id stringlengths 14 16 | text stringlengths 31 3.14k | source stringlengths 58 124 |
|---|---|---|
cc818135d6bf-24 | _DumpException(e){throw e;}\nfunction _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\\x... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
cc818135d6bf-25 | Lucky\\x22,\\x22lml\\x22:\\x22Learn more\\x22,\\x22psrc\\x22:\\x22This search was removed from your \\\\u003Ca 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:{... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
cc818135d6bf-26 | previous
Python REPL
next
Search Tools
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 26, 2023. | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/requests.html |
69e8e356f929-0 | .ipynb
.pdf
Arxiv API
Arxiv API#
This notebook goes over how to use the arxiv component.
First, you need to install arxiv python package.
!pip install arxiv
from langchain.utilities import ArxivAPIWrapper
Run a query to get information about some scientific article/articles. The query text is limited to 300 characters.... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/arxiv.html |
69e8e356f929-1 | 'Published: 2017-10-10\nTitle: On Mixing Behavior of a Family of Random Walks Determined by a Linear Recurrence\nAuthors: Caprice Stanley, Seth Sullivant\nSummary: We study random walks on the integers mod $G_n$ that are determined by an\ninteger sequence $\\{ G_n \\}_{n \\geq 1}$ generated by a linear recurrence\nrela... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/arxiv.html |
69e8e356f929-2 | V. Plyaskin\nSummary: The results on the fluxes of charged particles and neutrinos from a\n3-dimensional (3D) simulation of atmospheric showers are presented. An\nagreement of calculated fluxes with data on charged particles from the AMS and\nCAPRICE detectors is demonstrated. Predictions on neutrino fluxes at differen... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/arxiv.html |
69e8e356f929-3 | Now, we are trying to find information about non-existing article. In this case, the response is “No good Arxiv Result was found”
docs = arxiv.run("1605.08386WWW")
docs
'No good Arxiv Result was found'
previous
Apify
next
Bash
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 2... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/arxiv.html |
9f2399fb8ff7-0 | .ipynb
.pdf
Wikipedia API
Wikipedia API#
This notebook goes over how to use the wikipedia component.
First, you need to install wikipedia python package.
pip install wikipedia
from langchain.utilities import WikipediaAPIWrapper
wikipedia = WikipediaAPIWrapper()
wikipedia.run('HUNTER X HUNTER') | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
9f2399fb8ff7-1 | '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 ... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
9f2399fb8ff7-2 | 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 × H... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
9f2399fb8ff7-3 | 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 N... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
9f2399fb8ff7-4 | 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... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
9f2399fb8ff7-5 | previous
SerpAPI
next
Wolfram Alpha
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 26, 2023. | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html |
2404ade73218-0 | .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 l... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
2404ade73218-1 | > Entering new AgentExecutor chain...
I need to find out what the current weather is in Pomfret.
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 1... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
2404ade73218-2 | 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 fo... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
2404ade73218-3 | 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%.
> Finished AgentExecutor chain.
'Showers early becoming a steady light rain later in the... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
2404ade73218-4 | 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....
Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEA... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
2404ade73218-5 | 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...
Thought: I now know the final answer
Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in th... | /content/https://python.langchain.com/en/latest/modules/agents/tools/examples/search_tools.html |
70277ed69467-0 | .ipynb
.pdf
Custom MultiAction Agent
Custom MultiAction Agent#
This notebook goes through how to create your own custom agent.
An agent consists of three parts:
- Tools: The tools the agent has available to use.
- The agent class itself: this decides which action to take.
In this notebook we walk through how to create ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
70277ed69467-1 | along with observations
**kwargs: User inputs.
Returns:
Action specifying what tool to use.
"""
if len(intermediate_steps) == 0:
return [
AgentAction(tool="Search", tool_input=kwargs["input"], log=""),
AgentAction(tool="RandomWo... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
70277ed69467-2 | > Entering new AgentExecutor chain...
The current population of Canada is 38,669,152 as of Monday, April 24, 2023, based on Worldometer elaboration of the latest United Nations data.
Now I'm doing this!
foo
> Finished chain.
'bar'
previous
Custom MRKL Agent
next
Custom Agent with Tool Retrieval
By Harrison Chase
... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
e03e89b3f4f9-0 | .ipynb
.pdf
Custom MRKL Agent
Contents
Custom LLMChain
Multiple inputs
Custom MRKL Agent#
This notebook goes through how to create your own custom MRKL agent.
A MRKL agent consists of three parts:
- Tools: The tools the agent has available to use.
