognize, summarize, translate, predict and generate text and other content based on knowledge gained from massive datasets. Large language models are among the most successful applications of transformer models.\n\nAll of today’s well-known language models—e.g., GPT-3 from OpenAI, PaLM or LaMDA from Google, Galactica or OPT from Meta, Megatron-Turing from Nvidia/Microsoft, Jurassic-1 from AI21 Labs—are...\n\nLarge language models (LLMs) such as GPT-3are increasingly being used to generate text. These tools should be used with care, since they can generate content that is biased, non-verifiable, constitutes original research, or violates copyrights.'
Passing other Searx parameters for searx like language
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888", k=1)
search.run("deep learning", language='es', engines=['wiki']) | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-2 | search.run("deep learning", language='es', engines=['wiki'])
'Aprendizaje profundo (en inglés, deep learning) es un conjunto de algoritmos de aprendizaje automático (en inglés, machine learning) que intenta modelar abstracciones de alto nivel en datos usando arquitecturas computacionales que admiten transformaciones no lineales múltiples e iterativas de datos expresados en forma matricial o tensorial. 1'
Obtaining results with metadata#
In this example we will be looking for scientific paper using the categories parameter and limiting the results to a time_range (not all engines support the time range option).
We also would like to obtain the results in a structured way including metadata. For this we will be using the results method of the wrapper.
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888")
results = search.results("Large Language Model prompt", num_results=5, categories='science', time_range='year')
pprint.pp(results)
[{'snippet': '… on natural language instructions, large language models (… the '
'prompt used to steer the model, and most effective prompts … to '
'prompt engineering, we propose Automatic Prompt …',
'title': 'Large language models are human-level prompt engineers',
'link': 'https://arxiv.org/abs/2211.01910',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Large language models (LLMs) have introduced new possibilities '
'for prototyping with AI [18]. Pre-trained on a large amount of '
'text data, models … language instructions called prompts. …',
'title': 'Promptchainer: Chaining large language model prompts through ' | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-3 | 'title': 'Promptchainer: Chaining large language model prompts through '
'visual programming',
'link': 'https://dl.acm.org/doi/abs/10.1145/3491101.3519729',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… can introspect the large prompt model. We derive the view '
'ϕ0(X) and the model h0 from T01. However, instead of fully '
'fine-tuning T0 during co-training, we focus on soft prompt '
'tuning, …',
'title': 'Co-training improves prompt-based learning for large language '
'models',
'link': 'https://proceedings.mlr.press/v162/lang22a.html',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… With the success of large language models (LLMs) of code and '
'their use as … prompt design process become important. In this '
'work, we propose a framework called Repo-Level Prompt …',
'title': 'Repository-level prompt generation for large language models of '
'code',
'link': 'https://arxiv.org/abs/2206.12839',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Figure 2 | The benefits of different components of a prompt '
'for the largest language model (Gopher), as estimated from '
'hierarchical logistic regression. Each point estimates the '
'unique …',
'title': 'Can language models learn from explanations in context?',
'link': 'https://arxiv.org/abs/2204.02329', | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-4 | 'link': 'https://arxiv.org/abs/2204.02329',
'engines': ['google scholar'],
'category': 'science'}]
Get papers from arxiv
results = search.results("Large Language Model prompt", num_results=5, engines=['arxiv'])
pprint.pp(results)
[{'snippet': 'Thanks to the advanced improvement of large pre-trained language '
'models, prompt-based fine-tuning is shown to be effective on a '
'variety of downstream tasks. Though many prompting methods have '
'been investigated, it remains unknown which type of prompts are '
'the most effective among three types of prompts (i.e., '
'human-designed prompts, schema prompts and null prompts). In '
'this work, we empirically compare the three types of prompts '
'under both few-shot and fully-supervised settings. Our '
'experimental results show that schema prompts are the most '
'effective in general. Besides, the performance gaps tend to '
'diminish when the scale of training data grows large.',
'title': 'Do Prompts Solve NLP Tasks Using Natural Language?',
'link': 'http://arxiv.org/abs/2203.00902v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Cross-prompt automated essay scoring (AES) requires the system '
'to use non target-prompt essays to award scores to a '
'target-prompt essay. Since obtaining a large quantity of '
'pre-graded essays to a particular prompt is often difficult and '
'unrealistic, the task of cross-prompt AES is vital for the '
'development of real-world AES systems, yet it remains an ' | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-5 | 'development of real-world AES systems, yet it remains an '
'under-explored area of research. Models designed for '
'prompt-specific AES rely heavily on prompt-specific knowledge '
'and perform poorly in the cross-prompt setting, whereas current '
'approaches to cross-prompt AES either require a certain quantity '
'of labelled target-prompt essays or require a large quantity of '
'unlabelled target-prompt essays to perform transfer learning in '
'a multi-step manner. To address these issues, we introduce '
'Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES. Our '
'method requires no access to labelled or unlabelled '
'target-prompt data during training and is a single-stage '
'approach. PAES is easy to apply in practice and achieves '
'state-of-the-art performance on the Automated Student Assessment '
'Prize (ASAP) dataset.',
'title': 'Prompt Agnostic Essay Scorer: A Domain Generalization Approach to '
'Cross-prompt Automated Essay Scoring',
'link': 'http://arxiv.org/abs/2008.01441v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Research on prompting has shown excellent performance with '
'little or even no supervised training across many tasks. '
'However, prompting for machine translation is still '
'under-explored in the literature. We fill this gap by offering a '
'systematic study on prompting strategies for translation, '
'examining various factors for prompt template and demonstration '
'example selection. We further explore the use of monolingual ' | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-6 | 'example selection. We further explore the use of monolingual '
'data and the feasibility of cross-lingual, cross-domain, and '
'sentence-to-document transfer learning in prompting. Extensive '
'experiments with GLM-130B (Zeng et al., 2022) as the testbed '
'show that 1) the number and the quality of prompt examples '
'matter, where using suboptimal examples degenerates translation; '
'2) several features of prompt examples, such as semantic '
'similarity, show significant Spearman correlation with their '
'prompting performance; yet, none of the correlations are strong '
'enough; 3) using pseudo parallel prompt examples constructed '
'from monolingual data via zero-shot prompting could improve '
'translation; and 4) improved performance is achievable by '
'transferring knowledge from prompt examples selected in other '
'settings. We finally provide an analysis on the model outputs '
'and discuss several problems that prompting still suffers from.',
'title': 'Prompting Large Language Model for Machine Translation: A Case '
'Study',
'link': 'http://arxiv.org/abs/2301.07069v2',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Large language models can perform new tasks in a zero-shot '
'fashion, given natural language prompts that specify the desired '
'behavior. Such prompts are typically hand engineered, but can '
'also be learned with gradient-based methods from labeled data. '
'However, it is underexplored what factors make the prompts '
'effective, especially when the prompts are natural language. In ' | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-7 | 'effective, especially when the prompts are natural language. In '
'this paper, we investigate common attributes shared by effective '
'prompts. We first propose a human readable prompt tuning method '
'(F LUENT P ROMPT) based on Langevin dynamics that incorporates a '
'fluency constraint to find a diverse distribution of effective '
'and fluent prompts. Our analysis reveals that effective prompts '
'are topically related to the task domain and calibrate the prior '
'probability of label words. Based on these findings, we also '
'propose a method for generating prompts using only unlabeled '
'data, outperforming strong baselines by an average of 7.0% '
'accuracy across three tasks.',
'title': "Toward Human Readable Prompt Tuning: Kubrick's The Shining is a "
'good movie, and a good prompt too?',
'link': 'http://arxiv.org/abs/2212.10539v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Prevailing methods for mapping large generative language models '
"to supervised tasks may fail to sufficiently probe models' novel "
'capabilities. Using GPT-3 as a case study, we show that 0-shot '
'prompts can significantly outperform few-shot prompts. We '
'suggest that the function of few-shot examples in these cases is '
'better described as locating an already learned task rather than '
'meta-learning. This analysis motivates rethinking the role of '
'prompts in controlling and evaluating powerful language models. '
'In this work, we discuss methods of prompt programming, ' | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-8 | 'In this work, we discuss methods of prompt programming, '
'emphasizing the usefulness of considering prompts through the '
'lens of natural language. We explore techniques for exploiting '
'the capacity of narratives and cultural anchors to encode '
'nuanced intentions and techniques for encouraging deconstruction '
'of a problem into components before producing a verdict. '
'Informed by this more encompassing theory of prompt programming, '
'we also introduce the idea of a metaprompt that seeds the model '
'to generate its own natural language prompts for a range of '
'tasks. Finally, we discuss how these more general methods of '
'interacting with language models can be incorporated into '
'existing and future benchmarks and practical applications.',
'title': 'Prompt Programming for Large Language Models: Beyond the Few-Shot '
'Paradigm',
'link': 'http://arxiv.org/abs/2102.07350v1',
'engines': ['arxiv'],
'category': 'science'}]
In this example we query for large language models under the it category. We then filter the results that come from github.
results = search.results("large language model", num_results = 20, categories='it')
pprint.pp(list(filter(lambda r: r['engines'][0] == 'github', results)))
[{'snippet': 'Guide to using pre-trained large language models of source code',
'title': 'Code-LMs',
'link': 'https://github.com/VHellendoorn/Code-LMs',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Dramatron uses large language models to generate coherent '
'scripts and screenplays.', | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-9 | 'scripts and screenplays.',
'title': 'dramatron',
'link': 'https://github.com/deepmind/dramatron',
'engines': ['github'],
'category': 'it'}]
We could also directly query for results from github and other source forges.
results = search.results("large language model", num_results = 20, engines=['github', 'gitlab'])
pprint.pp(results)
[{'snippet': "Implementation of 'A Watermark for Large Language Models' paper "
'by Kirchenbauer & Geiping et. al.',
'title': 'Peutlefaire / LMWatermark',
'link': 'https://gitlab.com/BrianPulfer/LMWatermark',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Guide to using pre-trained large language models of source code',
'title': 'Code-LMs',
'link': 'https://github.com/VHellendoorn/Code-LMs',
'engines': ['github'],
'category': 'it'},
{'snippet': '',
'title': 'Simen Burud / Large-scale Language Models for Conversational '
'Speech Recognition',
'link': 'https://gitlab.com/BrianPulfer',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Dramatron uses large language models to generate coherent '
'scripts and screenplays.',
'title': 'dramatron',
'link': 'https://github.com/deepmind/dramatron',
'engines': ['github'],
'category': 'it'}, | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-10 | 'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for loralib, an implementation of "LoRA: Low-Rank '
'Adaptation of Large Language Models"',
'title': 'LoRA',
'link': 'https://github.com/microsoft/LoRA',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for the paper "Evaluating Large Language Models Trained on '
'Code"',
'title': 'human-eval',
'link': 'https://github.com/openai/human-eval',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A trend starts from "Chain of Thought Prompting Elicits '
'Reasoning in Large Language Models".',
'title': 'Chain-of-ThoughtsPapers',
'link': 'https://github.com/Timothyxxx/Chain-of-ThoughtsPapers',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Mistral: A strong, northwesterly wind: Framework for transparent '
'and accessible large-scale language model training, built with '
'Hugging Face 🤗 Transformers.',
'title': 'mistral',
'link': 'https://github.com/stanford-crfm/mistral',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A prize for finding tasks that cause large language models to '
'show inverse scaling',
'title': 'prize',
'link': 'https://github.com/inverse-scaling/prize',
'engines': ['github'], | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-11 | 'engines': ['github'],
'category': 'it'},
{'snippet': 'Optimus: the first large-scale pre-trained VAE language model',
'title': 'Optimus',
'link': 'https://github.com/ChunyuanLI/Optimus',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Seminar on Large Language Models (COMP790-101 at UNC Chapel '
'Hill, Fall 2022)',
'title': 'llm-seminar',
'link': 'https://github.com/craffel/llm-seminar',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A central, open resource for data and tools related to '
'chain-of-thought reasoning in large language models. Developed @ '
'Samwald research group: https://samwald.info/',
'title': 'ThoughtSource',
'link': 'https://github.com/OpenBioLink/ThoughtSource',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A comprehensive list of papers using large language/multi-modal '
'models for Robotics/RL, including papers, codes, and related '
'websites',
'title': 'Awesome-LLM-Robotics',
'link': 'https://github.com/GT-RIPL/Awesome-LLM-Robotics',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Tools for curating biomedical training data for large-scale '
'language modeling',
'title': 'biomedical',
'link': 'https://github.com/bigscience-workshop/biomedical', | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-12 | 'link': 'https://github.com/bigscience-workshop/biomedical',
'engines': ['github'],
'category': 'it'},
{'snippet': 'ChatGPT @ Home: Large Language Model (LLM) chatbot application, '
'written by ChatGPT',
'title': 'ChatGPT-at-Home',
'link': 'https://github.com/Sentdex/ChatGPT-at-Home',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Design and Deploy Large Language Model Apps',
'title': 'dust',
'link': 'https://github.com/dust-tt/dust',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Polyglot: Large Language Models of Well-balanced Competence in '
'Multi-languages',
'title': 'polyglot',
'link': 'https://github.com/EleutherAI/polyglot',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code release for "Learning Video Representations from Large '
'Language Models"',
'title': 'LaViLa',
'link': 'https://github.com/facebookresearch/LaViLa',
'engines': ['github'],
'category': 'it'},
{'snippet': 'SmoothQuant: Accurate and Efficient Post-Training Quantization '
'for Large Language Models',
'title': 'smoothquant',
'link': 'https://github.com/mit-han-lab/smoothquant',
'engines': ['github'],
'category': 'it'}, | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
189cbc865da8-13 | 'engines': ['github'],
'category': 'it'},
{'snippet': 'This repository contains the code, data, and models of the paper '
'titled "XL-Sum: Large-Scale Multilingual Abstractive '
'Summarization for 44 Languages" published in Findings of the '
'Association for Computational Linguistics: ACL-IJCNLP 2021.',
'title': 'xl-sum',
'link': 'https://github.com/csebuetnlp/xl-sum',
'engines': ['github'],
'category': 'it'}]
previous
Search Tools
next
SerpAPI
Contents
Custom Parameters
Obtaining results with metadata
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/searx_search.html |
532f3fe57011-0 | .ipynb
.pdf
SerpAPI
Contents
Custom Parameters
SerpAPI#
This notebook goes over how to use the SerpAPI component to search the web.
from langchain.utilities import SerpAPIWrapper
search = SerpAPIWrapper()
search.run("Obama's first name?")
'Barack Hussein Obama II'
Custom Parameters#
You can also customize the SerpAPI wrapper with arbitrary parameters. For example, in the below example we will use bing instead of google.
params = {
"engine": "bing",
"gl": "us",
"hl": "en",
}
search = SerpAPIWrapper(params=params)
search.run("Obama's first name?")
'Barack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American presi…New content will be added above the current area of focus upon selectionBarack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American president of the United States. He previously served as a U.S. senator from Illinois from 2005 to 2008 and as an Illinois state senator from 1997 to 2004, and previously worked as a civil rights lawyer before entering politics.Wikipediabarackobama.com'
from langchain.agents import Tool
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl", | https://python.langchain.com/en/latest/modules/agents/tools/examples/serpapi.html |
532f3fe57011-1 | repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=search.run,
)
previous
SearxNG Search API
next
Twilio
Contents
Custom Parameters
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/serpapi.html |
2d55e5c3aa9b-0 | .ipynb
.pdf
Bing Search
Contents
Number of results
Metadata Results
Bing Search#
This notebook goes over how to use the bing search component.
First, you need to set up the proper API keys and environment variables. To set it up, follow the instructions found here.
Then we will need to set some environment variables.
import os
os.environ["BING_SUBSCRIPTION_KEY"] = ""
os.environ["BING_SEARCH_URL"] = ""
from langchain.utilities import BingSearchAPIWrapper
search = BingSearchAPIWrapper()
search.run("python") | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
2d55e5c3aa9b-1 | 'Thanks to the flexibility of <b>Python</b> and the powerful ecosystem of packages, the Azure CLI supports features such as autocompletion (in shells that support it), persistent credentials, JMESPath result parsing, lazy initialization, network-less unit tests, and more. Building an open-source and cross-platform Azure CLI with <b>Python</b> by Dan Taylor. <b>Python</b> releases by version number: Release version Release date Click for more. <b>Python</b> 3.11.1 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.10.9 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.9.16 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.8.16 Dec. 6, 2022 Download Release Notes. <b>Python</b> 3.7.16 Dec. 6, 2022 Download Release Notes. In this lesson, we will look at the += operator in <b>Python</b> and see how it works with several simple examples.. The operator ‘+=’ is a shorthand for the addition assignment operator.It adds two values and assigns the sum | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
2d55e5c3aa9b-2 | assignment operator.It adds two values and assigns the sum to a variable (left operand). W3Schools offers free online tutorials, references and exercises in all the major languages of the web. Covering popular subjects like HTML, CSS, JavaScript, <b>Python</b>, SQL, Java, and many, many more. This tutorial introduces the reader informally to the basic concepts and features of the <b>Python</b> language and system. It helps to have a <b>Python</b> interpreter handy for hands-on experience, but all examples are self-contained, so the tutorial can be read off-line as well. For a description of standard objects and modules, see The <b>Python</b> Standard ... <b>Python</b> is a general-purpose, versatile, and powerful programming language. It's a great first language because <b>Python</b> code is concise and easy to read. Whatever you want to do, <b>python</b> can do it. From web development to machine learning to data science, <b>Python</b> is the language for you. To install <b>Python</b> using the Microsoft Store: | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
2d55e5c3aa9b-3 | To install <b>Python</b> using the Microsoft Store: Go to your Start menu (lower left Windows icon), type "Microsoft Store", select the link to open the store. Once the store is open, select Search from the upper-right menu and enter "<b>Python</b>". Select which version of <b>Python</b> you would like to use from the results under Apps. Under the “<b>Python</b> Releases for Mac OS X” heading, click the link for the Latest <b>Python</b> 3 Release - <b>Python</b> 3.x.x. As of this writing, the latest version was <b>Python</b> 3.8.4. Scroll to the bottom and click macOS 64-bit installer to start the download. When the installer is finished downloading, move on to the next step. Step 2: Run the Installer' | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
2d55e5c3aa9b-4 | Number of results#
You can use the k parameter to set the number of results
search = BingSearchAPIWrapper(k=1)
search.run("python")
'Thanks to the flexibility of <b>Python</b> and the powerful ecosystem of packages, the Azure CLI supports features such as autocompletion (in shells that support it), persistent credentials, JMESPath result parsing, lazy initialization, network-less unit tests, and more. Building an open-source and cross-platform Azure CLI with <b>Python</b> by Dan Taylor.'