- LLMChain: The LLMChain that produces the text that is parsed in a ce... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
e03e89b3f4f9-1 | suffix: String to put after the list of tools.
input_variables: List of input variables the final prompt will expect.
For this exercise, we will give our agent access to Google Search, and we will customize it in that we will have it answer as a pirate.
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
fr... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
e03e89b3f4f9-2 | Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin! Remember to speak as a pirate when giving your final answer. Use lot... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
e03e89b3f4f9-3 | Thought: I now know the final answer
Final Answer: Arrr, Canada be havin' 38,661,927 people livin' there as of 2023!
> Finished chain.
"Arrr, Canada be havin' 38,661,927 people livin' there as of 2023!"
Multiple inputs#
Agents can also work with prompts that require multiple inputs.
prefix = """Answer the following que... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
e03e89b3f4f9-4 | Action: Search
Action Input: Canada population estimates 2023
Observation: Canada's population was estimated at 39,566,248 on January 1, 2023, after a record population growth of 1,050,110 people from January 1, 2022, to January 1, 2023.
Thought: I now know the final answer.
Final Answer: La popolazione del Canada è st... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
fd90cd463bf0-0 | .md
.pdf
Agent Types
Contents
zero-shot-react-description
react-docstore
self-ask-with-search
conversational-react-description
Agent Types#
Agents use an LLM to determine which actions to take and in what order.
An action can either be using a tool and observing its output, or returning a response to the user.
Here a... | /content/https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html |
fd90cd463bf0-1 | react-docstore
self-ask-with-search
conversational-react-description
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 26, 2023. | /content/https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html |
4256fb2a80a0-0 | .ipynb
.pdf
Custom Agent
Custom Agent#
This notebook goes through how to create your own custom agent.
An agent consists of three parts:
- Tools: The tools the agent has available to use.
- The agent class itself: this decides which action to take.
In this notebook we walk through how to create a custom agent.
from lan... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent.html |
4256fb2a80a0-1 | ) -> Union[AgentAction, AgentFinish]:
"""Given input, decided what to do.
Args:
intermediate_steps: Steps the LLM has taken to date,
along with observations
**kwargs: User inputs.
Returns:
Action specifying what tool to use.
"""
... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent.html |
dcb1e1ca814f-0 | .ipynb
.pdf
Custom LLM Agent
Contents
Set up environment
Set up tool
Prompt Template
Output Parser
Set up LLM
Define the stop sequence
Set up the Agent
Use the Agent
Adding Memory
Custom LLM Agent#
This notebook goes through how to create your own custom LLM agent.
An LLM agent consists of three parts:
PromptTemplate... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-1 | Set up environment#
Do necessary imports, etc.
from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser
from langchain.prompts import StringPromptTemplate
from langchain import OpenAI, SerpAPIWrapper, LLMChain
from typing import List, Union
from langchain.schema import AgentAction, Agen... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-2 | Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin! Remember to speak as a pirate when giving your final answer. Use lot... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-3 | prompt = CustomPromptTemplate(
template=template,
tools=tools,
# This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically
# This includes the `intermediate_steps` variable because that is needed
input_variables=["input", "intermediate_steps"]
)
O... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-4 | if not match:
raise ValueError(f"Could not parse LLM output: `{llm_output}`")
action = match.group(1).strip()
action_input = match.group(2)
# Return the action and action input
return AgentAction(tool=action, tool_input=action_input.strip(" ").strip('"'), log=llm_output)
outp... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-5 | > Entering new AgentExecutor chain...
Thought: I need to find out the population of Canada in 2023
Action: Search
Action Input: Population of Canada in 2023
Observation:The current population of Canada is 38,658,314 as of Wednesday, April 12, 2023, based on Worldometer elaboration of the latest United Nations data. I n... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-6 | template=template_with_history,
tools=tools,
# This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically
# This includes the `intermediate_steps` variable because that is needed
input_variables=["input", "intermediate_steps", "history"]
)
llm_chain = ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
dcb1e1ca814f-7 | > Finished chain.
"Arrr, there be 38,658,314 people livin' in Canada as of 2023!"
agent_executor.run("how about in mexico?")
> Entering new AgentExecutor chain...
Thought: I need to find out how many people live in Mexico.
Action: Search
Action Input: How many people live in Mexico as of 2023?
Observation:The current p... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
02ec69249e0e-0 | .ipynb
.pdf
Custom Agent with Tool Retrieval
Contents
Set up environment
Set up tools
Tool Retriever
Prompt Template
Output Parser
Set up LLM, stop sequence, and the agent
Use the Agent
Custom Agent with Tool Retrieval#
This notebook builds off of this notebook and assumes familiarity with how agents work.