Metadata Results#
Run query through BingSearch and return snippet, title, and link metadata.
Snippet: The description of the result.
Title: The title of the result.
Link: The link to the result.
search = BingSearchAPIWrapper()
search.results("apples", 5)
[{'snippet': 'Lady Alice. Pink Lady <b>apples</b> aren’t the only lady in the apple family. Lady Alice <b>apples</b> were discovered growing, thanks to bees pollinating, in Washington. They are smaller and slightly more stout in appearance than other varieties. Their skin color appears to have red and yellow stripes running from stem to butt.',
'title': '25 Types of Apples - Jessica Gavin',
'link': 'https://www.jessicagavin.com/types-of-apples/'},
{'snippet': '<b>Apples</b> can do a lot for you, thanks to plant chemicals called flavonoids. And they have pectin, a fiber that breaks down in your gut. If you take off the apple’s skin before eating it, you won ...',
'title': 'Apples: Nutrition & Health Benefits - WebMD',
'link': 'https://www.webmd.com/food-recipes/benefits-apples'}, | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
2d55e5c3aa9b-5 | {'snippet': '<b>Apples</b> boast many vitamins and minerals, though not in high amounts. However, <b>apples</b> are usually a good source of vitamin C. Vitamin C. Also called ascorbic acid, this vitamin is a common ...',
'title': 'Apples 101: Nutrition Facts and Health Benefits',
'link': 'https://www.healthline.com/nutrition/foods/apples'},
{'snippet': 'Weight management. The fibers in <b>apples</b> can slow digestion, helping one to feel greater satisfaction after eating. After following three large prospective cohorts of 133,468 men and women for 24 years, researchers found that higher intakes of fiber-rich fruits with a low glycemic load, particularly <b>apples</b> and pears, were associated with the least amount of weight gain over time.',
'title': 'Apples | The Nutrition Source | Harvard T.H. Chan School of Public Health',
'link': 'https://www.hsph.harvard.edu/nutritionsource/food-features/apples/'}]
previous
Shell Tool
next
ChatGPT Plugins
Contents
Number of results
Metadata Results
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html |
675d9b297074-0 | .ipynb
.pdf
Shell Tool
Contents
Use with Agents
Shell Tool#
Giving agents access to the shell is powerful (though risky outside a sandboxed environment).
The LLM can use it to execute any shell commands. A common use case for this is letting the LLM interact with your local file system.
from langchain.tools import ShellTool
shell_tool = ShellTool()
print(shell_tool.run({"commands": ["echo 'Hello World!'", "time"]}))
Hello World!
real 0m0.000s
user 0m0.000s
sys 0m0.000s
/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning: The shell tool has no safeguards by default. Use at your own risk.
warnings.warn(
Use with Agents#
As with all tools, these can be given to an agent to accomplish more complex tasks. Let’s have the agent fetch some links from a web page.
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent
from langchain.agents import AgentType
llm = ChatOpenAI(temperature=0)
shell_tool.description = shell_tool.description + f"args {shell_tool.args}".replace("{", "{{").replace("}", "}}")
self_ask_with_search = initialize_agent([shell_tool], llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
self_ask_with_search.run("Download the langchain.com webpage and grep for all urls. Return only a sorted list of them. Be sure to use double quotes.")
> Entering new AgentExecutor chain...
Question: What is the task?
Thought: We need to download the langchain.com webpage and extract all the URLs from it. Then we need to sort the URLs and return them.
Action:
``` | https://python.langchain.com/en/latest/modules/agents/tools/examples/bash.html |
675d9b297074-1 | Action:
```
{
"action": "shell",
"action_input": {
"commands": [
"curl -s https://langchain.com | grep -o 'http[s]*://[^\" ]*' | sort"
]
}
}
```
/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning: The shell tool has no safeguards by default. Use at your own risk.
warnings.warn(
Observation: https://blog.langchain.dev/
https://discord.gg/6adMQxSpJS
https://docs.langchain.com/docs/
https://github.com/hwchase17/chat-langchain
https://github.com/hwchase17/langchain
https://github.com/hwchase17/langchainjs
https://github.com/sullivan-sean/chat-langchainjs
https://js.langchain.com/docs/
https://python.langchain.com/en/latest/
https://twitter.com/langchainai
Thought:The URLs have been successfully extracted and sorted. We can return the list of URLs as the final answer.
Final Answer: ["https://blog.langchain.dev/", "https://discord.gg/6adMQxSpJS", "https://docs.langchain.com/docs/", "https://github.com/hwchase17/chat-langchain", "https://github.com/hwchase17/langchain", "https://github.com/hwchase17/langchainjs", "https://github.com/sullivan-sean/chat-langchainjs", "https://js.langchain.com/docs/", "https://python.langchain.com/en/latest/", "https://twitter.com/langchainai"]
> Finished chain. | https://python.langchain.com/en/latest/modules/agents/tools/examples/bash.html |
675d9b297074-2 | > Finished chain.
'["https://blog.langchain.dev/", "https://discord.gg/6adMQxSpJS", "https://docs.langchain.com/docs/", "https://github.com/hwchase17/chat-langchain", "https://github.com/hwchase17/langchain", "https://github.com/hwchase17/langchainjs", "https://github.com/sullivan-sean/chat-langchainjs", "https://js.langchain.com/docs/", "https://python.langchain.com/en/latest/", "https://twitter.com/langchainai"]'
previous
AWS Lambda API
next
Bing Search
Contents
Use with Agents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/bash.html |
8c46ab3a65fe-0 | .ipynb
.pdf
Wikipedia
Wikipedia#
Wikipedia is a multilingual free online encyclopedia written and maintained by a community of volunteers, known as Wikipedians, through open collaboration and using a wiki-based editing system called MediaWiki. Wikipedia is the largest and most-read reference work in history.
First, you need to install wikipedia python package.