The novel ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-1 | description="useful for when you need to answer questions about current events"
)
def fake_func(inp: str) -> str:
return "foo"
fake_tools = [
Tool(
name=f"foo-{i}",
func=fake_func,
description=f"a silly function that you can use to get more information about the number {i}"
)
... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-2 | get_tools("whats the weather?")
[Tool(name='Search', description='useful for when you need to answer questions about current events', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<bound method SerpAPIWrapper.run of SerpAPIWrapper(sea... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-3 | Tool(name='foo-12', description='a silly function that you can use to get more information about the number 12', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),
Tool(name='foo-15', ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-4 | Tool(name='foo-12', description='a silly function that you can use to get more information about the number 12', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),
Tool(name='foo-14', ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-5 | {tools}
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can r... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-6 | tools = self.tools_getter(kwargs["input"])
# Create a tools variable from the list of tools provided
kwargs["tools"] = "\n".join([f"{tool.name}: {tool.description}" for tool in tools])
# Create a list of tool names for the tools provided
kwargs["tool_names"] = ", ".join([tool.name for to... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-7 | log=llm_output,
)
# Parse out the action and action input
regex = r"Action\s*\d*\s*:(.*?)\nAction\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
match = re.search(regex, llm_output, re.DOTALL)
if not match:
raise ValueError(f"Could not parse LLM output: `{llm_output}`")
... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
02ec69249e0e-8 | agent_executor.run("What's the weather in SF?")
> Entering new AgentExecutor chain...
Thought: I need to find out what the weather is in SF
Action: Search
Action Input: Weather in SF
Observation:Mostly cloudy skies early, then partly cloudy in the afternoon. High near 60F. ENE winds shifting to W at 10 to 15 mph. Humid... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
330d82ff81f6-0 | .ipynb
.pdf
Custom LLM Agent (with a ChatModel)
Contents
Set up environment
Set up tool
Prompt Template
Output Parser
Set up LLM
Define the stop sequence
Set up the Agent
Use the Agent
Custom LLM Agent (with a ChatModel)#
This notebook goes through how to create your own custom agent based on a chat model.
An LLM cha... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
330d82ff81f6-1 | In this notebook we walk through how to create a custom LLM agent.
Set up environment#
Do necessary imports, etc.
from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser
from langchain.prompts import BaseChatPromptTemplate
from langchain import SerpAPIWrapper, LLMChain
from langchain.c... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
330d82ff81f6-2 | Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin! Remember... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
330d82ff81f6-3 | formatted = self.template.format(**kwargs)
return [HumanMessage(content=formatted)]
prompt = CustomPromptTemplate(
template=template,
tools=tools,
# This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically
# This includes the `intermediate_st... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
330d82ff81f6-4 | match = re.search(regex, llm_output, re.DOTALL)
if not match:
raise ValueError(f"Could not parse LLM output: `{llm_output}`")
action = match.group(1).strip()
action_input = match.group(2)
# Return the action and action input
return AgentAction(tool=action, tool_input=... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
330d82ff81f6-5 | agent_executor.run("How many people live in canada as of 2023?")
> Entering new AgentExecutor chain...
Thought: Wot year be it now? That be important to know the answer.
Action: Search
Action Input: "current population canada 2023"
Observation:38,649,283Ahoy! That be the correct year, but the answer be in regular numbe... | /content/https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
d93bb485eca7-0 | .ipynb
.pdf
Conversation Agent
Conversation Agent#
This notebook walks through using an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
d93bb485eca7-1 | > Entering new AgentExecutor chain...
Thought: Do I need to use a tool? No
AI: Your name is Bob!
> Finished chain.
'Your name is Bob!'
agent_chain.run("what are some good dinners to make this week, if i like thai food?")
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: Current Search
... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
d93bb485eca7-2 | Observation: Argentina national football team
Thought: Do I need to use a tool? No
AI: The last letter in your name is "b" and the winner of the 1978 World Cup was the Argentina national football team.
> Finished chain.
'The last letter in your name is "b" and the winner of the 1978 World Cup was the Argentina national... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
619cc53cdb76-0 | .ipynb
.pdf
MRKL Chat
MRKL Chat#
This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models.
This uses the example Chinook database.
To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at t... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
619cc53cdb76-1 | ),
Tool(
name="FooBar DB",
func=db_chain.run,
description="useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context"
)
]
mrkl = initialize_agent(tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
619cc53cdb76-2 | Thought:I now know the final answer.
Final Answer: Gigi Hadid is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is approximately 4.13.
> Finished chain.