!pip install wikipedia
from langchain.utilities import WikipediaAPIWrapper
wikipedia = WikipediaAPIWrapper()
wikipedia.run('HUNTER X HUNTER') | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-1 | 'Page: Hunter × Hunter\nSummary: Hunter × Hunter (stylized as HUNTER×HUNTER and pronounced "hunter hunter") is a Japanese manga series written and illustrated by Yoshihiro Togashi. It has been serialized in Shueisha\'s shōnen manga magazine Weekly Shōnen Jump since March 1998, although the manga has frequently gone on extended hiatuses since 2006. Its chapters have been collected in 37 tankōbon volumes as of November 2022. The story focuses on a young boy named Gon Freecss who discovers that his father, who left him at a young age, is actually a world-renowned Hunter, a licensed professional who specializes in fantastical pursuits such as locating rare or unidentified animal species, treasure hunting, surveying unexplored enclaves, or hunting down lawless individuals. Gon departs on a journey to become a Hunter and eventually find his father. Along the way, Gon meets various other Hunters and encounters the paranormal.\nHunter × Hunter was adapted into a 62-episode | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-2 | × Hunter was adapted into a 62-episode anime television series produced by Nippon Animation and directed by Kazuhiro Furuhashi, which ran on Fuji Television from October 1999 to March 2001. Three separate original video animations (OVAs) totaling 30 episodes were subsequently produced by Nippon Animation and released in Japan from 2002 to 2004. A second anime television series by Madhouse aired on Nippon Television from October 2011 to September 2014, totaling 148 episodes, with two animated theatrical films released in 2013. There are also numerous audio albums, video games, musicals, and other media based on Hunter × Hunter.\nThe manga has been translated into English and released in North America by Viz Media since April 2005. Both television series have been also licensed by Viz Media, with the first series having aired on the Funimation Channel in 2009 and the second series broadcast on Adult Swim\'s Toonami programming block from April 2016 to June 2019.\nHunter × Hunter has been a huge critical and financial success | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-3 | × Hunter has been a huge critical and financial success and has become one of the best-selling manga series of all time, having over 84 million copies in circulation by July 2022.\n\nPage: Hunter × Hunter (2011 TV series)\nSummary: Hunter × Hunter is an anime television series that aired from 2011 to 2014 based on Yoshihiro Togashi\'s manga series Hunter × Hunter. The story begins with a young boy named Gon Freecss, who one day discovers that the father who he thought was dead, is in fact alive and well. He learns that his father, Ging, is a legendary "Hunter", an individual who has proven themselves an elite member of humanity. Despite the fact that Ging left his son with his relatives in order to pursue his own dreams, Gon becomes determined to follow in his father\'s footsteps, pass the rigorous "Hunter Examination", and eventually find his father to become a Hunter in his own right.\nThis new Hunter × Hunter anime was announced on July | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-4 | new Hunter × Hunter anime was announced on July 24, 2011. It is a complete reboot of the anime adaptation starting from the beginning of the manga, with no connections to the first anime from 1999. Produced by Nippon TV, VAP, Shueisha and Madhouse, the series is directed by Hiroshi Kōjina, with Atsushi Maekawa and Tsutomu Kamishiro handling series composition, Takahiro Yoshimatsu designing the characters and Yoshihisa Hirano composing the music. Instead of having the old cast reprise their roles for the new adaptation, the series features an entirely new cast to voice the characters. The new series premiered airing weekly on Nippon TV and the nationwide Nippon News Network from October 2, 2011. The series started to be collected in both DVD and Blu-ray format on January 25, 2012. Viz Media has licensed the anime for a DVD/Blu-ray release in North America with an English dub. On television, the series began airing on Adult | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-5 | On television, the series began airing on Adult Swim\'s Toonami programming block on April 17, 2016, and ended on June 23, 2019.The anime series\' opening theme is alternated between the song "Departure!" and an alternate version titled "Departure! -Second Version-" both sung by Galneryus\' vocalist Masatoshi Ono. Five pieces of music were used as the ending theme; "Just Awake" by the Japanese band Fear, and Loathing in Las Vegas in episodes 1 to 26, "Hunting for Your Dream" by Galneryus in episodes 27 to 58, "Reason" sung by Japanese duo Yuzu in episodes 59 to 75, "Nagareboshi Kirari" also sung by Yuzu from episode 76 to 98, which was originally from the anime film adaptation, Hunter × Hunter: Phantom Rouge, and "Hyōri Ittai" by Yuzu featuring Hyadain from episode 99 to 146, which was also used in the film Hunter × Hunter: The Last Mission. The background music and soundtrack for the series was composed | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-6 | The background music and soundtrack for the series was composed by Yoshihisa Hirano.\n\n\n\nPage: List of Hunter × Hunter characters\nSummary: The Hunter × Hunter manga series, created by Yoshihiro Togashi, features an extensive cast of characters. It takes place in a fictional universe where licensed specialists known as Hunters travel the world taking on special jobs ranging from treasure hunting to assassination. The story initially focuses on Gon Freecss and his quest to become a Hunter in order to find his father, Ging, who is himself a famous Hunter. On the way, Gon meets and becomes close friends with Killua Zoldyck, Kurapika and Leorio Paradinight.\nAlthough most characters are human, most possess superhuman strength and/or supernatural abilities due to Nen, the ability to control one\'s own life energy or aura. The world of the series also includes fantastical beasts such as the Chimera Ants or the Five great calamities.' | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
8c46ab3a65fe-7 | previous
Twilio
next
Wolfram Alpha
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
f792ebff78cc-0 | .ipynb
.pdf
File System Tools
Contents
The FileManagementToolkit
Selecting File System Tools
File System Tools#
LangChain provides tools for interacting with a local file system out of the box. This notebook walks through some of them.
Note: these tools are not recommended for use outside a sandboxed environment!
First, we’ll import the tools.
from langchain.tools.file_management import (
ReadFileTool,
CopyFileTool,
DeleteFileTool,
MoveFileTool,
WriteFileTool,
ListDirectoryTool,
)
from langchain.agents.agent_toolkits import FileManagementToolkit
from tempfile import TemporaryDirectory
# We'll make a temporary directory to avoid clutter
working_directory = TemporaryDirectory()
The FileManagementToolkit#
If you want to provide all the file tooling to your agent, it’s easy to do so with the toolkit. We’ll pass the temporary directory in as a root directory as a workspace for the LLM.
It’s recommended to always pass in a root directory, since without one, it’s easy for the LLM to pollute the working directory, and without one, there isn’t any validation against
straightforward prompt injection.
toolkit = FileManagementToolkit(root_dir=str(working_directory.name)) # If you don't provide a root_dir, operations will default to the current working directory
toolkit.get_tools() | https://python.langchain.com/en/latest/modules/agents/tools/examples/filesystem.html |
f792ebff78cc-1 | toolkit.get_tools()
[CopyFileTool(name='copy_file', description='Create a copy of a file in a specified location', args_schema=<class 'langchain.tools.file_management.copy.FileCopyInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
DeleteFileTool(name='file_delete', description='Delete a file', args_schema=<class 'langchain.tools.file_management.delete.FileDeleteInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
FileSearchTool(name='file_search', description='Recursively search for files in a subdirectory that match the regex pattern', args_schema=<class 'langchain.tools.file_management.file_search.FileSearchInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'), | https://python.langchain.com/en/latest/modules/agents/tools/examples/filesystem.html |
f792ebff78cc-2 | MoveFileTool(name='move_file', description='Move or rename a file from one location to another', args_schema=<class 'langchain.tools.file_management.move.FileMoveInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')] | https://python.langchain.com/en/latest/modules/agents/tools/examples/filesystem.html |
f792ebff78cc-3 | Selecting File System Tools#
If you only want to select certain tools, you can pass them in as arguments when initializing the toolkit, or you can individually initialize the desired tools.
tools = FileManagementToolkit(root_dir=str(working_directory.name), selected_tools=["read_file", "write_file", "list_directory"]).get_tools()
tools
[ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')]
read_tool, write_tool, list_tool = tools
write_tool.run({"file_path": "example.txt", "text": "Hello World!"}) | https://python.langchain.com/en/latest/modules/agents/tools/examples/filesystem.html |
f792ebff78cc-4 | write_tool.run({"file_path": "example.txt", "text": "Hello World!"})
'File written successfully to example.txt.'
# List files in the working directory
list_tool.run({})
'example.txt'
previous
DuckDuckGo Search
next
Google Places
Contents
The FileManagementToolkit
Selecting File System Tools
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/filesystem.html |
54783263fc0c-0 | .ipynb
.pdf
Requests
Contents
Inside the tool
Requests#
The web contains a lot of information that LLMs do not have access to. In order to easily let LLMs interact with that information, we provide a wrapper around the Python Requests module that takes in a URL and fetches data from that URL.
from langchain.agents import load_tools
requests_tools = load_tools(["requests_all"])
requests_tools
[RequestsGetTool(name='requests_get', description='A portal to the internet. Use this when you need to get specific content from a website. Input should be a url (i.e. https://www.google.com). The output will be the text response of the GET request.', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, requests_wrapper=TextRequestsWrapper(headers=None, aiosession=None)),
RequestsPostTool(name='requests_post', description='Use this when you want to POST to a website.\n Input should be a json string with two keys: "url" and "data".\n The value of "url" should be a string, and the value of "data" should be a dictionary of \n key-value pairs you want to POST to the url.\n Be careful to always use double quotes for strings in the json string\n The output will be the text response of the POST request.\n ', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, requests_wrapper=TextRequestsWrapper(headers=None, aiosession=None)), | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-1 | RequestsPatchTool(name='requests_patch', description='Use this when you want to PATCH to a website.\n Input should be a json string with two keys: "url" and "data".\n The value of "url" should be a string, and the value of "data" should be a dictionary of \n key-value pairs you want to PATCH to the url.\n Be careful to always use double quotes for strings in the json string\n The output will be the text response of the PATCH request.\n ', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, requests_wrapper=TextRequestsWrapper(headers=None, aiosession=None)),
RequestsPutTool(name='requests_put', description='Use this when you want to PUT to a website.\n Input should be a json string with two keys: "url" and "data".\n The value of "url" should be a string, and the value of "data" should be a dictionary of \n key-value pairs you want to PUT to the url.\n Be careful to always use double quotes for strings in the json string.\n The output will be the text response of the PUT request.\n ', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, requests_wrapper=TextRequestsWrapper(headers=None, aiosession=None)),
RequestsDeleteTool(name='requests_delete', description='A portal to the internet. Use this when you need to make a DELETE request to a URL. Input should be a specific url, and the output will be the text response of the DELETE request.', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, requests_wrapper=TextRequestsWrapper(headers=None, aiosession=None))]
Inside the tool#
Each requests tool contains a requests wrapper. You can work with these wrappers directly below | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-2 | Each requests tool contains a requests wrapper. You can work with these wrappers directly below
# Each tool wrapps a requests wrapper
requests_tools[0].requests_wrapper
TextRequestsWrapper(headers=None, aiosession=None)
from langchain.utilities import TextRequestsWrapper
requests = TextRequestsWrapper()
requests.get("https://www.google.com") | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-3 | '<!doctype html><html itemscope="" itemtype="http://schema.org/WebPage" lang="en"><head><meta content="Search the world\'s information, including webpages, images, videos and more. Google has many special features to help you find exactly what you\'re looking for." name="description"><meta content="noodp" name="robots"><meta content="text/html; charset=UTF-8" http-equiv="Content-Type"><meta content="/images/branding/googleg/1x/googleg_standard_color_128dp.png" itemprop="image"><title>Google</title><script | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-4 | nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google={kEI:\'TA9QZOa5EdTakPIPuIad-Ac\',kEXPI:\'0,1359409,6059,206,4804,2316,383,246,5,1129120,1197768,626,380097,16111,28687,22431,1361,12319,17581,4997,13228,37471,7692,2891,3926,213,7615,606,50058,8228,17728,432,3,346,1244,1,16920,2648,4,1528,2304,29062,9871,3194,13658,2980,1457,16786,5803,2554,4094,7596,1,42154,2,14022,2373,342,23024,6699,31123 | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-5 | 342,23024,6699,31123,4568,6258,23418,1252,5835,14967,4333,4239,3245,445,2,2,1,26632,239,7916,7321,60,2,3,15965,872,7830,1796,10008,7,1922,9779,36154,6305,2007,17765,427,20136,14,82,2730,184,13600,3692,109,2412,1548,4308,3785,15175,3888,1515,3030,5628,478,4,9706,1804,7734,2738,1853,1032,9480,2995,576,1041,5648,3722,2058,3048,2130,2365,662,476,958,87,111,5807,2,975,1167,891,3580,1439,1128,7343,426,2 | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-6 | 1439,1128,7343,426,249,517,95,1102,14,696,1270,750,400,2208,274,2776,164,89,119,204,139,129,1710,2505,320,3,631,439,2,300,1645,172,1783,784,169,642,329,401,50,479,614,238,757,535,717,102,2,739,738,44,232,22,442,961,45,214,383,567,500,487,151,120,256,253,179,673,2,102,2,10,535,123,135,1685,5206695,190,2,20,50,198,5994221,2804424,3311,141,795,19735,1,1,346,5008,7,13,10,24,31,2,39,1,5,1,16,7,2,41,247 | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-7 | ,1,5,1,16,7,2,41,247,4,9,7,9,15,4,4,121,24,23944834,4042142,1964,16672,2894,6250,15739,1726,647,409,837,1411438,146986,23612960,7,84,93,33,101,816,57,532,163,1,441,86,1,951,73,31,2,345,178,243,472,2,148,962,455,167,178,29,702,1856,288,292,805,93,137,68,416,177,292,399,55,95,2566\',kBL:\'hw1A\',kOPI:89978449};google.sn=\'webhp\';google.kHL=\'en\';})();(function(){\nvar | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-8 | h=this||self;function l(){return void 0!==window.google&&void 0!==window.google.kOPI&&0!==window.google.kOPI?window.google.kOPI:null};var m,n=[];function p(a){for(var b;a&&(!a.getAttribute||!(b=a.getAttribute("eid")));)a=a.parentNode;return b||m}function q(a){for(var b=null;a&&(!a.getAttribute||!(b=a.getAttribute("leid")));)a=a.parentNode;return b}function r(a){/^http:/i.test(a)&&"https:"===window.location.protocol&&(google.ml&&google.ml(Error("a"),!1,{src:a,glmm:1}),a="");return a}\nfunction t(a,b,c,d,k){var e="";-1===b.search("&ei=")&&(e="&ei="+p(d),-1===b.search("&lei=")&&(d=q(d))&&(e+="&lei="+d));d="";var g=-1===b.search("&cshid=")&&"slh"!==a,f=[];f.push(["zx",Date.now().toString()]);h._cshid&&g&&f.push(["cshid",h._cshid]);c=c();null!=c&&f.push(["opi",c.toString()]);for(c=0;c<f.length;c++){if(0===c||0<c)d+="&";d+=f[c][0]+"="+f[c][1]}return"/"+(k||"gen_204")+"?atyp=i&ct="+String(a)+"&cad="+(b+e+d)};m=google.kEI;google.getEI=p;google.getLEI=q;google.ml=function(){return null};google.log=function(a,b,c,d,k,e){e=void | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-9 | null};google.log=function(a,b,c,d,k,e){e=void 0===e?l:e;c||(c=t(a,b,e,d,k));if(c=r(c)){a=new Image;var g=n.length;n[g]=a;a.onerror=a.onload=a.onabort=function(){delete n[g]};a.src=c}};google.logUrl=function(a,b){b=void 0===b?l:b;return t("",a,b)};}).call(this);(function(){google.y={};google.sy=[];google.x=function(a,b){if(a)var c=a.id;else{do c=Math.random();while(google.y[c])}google.y[c]=[a,b];return!1};google.sx=function(a){google.sy.push(a)};google.lm=[];google.plm=function(a){google.lm.push.apply(google.lm,a)};google.lq=[];google.load=function(a,b,c){google.lq.push([[a],b,c])};google.loadAll=function(a,b){google.lq.push([a,b])};google.bx=!1;google.lx=function(){};}).call(this);google.f={};(function(){\ndocument.documentElement.addEventListener("submit",function(b){var a;if(a=b.target){var c=a.getAttribute("data-submitfalse");a="1"===c||"q"===c&&!a.elements.q.value?!0:!1}else a=!1;a&&(b.preventDefault(),b.stopPropagation())},!0);document.documentElement.addEventListener("click",function(b){var a;a:{for(a=b.target;a&&a!==document.documentElement;a=a.parentElement)if("A"===a.tagName){a="1"===a.getAttribute("data-nohref");break | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-10 | a}a=!1}a&&b.preventDefault()},!0);}).call(this);</script><style>#gbar,#guser{font-size:13px;padding-top:1px !important;}#gbar{height:22px}#guser{padding-bottom:7px !important;text-align:right}.gbh,.gbd{border-top:1px solid #c9d7f1;font-size:1px}.gbh{height:0;position:absolute;top:24px;width:100%}@media all{.gb1{height:22px;margin-right:.5em;vertical-align:top}#gbar{float:left}}a.gb1,a.gb4{text-decoration:underline !important}a.gb1,a.gb4{color:#00c !important}.gbi .gb4{color:#dd8e27 !important}.gbf .gb4{color:#900 !important}\n</style><style>body,td,a,p,.h{font-family:arial,sans-serif}body{margin:0;overflow-y:scroll}#gog{padding:3px 8px 0}td{line-height:.8em}.gac_m td{line-height:17px}form{margin-bottom:20px}.h{color:#1558d6}em{font-weight:bold;font-style:normal}.lst{height:25px;width:496px}.gsfi,.lst{font:18px arial,sans-serif}.gsfs{font:17px arial,sans-serif}.ds{display:inline-box;display:inline-block;margin:3px 0 4px;margin-left:4px}input{font-family:inherit}body{background:#fff;color:#000}a{color:#4b11a8;text-decoration:none}a:hover,a:active{text-decoration:underline}.fl | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-11 | a{color:#1558d6}a:visited{color:#4b11a8}.sblc{padding-top:5px}.sblc a{display:block;margin:2px 0;margin-left:13px;font-size:11px}.lsbb{background:#f8f9fa;border:solid 1px;border-color:#dadce0 #70757a #70757a #dadce0;height:30px}.lsbb{display:block}#WqQANb a{display:inline-block;margin:0 12px}.lsb{background:url(/images/nav_logo229.png) 0 -261px repeat-x;border:none;color:#000;cursor:pointer;height:30px;margin:0;outline:0;font:15px arial,sans-serif;vertical-align:top}.lsb:active{background:#dadce0}.lst:focus{outline:none}</style><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google.erd={jsr:1,bv:1785,de:true};\nvar h=this||self;var k,l=null!