"Gigi Hadid is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is approximately 4.13."
mrkl.run("What is the full name o... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
619cc53cdb76-3 | What albums does Alanis Morissette have in the database?
SQLQuery:
/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:191: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
bea49bafd3e5-0 | .ipynb
.pdf
Conversation Agent (for Chat Models)
Conversation Agent (for Chat Models)#
This notebook walks through using an agent optimized for conversation, using ChatModels. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may w... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
bea49bafd3e5-1 | ),
]
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
llm=ChatOpenAI(temperature=0)
agent_chain = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
agent_chain.run(input="hi, i am bob")
> Entering new AgentExecutor chain...... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
bea49bafd3e5-2 | {
"action": "Final Answer",
"action_input": "Your name is Bob."
}
> Finished chain.
'Your name is Bob.'
agent_chain.run("what are some good dinners to make this week, if i like thai food?")
> Entering new AgentExecutor chain...
{
"action": "Current Search",
"action_input": "Thai food dinner recipes"
}
O... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
bea49bafd3e5-3 | agent_chain.run(input="tell me the last letter in my name, and also tell me who won the world cup in 1978?")
> Entering new AgentExecutor chain...
```json
{
"action": "Current Search",
"action_input": "who won the world cup in 1978"
}
```
Observation: Argentina national football team
Thought:
WARNING:root:Faile... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
bea49bafd3e5-4 | Thought:
WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fa9d7f0>: Failed to establish a new connection: [Errno 61] Connection refused'))
{
"action": "Final... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
8f5fee1969aa-0 | .ipynb
.pdf
ReAct
ReAct#
This notebook showcases using an agent to implement the ReAct logic.
from langchain import OpenAI, Wikipedia
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.agents.react.base import DocstoreExplorer
docstore=DocstoreExplorer(Wikipedia())... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/react.html |
8f5fee1969aa-1 | Action: Search[David Chanoff]
Observation: David Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/react.html |
20edeaeb035a-0 | .ipynb
.pdf
Self Ask With Search
Self Ask With Search#
This notebook showcases the Self Ask With Search chain.
from langchain import OpenAI, SerpAPIWrapper
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
llm = OpenAI(temperature=0)
search = SerpAPIWrapper()
tools = [
Tool(... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/self_ask_with_search.html |
3b774017deb4-0 | .ipynb
.pdf
MRKL
MRKL#
This notebook showcases using an agent to replicate the MRKL chain.
This uses the example Chinook database.
To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository.
from langchain import L... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
3b774017deb4-1 | )
]
mrkl = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
mrkl.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
> Entering new AgentExecutor chain...
I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised ... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
3b774017deb4-2 | mrkl.run("What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?")
> Entering new AgentExecutor chain...
I need to find out the artist's full name and then search the FooBar data... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
3b774017deb4-3 | sample_rows = connection.execute(command)
SELECT "Title" FROM "Album" INNER JOIN "Artist" ON "Album"."ArtistId" = "Artist"."ArtistId" WHERE "Name" = 'Alanis Morissette' LIMIT 5;
SQLResult: [('Jagged Little Pill',)]
Answer: The albums by Alanis Morissette in the FooBar database are Jagged Little Pill.
> Finished chain.... | /content/https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
03c6e2e9dce9-0 | .ipynb
.pdf
SQL Database Agent
Contents
Initialization
Example: describing a table
Example: describing a table, recovering from an error
Example: running queries
Recovering from an error
SQL Database Agent#
This notebook showcases an agent designed to interact with a sql databases. The agent builds off of SQLDatabase... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-1 | agent_executor.run("Describe the playlisttrack table")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: Artist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer
Thought: I should look at the schema of the playlisttrack table
... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-2 | agent_executor.run("Describe the playlistsong table")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: Genre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist
Thought: I should look at the schema of the PlaylistSong table
Ac... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-3 | 1 3402
1 3389
1 3390
Thought: I now know the final answer
Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.
> Finished chain.
'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both in... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-4 | "Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
SELECT * FROM 'Customer' LIMIT 3;
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer ... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-5 | PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
SELECT * FROM 'Invoice' LIMIT 3;
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-6 | Thought: I now know the final answer
Final Answer: The customers from the USA spent the most, with a total of $523.06.
> Finished chain.
'The customers from the USA spent the most, with a total of $523.06.'
agent_executor.run("Show the total number of tracks in each playlist. The Playlist name should be included in the... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-7 | PlaylistId TrackId
1 3402
1 3389
1 3390
Thought: I can use a SELECT statement to get the total number of tracks in each playlist.
Action: query_checker_sql_db
Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.Pla... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-8 | Thought: I now know the final answer.
Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-9 | Action Input: "Artist, InvoiceLine, Track"
Observation:
CREATE TABLE "Artist" (
"ArtistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("ArtistId")
)
SELECT * FROM 'Artist' LIMIT 3;
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NU... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-10 | 2 Balls to the Wall 2 2 1 None 342562 5510424 0.99
3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99
CREATE TABLE "InvoiceLine" (
"InvoiceLineId" INTEGER NOT NULL,
"InvoiceId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
"Quant... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-11 | Observation: Error: (sqlite3.OperationalError) no such column: Track.ArtistId
[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DE... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
03c6e2e9dce9-12 | Thought: I now know the final answer.
Action: query_sql_db
Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP B... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
ef29d9ea4bc2-0 | .ipynb
.pdf
CSV Agent
CSV Agent#
This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.
NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM gene... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/csv.html |
ef29d9ea4bc2-1 | agent.run("whats the square root of the average age?")
> Entering new AgentExecutor chain...
Thought: I need to calculate the average age first
Action: python_repl_ast
Action Input: df['Age'].mean()
Observation: 29.69911764705882
Thought: I can now calculate the square root
Action: python_repl_ast
Action Input: math.sq... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/csv.html |
ed7a79af929d-0 | .ipynb
.pdf
Natural Language APIs
Contents
First, import dependencies and load the LLM
Next, load the Natural Language API Toolkits
Create the Agent
Using Auth + Adding more Endpoints
Thank you!
Natural Language APIs#
Natural Language API Toolkits (NLAToolkits) permit LangChain Agents to efficiently plan and combine ... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-1 | Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Attempting to load an OpenAPI 3.... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-2 | verbose=True, agent_kwargs={"format_instructions":openapi_format_instructions})
mrkl.run("I have an end of year party for my Italian class and have to buy some Italian clothes for it")
> Entering new AgentExecutor chain...
I need to find out what kind of Italian clothes are available
Action: Open_AI_Klarna_product_Api... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-3 | Since each NLATool exposes a concisee natural language interface to its wrapped API, the top level conversational agent has an easier job incorporating each endpoint to satisfy a user’s request.
Adding the Spoonacular endpoints.
Go to the Spoonacular API Console and make a free account.
Click on Profile and copy your A... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-4 | Unsupported APIPropertyLocation "header" for parameter Content-Type. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Content... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-5 | Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept. Valid... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-6 | )
mrkl.run(user_input)
> Entering new AgentExecutor chain...
I need to find a recipe and an outfit that is Italian-themed.
Action: spoonacular_API.searchRecipes
Action Input: Italian
Observation: The API response contains 10 Italian recipes, including Turkey Tomato Cheese Pizza, Broccolini Quinoa Pilaf, Bruschetta Sty... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-7 | Thought: I now know the final answer.
Final Answer: To present for your Italian language class, you could wear an Italian Gold Sparkle Perfectina Necklace - Gold, an Italian Design Miami Cuban Link Chain Necklace - Gold, or an Italian Gold Miami Cuban Link Chain Necklace - Gold. For a recipe, you could make Turkey Toma... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
ed7a79af929d-8 | "In Italian, you can say 'Buon appetito' to someone to wish them to enjoy their meal. This phrase is commonly used in Italy when someone is about to eat, often at the beginning of a meal. It's similar to saying 'Bon appétit' in French or 'Guten Appetit' in German."
previous
OpenAPI agents
next
Pandas Dataframe Agent
C... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
58136f950fdf-0 | .ipynb
.pdf
Python Agent
Contents
Fibonacci Example
Training neural net
Python Agent#
This notebook showcases an agent designed to write and execute python code to answer a question.
from langchain.agents.agent_toolkits import create_python_agent
from langchain.tools.python.tool import PythonREPLTool
from langchain.p... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
58136f950fdf-1 | Return prediction for x = 5""")
> Entering new AgentExecutor chain...
I need to write a neural network in PyTorch and train it on the given data.
Action: Python REPL
Action Input:
import torch
# Define the model
model = torch.nn.Sequential(
torch.nn.Linear(1, 1)
)
# Define the loss
loss_fn = torch.nn.MSELoss()
# ... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
58136f950fdf-2 | Epoch 900: loss = 0.0000
Epoch 1000: loss = 0.0000
Thought: I now know the final answer
Final Answer: The prediction for x = 5 is 10.0.
> Finished chain.
'The prediction for x = 5 is 10.0.'
previous
PowerBI Dataset Agent
next
SQL Database Agent
Contents
Fibonacci Example
Training neural net
By Harrison Chase
... | /content/https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.