=(k=h.mei)?k:1,n,p=null!=(n=h.sdo)?n:!0,q=0,r,t=google.erd,v=t.jsr;google.ml=function(a,b,d,m,e){e=void 0===e?2:e;b&&(r=a&&a.message);if(google.dl)return google.dl(a,e,d),null;if(0>v){window.console&&console.error(a,d);if(-2===v)throw a;b=!1}else b=!a||!a.message||"Error loading script"===a.message||q>=l&&!m?!1:!0;if(!b)return null;q++;d=d||{};b=encodeURIComponent;var | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-12 | null;q++;d=d||{};b=encodeURIComponent;var c="/gen_204?atyp=i&ei="+b(google.kEI);google.kEXPI&&(c+="&jexpid="+b(google.kEXPI));c+="&srcpg="+b(google.sn)+"&jsr="+b(t.jsr)+"&bver="+b(t.bv);var f=a.lineNumber;void 0!==f&&(c+="&line="+f);var g=\na.fileName;g&&(0<g.indexOf("-extension:/")&&(e=3),c+="&script="+b(g),f&&g===window.location.href&&(f=document.documentElement.outerHTML.split("\\n")[f],c+="&cad="+b(f?f.substring(0,300):"No script found.")));c+="&jsel="+e;for(var u in d)c+="&",c+=b(u),c+="=",c+=b(d[u]);c=c+"&emsg="+b(a.name+": "+a.message);c=c+"&jsst="+b(a.stack||"N/A");12288<=c.length&&(c=c.substr(0,12288));a=c;m||google.log(0,"",a);return a};window.onerror=function(a,b,d,m,e){r!==a&&(a=e instanceof Error?e:Error(a),void 0===d||"lineNumber"in a||(a.lineNumber=d),void 0===b||"fileName"in a||(a.fileName=b),google.ml(a,!1,void 0,!1,"SyntaxError"===a.name||"SyntaxError"===a.message.substring(0,11)||-1!==a.message.indexOf("Script error")?3:0));r=null;p&&q>=l&&(window.onerror=null)};})();</script></head><body bgcolor="#fff"><script | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-13 | bgcolor="#fff"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var src=\'/images/nav_logo229.png\';var iesg=false;document.body.onload = function(){window.n && window.n();if (document.images){new Image().src=src;}\nif (!iesg){document.f&&document.f.q.focus();document.gbqf&&document.gbqf.q.focus();}\n}\n})();</script><div id="mngb"><div id=gbar><nobr><b class=gb1>Search</b> <a class=gb1 href="https://www.google.com/imghp?hl=en&tab=wi">Images</a> <a class=gb1 href="https://maps.google.com/maps?hl=en&tab=wl">Maps</a> <a class=gb1 href="https://play.google.com/?hl=en&tab=w8">Play</a> <a class=gb1 href="https://www.youtube.com/?tab=w1">YouTube</a> <a class=gb1 href="https://news.google.com/?tab=wn">News</a> <a class=gb1 href="https://mail.google.com/mail/?tab=wm">Gmail</a> <a class=gb1 href="https://drive.google.com/?tab=wo">Drive</a> <a class=gb1 style="text-decoration:none" href="https://www.google.com/intl/en/about/products?tab=wh"><u>More</u> »</a></nobr></div><div id=guser width=100%><nobr><span id=gbn class=gbi></span><span id=gbf | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-14 | id=gbn class=gbi></span><span id=gbf class=gbf></span><span id=gbe></span><a href="http://www.google.com/history/optout?hl=en" class=gb4>Web History</a> | <a href="/preferences?hl=en" class=gb4>Settings</a> | <a target=_top id=gb_70 href="https://accounts.google.com/ServiceLogin?hl=en&passive=true&continue=https://www.google.com/&ec=GAZAAQ" class=gb4>Sign in</a></nobr></div><div class=gbh style=left:0></div><div class=gbh style=right:0></div></div><center><br clear="all" id="lgpd"><div id="lga"><img alt="Google" height="92" src="/images/branding/googlelogo/1x/googlelogo_white_background_color_272x92dp.png" style="padding:28px 0 14px" width="272" id="hplogo"><br><br></div><form action="/search" name="f"><table cellpadding="0" cellspacing="0"><tr valign="top"><td width="25%"> </td><td align="center" nowrap=""><input name="ie" value="ISO-8859-1" type="hidden"><input value="en" name="hl" type="hidden"><input name="source" type="hidden" value="hp"><input name="biw" type="hidden"><input name="bih" type="hidden"><div class="ds" | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-15 | name="bih" type="hidden"><div class="ds" style="height:32px;margin:4px 0"><input class="lst" style="margin:0;padding:5px 8px 0 6px;vertical-align:top;color:#000" autocomplete="off" value="" title="Google Search" maxlength="2048" name="q" size="57"></div><br style="line-height:0"><span class="ds"><span class="lsbb"><input class="lsb" value="Google Search" name="btnG" type="submit"></span></span><span class="ds"><span class="lsbb"><input class="lsb" id="tsuid_1" value="I\'m Feeling Lucky" name="btnI" type="submit"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var id=\'tsuid_1\';document.getElementById(id).onclick = function(){if (this.form.q.value){this.checked = 1;if (this.form.iflsig)this.form.iflsig.disabled = false;}\nelse top.location=\'/doodles/\';};})();</script><input value="AOEireoAAAAAZFAdXGKCXWBK5dlWxPhh8hNPQz1s9YT6" name="iflsig" type="hidden"></span></span></td><td class="fl sblc" align="left" nowrap="" width="25%"><a href="/advanced_search?hl=en&authuser=0">Advanced search</a></td></tr></table><input id="gbv" | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-16 | search</a></td></tr></table><input id="gbv" name="gbv" type="hidden" value="1"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var a,b="1";if(document&&document.getElementById)if("undefined"!=typeof XMLHttpRequest)b="2";else if("undefined"!=typeof ActiveXObject){var c,d,e=["MSXML2.XMLHTTP.6.0","MSXML2.XMLHTTP.3.0","MSXML2.XMLHTTP","Microsoft.XMLHTTP"];for(c=0;d=e[c++];)try{new ActiveXObject(d),b="2"}catch(h){}}a=b;if("2"==a&&-1==location.search.indexOf("&gbv=2")){var f=google.gbvu,g=document.getElementById("gbv");g&&(g.value=a);f&&window.setTimeout(function(){location.href=f},0)};}).call(this);</script></form><div id="gac_scont"></div><div style="font-size:83%;min-height:3.5em"><br><div id="prm"><style>.szppmdbYutt__middle-slot-promo{font-size:small;margin-bottom:32px}.szppmdbYutt__middle-slot-promo a.ZIeIlb{display:inline-block;text-decoration:none}.szppmdbYutt__middle-slot-promo img{border:none;margin-right:5px;vertical-align:middle}</style><div class="szppmdbYutt__middle-slot-promo" data-ved="0ahUKEwjmj7fr6dT-AhVULUQIHThDB38QnIcBCAQ"><a class="NKcBbd" | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-17 | class="NKcBbd" href="https://www.google.com/url?q=https://blog.google/outreach-initiatives/diversity/asian-pacific-american-heritage-month-2023/%3Futm_source%3Dhpp%26utm_medium%3Downed%26utm_campaign%3Dapahm&source=hpp&id=19035152&ct=3&usg=AOvVaw1zrN82vzhoWl4hz1zZ4gLp&sa=X&ved=0ahUKEwjmj7fr6dT-AhVULUQIHThDB38Q8IcBCAU" rel="nofollow">Celebrate Asian Pacific American Heritage Month with Google</a></div></div></div><span id="footer"><div style="font-size:10pt"><div style="margin:19px auto;text-align:center" id="WqQANb"><a href="/intl/en/ads/">Advertising</a><a href="/services/">Business Solutions</a><a href="/intl/en/about.html">About Google</a></div></div><p style="font-size:8pt;color:#70757a">© 2023 - <a href="/intl/en/policies/privacy/">Privacy</a> - <a href="/intl/en/policies/terms/">Terms</a></p></span></center><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google.cdo={height:757,width:1440};(function(){var a=window.innerWidth,b=window.innerHeight;if(!a||!b){var | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-18 | a=window.innerWidth,b=window.innerHeight;if(!a||!b){var c=window.document,d="CSS1Compat"==c.compatMode?c.documentElement:c.body;a=d.clientWidth;b=d.clientHeight}a&&b&&(a!=google.cdo.width||b!=google.cdo.height)&&google.log("","","/client_204?&atyp=i&biw="+a+"&bih="+b+"&ei="+google.kEI);}).call(this);})();</script> <script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){google.xjs={ck:\'xjs.hp.vUsZk7fd8do.L.X.O\',cs:\'ACT90oF8ktm8JGoaZ23megDhHoJku7YaGw\',excm:[]};})();</script> <script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var u=\'/xjs/_/js/k\\x3dxjs.hp.en.q0lHXBfs9JY.O/am\\x3dAAAA6AQAUABgAQ/d\\x3d1/ed\\x3d1/rs\\x3dACT90oE3ek6-fjkab6CsTH0wUEUUPhnExg/m\\x3dsb_he,d\';var amd=0;\nvar e=this||self,f=function(c){return c};var h;var n=function(c,g){this.g=g===l?c:""};n.prototype.toString=function(){return this.g+""};var l={};\nfunction p(){var c=u,g=function(){};google.lx=google.stvsc?g:function(){google.timers&&google.timers.load&&google.tick&&google.tick("load","xjsls");var | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-19 | a=document;var b="SCRIPT";"application/xhtml+xml"===a.contentType&&(b=b.toLowerCase());b=a.createElement(b);a=null===c?"null":void 0===c?"undefined":c;if(void 0===h){var d=null;var m=e.trustedTypes;if(m&&m.createPolicy){try{d=m.createPolicy("goog#html",{createHTML:f,createScript:f,createScriptURL:f})}catch(r){e.console&&e.console.error(r.message)}h=\nd}else h=d}a=(d=h)?d.createScriptURL(a):a;a=new n(a,l);b.src=a instanceof n&&a.constructor===n?a.g:"type_error:TrustedResourceUrl";var k,q;(k=(a=null==(q=(k=(b.ownerDocument&&b.ownerDocument.defaultView||window).document).querySelector)?void 0:q.call(k,"script[nonce]"))?a.nonce||a.getAttribute("nonce")||"":"")&&b.setAttribute("nonce",k);document.body.appendChild(b);google.psa=!0;google.lx=g};google.bx||google.lx()};google.xjsu=u;e._F_jsUrl=u;setTimeout(function(){0<amd?google.caft(function(){return p()},amd):p()},0);})();window._ = window._ || {};window._DumpException = _._DumpException = function(e){throw e;};window._s = window._s || {};_s._DumpException = _._DumpException;window._qs = window._qs || {};_qs._DumpException = _._DumpException;function | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-20 | || {};_qs._DumpException = _._DumpException;function _F_installCss(c){}\n(function(){google.jl={blt:\'none\',chnk:0,dw:false,dwu:true,emtn:0,end:0,ico:false,ikb:0,ine:false,injs:\'none\',injt:0,injth:0,injv2:false,lls:\'default\',pdt:0,rep:0,snet:true,strt:0,ubm:false,uwp:true};})();(function(){var pmc=\'{\\x22d\\x22:{},\\x22sb_he\\x22:{\\x22agen\\x22:true,\\x22cgen\\x22:true,\\x22client\\x22:\\x22heirloom-hp\\x22,\\x22dh\\x22:true,\\x22ds\\x22:\\x22\\x22,\\x22fl\\x22:true,\\x22host\\x22:\\x22google.com\\x22,\\x22jsonp\\x22:true,\\x22msgs\\x22:{\\x22cibl\\x22:\\x22Clear Search\\x22,\\x22dym\\x22:\\x22Did you mean:\\x22,\\x22lcky\\x22:\\x22I\\\\u0026#39;m Feeling Lucky\\x22,\\x22lml\\x22:\\x22Learn more\\x22,\\x22psrc\\x22:\\x22This search was removed from your \\\\u003Ca href\\x3d\\\\\\x22/history\\\\\\x22\\\\u003EWeb | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-21 | href\\x3d\\\\\\x22/history\\\\\\x22\\\\u003EWeb History\\\\u003C/a\\\\u003E\\x22,\\x22psrl\\x22:\\x22Remove\\x22,\\x22sbit\\x22:\\x22Search by image\\x22,\\x22srch\\x22:\\x22Google Search\\x22},\\x22ovr\\x22:{},\\x22pq\\x22:\\x22\\x22,\\x22rfs\\x22:[],\\x22sbas\\x22:\\x220 3px 8px 0 rgba(0,0,0,0.2),0 0 0 1px rgba(0,0,0,0.08)\\x22,\\x22stok\\x22:\\x22C3TIBpTor6RHJfEIn2nbidnhv50\\x22}}\';google.pmc=JSON.parse(pmc);})();</script> </body></html>' | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
54783263fc0c-22 | previous
Python REPL
next
SceneXplain
Contents
Inside the tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
550b9f857c5a-0 | .ipynb
.pdf
HuggingFace Tools
HuggingFace Tools#
Huggingface Tools supporting text I/O can be
loaded directly using the load_huggingface_tool function.
# Requires transformers>=4.29.0 and huggingface_hub>=0.14.1
!pip install --upgrade transformers huggingface_hub > /dev/null
from langchain.agents import load_huggingface_tool
tool = load_huggingface_tool("lysandre/hf-model-downloads")
print(f"{tool.name}: {tool.description}")
model_download_counter: This is a tool that returns the most downloaded model of a given task on the Hugging Face Hub. It takes the name of the category (such as text-classification, depth-estimation, etc), and returns the name of the checkpoint
tool.run("text-classification")
'facebook/bart-large-mnli'
previous
GraphQL tool
next
Human as a tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/tools/examples/huggingface_tools.html |
482cbafcf0bc-0 | .ipynb
.pdf
PlayWright Browser Toolkit
Contents
Instantiating a Browser Toolkit
Use within an Agent
PlayWright Browser Toolkit#
This toolkit is used to interact with the browser. While other tools (like the Requests tools) are fine for static sites, Browser toolkits let your agent navigate the web and interact with dynamically rendered sites. Some tools bundled within the Browser toolkit include:
NavigateTool (navigate_browser) - navigate to a URL
NavigateBackTool (previous_page) - wait for an element to appear
ClickTool (click_element) - click on an element (specified by selector)
ExtractTextTool (extract_text) - use beautiful soup to extract text from the current web page
ExtractHyperlinksTool (extract_hyperlinks) - use beautiful soup to extract hyperlinks from the current web page
GetElementsTool (get_elements) - select elements by CSS selector
CurrentPageTool (current_page) - get the current page URL
# !pip install playwright > /dev/null
# !pip install lxml
# If this is your first time using playwright, you'll have to install a browser executable.
# Running `playwright install` by default installs a chromium browser executable.
# playwright install
from langchain.agents.agent_toolkits import PlayWrightBrowserToolkit
from langchain.tools.playwright.utils import (
create_async_playwright_browser,
create_sync_playwright_browser,# A synchronous browser is available, though it isn't compatible with jupyter.
)
# This import is required only for jupyter notebooks, since they have their own eventloop
import nest_asyncio
nest_asyncio.apply()
Instantiating a Browser Toolkit#
It’s always recommended to instantiate using the from_browser method so that the
async_browser = create_async_playwright_browser()
toolkit = PlayWrightBrowserToolkit.from_browser(async_browser=async_browser)
tools = toolkit.get_tools() | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-1 | tools = toolkit.get_tools()
tools
[ClickTool(name='click_element', description='Click on an element with the given CSS selector', args_schema=<class 'langchain.tools.playwright.click.ClickToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
NavigateTool(name='navigate_browser', description='Navigate a browser to the specified URL', args_schema=<class 'langchain.tools.playwright.navigate.NavigateToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
NavigateBackTool(name='previous_webpage', description='Navigate back to the previous page in the browser history', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>), | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-2 | ExtractTextTool(name='extract_text', description='Extract all the text on the current webpage', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
ExtractHyperlinksTool(name='extract_hyperlinks', description='Extract all hyperlinks on the current webpage', args_schema=<class 'langchain.tools.playwright.extract_hyperlinks.ExtractHyperlinksToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
GetElementsTool(name='get_elements', description='Retrieve elements in the current web page matching the given CSS selector', args_schema=<class 'langchain.tools.playwright.get_elements.GetElementsToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>), | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-3 | CurrentWebPageTool(name='current_webpage', description='Returns the URL of the current page', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>)]
tools_by_name = {tool.name: tool for tool in tools}
navigate_tool = tools_by_name["navigate_browser"]
get_elements_tool = tools_by_name["get_elements"]
await navigate_tool.arun({"url": "https://web.archive.org/web/20230428131116/https://www.cnn.com/world"})
'Navigating to https://web.archive.org/web/20230428131116/https://www.cnn.com/world returned status code 200'
# The browser is shared across tools, so the agent can interact in a stateful manner
await get_elements_tool.arun({"selector": ".container__headline", "attributes": ["innerText"]}) | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-4 | '[{"innerText": "These Ukrainian veterinarians are risking their lives to care for dogs and cats in the war zone"}, {"innerText": "Life in the ocean\\u2019s \\u2018twilight zone\\u2019 could disappear due to the climate crisis"}, {"innerText": "Clashes renew in West Darfur as food and water shortages worsen in Sudan violence"}, {"innerText": "Thai policeman\\u2019s wife investigated over alleged murder and a dozen other poison cases"}, {"innerText": "American teacher escaped Sudan on French evacuation plane, with no help offered back home"}, {"innerText": "Dubai\\u2019s emerging hip-hop scene is finding its voice"}, {"innerText": "How an underwater film inspired a marine protected area off Kenya\\u2019s coast"}, {"innerText": "The Iranian drones deployed by Russia in Ukraine are powered by stolen Western technology, research reveals"}, {"innerText": "India says border violations erode \\u2018entire basis\\u2019 of ties with China"}, {"innerText": "Australian police sift through 3,000 tons of trash | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-5 | "Australian police sift through 3,000 tons of trash for missing woman\\u2019s remains"}, {"innerText": "As US and Philippine defense ties grow, China warns over Taiwan tensions"}, {"innerText": "Don McLean offers duet with South Korean president who sang \\u2018American Pie\\u2019 to Biden"}, {"innerText": "Almost two-thirds of elephant habitat lost across Asia, study finds"}, {"innerText": "\\u2018We don\\u2019t sleep \\u2026 I would call it fainting\\u2019: Working as a doctor in Sudan\\u2019s crisis"}, {"innerText": "Kenya arrests second pastor to face criminal charges \\u2018related to mass killing of his followers\\u2019"}, {"innerText": "Russia launches deadly wave of strikes across Ukraine"}, {"innerText": "Woman forced to leave her forever home or \\u2018walk to your death\\u2019 she says"}, {"innerText": "U.S. House Speaker Kevin McCarthy weighs in on Disney-DeSantis feud"}, {"innerText": "Two sides agree to extend Sudan ceasefire"}, {"innerText": "Spanish | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-6 | to extend Sudan ceasefire"}, {"innerText": "Spanish Leopard 2 tanks are on their way to Ukraine, defense minister confirms"}, {"innerText": "Flamb\\u00e9ed pizza thought to have sparked deadly Madrid restaurant fire"}, {"innerText": "Another bomb found in Belgorod just days after Russia accidentally struck the city"}, {"innerText": "A Black teen\\u2019s murder sparked a crisis over racism in British policing. Thirty years on, little has changed"}, {"innerText": "Belgium destroys shipment of American beer after taking issue with \\u2018Champagne of Beer\\u2019 slogan"}, {"innerText": "UK Prime Minister Rishi Sunak rocked by resignation of top ally Raab over bullying allegations"}, {"innerText": "Iran\\u2019s Navy seizes Marshall Islands-flagged ship"}, {"innerText": "A divided Israel stands at a perilous crossroads on its 75th birthday"}, {"innerText": "Palestinian reporter breaks barriers by reporting in Hebrew on Israeli TV"}, {"innerText": "One-fifth of water pollution comes from textile dyes. But a shellfish-inspired | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-7 | comes from textile dyes. But a shellfish-inspired solution could clean it up"}, {"innerText": "\\u2018People sacrificed their lives for just\\u00a010 dollars\\u2019: At least 78 killed in Yemen crowd surge"}, {"innerText": "Israeli police say two men shot near Jewish tomb in Jerusalem in suspected \\u2018terror attack\\u2019"}, {"innerText": "King Charles III\\u2019s coronation: Who\\u2019s performing at the ceremony"}, {"innerText": "The week in 33 photos"}, {"innerText": "Hong Kong\\u2019s endangered turtles"}, {"innerText": "In pictures: Britain\\u2019s Queen Camilla"}, {"innerText": "Catastrophic drought that\\u2019s pushed millions into crisis made 100 times more likely by climate change, analysis finds"}, {"innerText": "For years, a UK mining giant was untouchable in Zambia for pollution until a former miner\\u2019s son took them on"}, {"innerText": "Former Sudanese minister Ahmed Haroun wanted on war crimes charges freed from Khartoum prison"}, {"innerText": "WHO warns | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-8 | from Khartoum prison"}, {"innerText": "WHO warns of \\u2018biological risk\\u2019 after Sudan fighters seize lab, as violence mars US-brokered ceasefire"}, {"innerText": "How Colombia\\u2019s Petro, a former leftwing guerrilla, found his opening in Washington"}, {"innerText": "Bolsonaro accidentally created Facebook post questioning Brazil election results, say his attorneys"}, {"innerText": "Crowd kills over a dozen suspected gang members in Haiti"}, {"innerText": "Thousands of tequila bottles containing liquid meth seized"}, {"innerText": "Why send a US stealth submarine to South Korea \\u2013 and tell the world about it?"}, {"innerText": "Fukushima\\u2019s fishing industry survived a nuclear disaster. 12 years on, it fears Tokyo\\u2019s next move may finish it off"}, {"innerText": "Singapore executes man for trafficking two pounds of cannabis"}, {"innerText": "Conservative Thai party looks to woo voters with promise to legalize sex toys"}, {"innerText": "Inside the Italian village being repopulated by Americans"}, | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-9 | "Inside the Italian village being repopulated by Americans"}, {"innerText": "Strikes, soaring airfares and yo-yoing hotel fees: A traveler\\u2019s guide to the coronation"}, {"innerText": "A year in Azerbaijan: From spring\\u2019s Grand Prix to winter ski adventures"}, {"innerText": "The bicycle mayor peddling a two-wheeled revolution in Cape Town"}, {"innerText": "Tokyo ramen shop bans customers from using their phones while eating"}, {"innerText": "South African opera star will perform at coronation of King Charles III"}, {"innerText": "Luxury loot under the hammer: France auctions goods seized from drug dealers"}, {"innerText": "Judy Blume\\u2019s books were formative for generations of readers. Here\\u2019s why they endure"}, {"innerText": "Craft, salvage and sustainability take center stage at Milan Design Week"}, {"innerText": "Life-sized chocolate King Charles III sculpture unveiled to celebrate coronation"}, {"innerText": "Severe storms to strike the South again as millions in Texas could see damaging winds and | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-10 | as millions in Texas could see damaging winds and hail"}, {"innerText": "The South is in the crosshairs of severe weather again, as the multi-day threat of large hail and tornadoes continues"}, {"innerText": "Spring snowmelt has cities along the Mississippi bracing for flooding in homes and businesses"}, {"innerText": "Know the difference between a tornado watch, a tornado warning and a tornado emergency"}, {"innerText": "Reporter spotted familiar face covering Sudan evacuation. See what happened next"}, {"innerText": "This country will soon become the world\\u2019s most populated"}, {"innerText": "April 27, 2023 - Russia-Ukraine news"}, {"innerText": "\\u2018Often they shoot at each other\\u2019: Ukrainian drone operator details chaos in Russian ranks"}, {"innerText": "Hear from family members of Americans stuck in Sudan frustrated with US response"}, {"innerText": "U.S. talk show host Jerry Springer dies at 79"}, {"innerText": "Bureaucracy stalling at least one family\\u2019s evacuation from Sudan"}, {"innerText": | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-11 | evacuation from Sudan"}, {"innerText": "Girl to get life-saving treatment for rare immune disease"}, {"innerText": "Haiti\\u2019s crime rate more than doubles in a year"}, {"innerText": "Ocean census aims to discover 100,000 previously unknown marine species"}, {"innerText": "Wall Street Journal editor discusses reporter\\u2019s arrest in Moscow"}, {"innerText": "Can Tunisia\\u2019s democracy be saved?"}, {"innerText": "Yasmeen Lari, \\u2018starchitect\\u2019 turned social engineer, wins one of architecture\\u2019s most coveted prizes"}, {"innerText": "A massive, newly restored Frank Lloyd Wright mansion is up for sale"}, {"innerText": "Are these the most sustainable architectural projects in the world?"}, {"innerText": "Step inside a $72 million London townhouse in a converted army barracks"}, {"innerText": "A 3D-printing company is preparing to build on the lunar surface. But first, a moonshot at home"}, {"innerText": "Simona Halep says \\u2018the stress is huge\\u2019 as she battles to | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-12 | stress is huge\\u2019 as she battles to return to tennis following positive drug test"}, {"innerText": "Barcelona reaches third straight Women\\u2019s Champions League final with draw against Chelsea"}, {"innerText": "Wrexham: An intoxicating tale of Hollywood glamor and sporting romance"}, {"innerText": "Shohei Ohtani comes within inches of making yet more MLB history in Angels win"}, {"innerText": "This CNN Hero is recruiting recreational divers to help rebuild reefs in Florida one coral at a time"}, {"innerText": "This CNN Hero offers judgment-free veterinary care for the pets of those experiencing homelessness"}, {"innerText": "Don\\u2019t give up on milestones: A CNN Hero\\u2019s message for Autism Awareness Month"}, {"innerText": "CNN Hero of the Year Nelly Cheboi returned to Kenya with plans to lift more students out of poverty"}]' | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
482cbafcf0bc-13 | # If the agent wants to remember the current webpage, it can use the `current_webpage` tool
await tools_by_name['current_webpage'].arun({})
'https://web.archive.org/web/20230428133211/https://cnn.com/world'
Use within an Agent#
Several of the browser tools are StructuredTool’s, meaning they expect multiple arguments. These aren’t compatible (out of the box) with agents older than the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION
from langchain.agents import initialize_agent, AgentType
from langchain.chat_models import ChatAnthropic
llm = ChatAnthropic(temperature=0) # or any other LLM, e.g., ChatOpenAI(), OpenAI()
agent_chain = initialize_agent(tools, llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
result = await agent_chain.arun("What are the headers on langchain.com?")
print(result)
> Entering new AgentExecutor chain...
Thought: I need to navigate to langchain.com to see the headers
Action:
```
{
"action": "navigate_browser",
"action_input": "https://langchain.com/"
}
```
Observation: Navigating to https://langchain.com/ returned status code 200
Thought: Action:
```
{
"action": "get_elements",
"action_input": {
"selector": "h1, h2, h3, h4, h5, h6"
}
}
```
Observation: []
Thought: Thought: The page has loaded, I can now extract the headers
Action:
```
{
"action": "get_elements",
"action_input": { | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/playwright.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.