id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
c97d1a88ecee-3 | Action Input: What are the advantages of using ruff over flake8?
Observation: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quali... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
c97d1a88ecee-4 | Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly.
tools = [
Tool(
name = "State of Union QA System",
func=state_of_union.run,
description="useful for when you need to answer questions a... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
c97d1a88ecee-5 | Action Input: What are the advantages of using ruff over flake8?
Observation: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quali... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
c97d1a88ecee-6 | Tool(
name = "Ruff QA System",
func=ruff.run,
description="useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before."
),
]
# Construct the agent. We will use the defau... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
c97d1a88ecee-7 | previous
Agent Executors
next
How to use the async API for Agents
Contents
Create the Vectorstore
Create the Agent
Use the Agent solely as a router
Multi-Hop vectorstore reasoning
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
1f702fe9ec35-0 | .ipynb
.pdf
Handle Parsing Errors
Contents
Setup
Error
Default error handling
Custom Error Message
Custom Error Function
Handle Parsing Errors#
Occasionally the LLM cannot determine what step to take because it outputs format in incorrect form to be handled by the output parser. In this case, by default the agent err... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-1 | 22 response = json.loads(action.strip())
IndexError: list index out of range
During handling of the above exception, another exception occurred:
OutputParserException Traceback (most recent call last)
Cell In[4], line 1
----> 1 mrkl.run("Who is Leo DiCaprio's girlfriend? No need to add Action")
... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-2 | 135 if new_arg_supported
136 else self._call(inputs)
137 )
138 except (KeyboardInterrupt, Exception) as e:
139 run_manager.on_chain_error(e)
File ~/workplace/langchain/langchain/agents/agent.py:947, in AgentExecutor._call(self, inputs, run_manager)
945 # We now enter the agen... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-3 | 758 Override this to take control of how the agent makes and acts on choices.
759 """
760 try:
761 # Call the LLM to see what to do.
--> 762 output = self.agent.plan(
763 intermediate_steps,
764 callbacks=run_manager.get_child() if run_manager else None,
765 **inp... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-4 | verbose=True,
handle_parsing_errors=True
)
mrkl.run("Who is Leo DiCaprio's girlfriend? No need to add Action")
> Entering new AgentExecutor chain...
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:Search for Leo DiCaprio's current girlfriend
Action:
```
{
"... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-5 | "action_input": "Who is Leo DiCaprio's girlfriend?"
}
```
Observation: DiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spott... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
1f702fe9ec35-6 | "action_input": "Who is Leo DiCaprio's girlfriend?"
}
```
Observation: DiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spott... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
454e621f219a-0 | .ipynb
.pdf
Custom Agent
Custom Agent#
This notebook goes through how to create your own custom agent.
An agent consists of two 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 langc... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent.html |
454e621f219a-1 | Args:
intermediate_steps: Steps the LLM has taken to date,
along with observations
**kwargs: User inputs.
Returns:
Action specifying what tool to use.
"""
return AgentAction(tool="Search", tool_input=kwargs["input"], log="")
agent = FakeAgent()... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent.html |
62cd40f161a0-0 | .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... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
62cd40f161a0-1 | !pip install langchain
!pip install google-search-results
!pip install openai
from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser
from langchain.prompts import BaseChatPromptTemplate
from langchain import SerpAPIWrapper, LLMChain
from langchain.chat_models import ChatOpenAI
from ty... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
62cd40f161a0-2 | 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
These were previous tasks you completed:
Begin!
Question: {input}
{agent_sc... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
62cd40f161a0-3 | # This includes the `intermediate_steps` variable because that is needed
input_variables=["input", "intermediate_steps"]
)
Output Parser#
The output parser is responsible for parsing the LLM output into AgentAction and AgentFinish. This usually depends heavily on the prompt used.
This is where you can change the pa... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
62cd40f161a0-4 | llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0)
Define the stop sequence#
This is important because it tells the LLM when to stop generation.
This depends heavily on the prompt and model you are using. Generally, you want this to be whatever token you use in the prompt to denote the start of an Observati... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
62cd40f161a0-5 | previous
Custom LLM Agent
next
Custom MRKL 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
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_chat_agent.html |
efd8bd7ba50a-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 ... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-1 | 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}"
)
for i in range(99)
]
ALL_TOOLS = [search_tool] + fake_tools
Tool Retriever#
We will use a vectorstore to create embedd... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-2 | Tool(name='foo-95', description='a silly function that you can use to get more information about the number 95', 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-12', ... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-3 | Tool(name='foo-14', description='a silly function that you can use to get more information about the number 14', 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-11', ... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-4 | from typing import Callable
# Set up a prompt template
class CustomPromptTemplate(StringPromptTemplate):
# The template to use
template: str
############## NEW ######################
# The list of tools available
tools_getter: Callable
def format(self, **kwargs) -> str:
# Get the in... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-5 | class CustomOutputParser(AgentOutputParser):
def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:
# Check if agent should finish
if "Final Answer:" in llm_output:
return AgentFinish(
# Return values is generally always a dictionary with a single `outp... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
efd8bd7ba50a-6 | output_parser=output_parser,
stop=["\nObservation:"],
allowed_tools=tool_names
)
Use the Agent#
Now we can use it!
agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
agent_executor.run("What's the weather in SF?")
> Entering new AgentExecutor chain...
Thought: I need to... | https://python.langchain.com/en/latest/modules/agents/agents/custom_agent_with_tool_retrieval.html |
2f9fa8b9587c-0 | .ipynb
.pdf
Custom MultiAction Agent
Custom MultiAction Agent#
This notebook goes through how to create your own custom agent.
An agent consists of two 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 ... | https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
2f9fa8b9587c-1 | """
if len(intermediate_steps) == 0:
return [
AgentAction(tool="Search", tool_input=kwargs["input"], log=""),
AgentAction(tool="RandomWord", tool_input=kwargs["input"], log=""),
]
else:
return AgentFinish(return_values={"output": "bar"}... | https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
2f9fa8b9587c-2 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/agents/custom_multi_action_agent.html |
b9400845cef9-0 | .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... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-1 | from langchain.prompts import StringPromptTemplate
from langchain import OpenAI, SerpAPIWrapper, LLMChain
from typing import List, Union
from langchain.schema import AgentAction, AgentFinish
import re
Set up tool#
Set up any tools the agent may want to use. This may be necessary to put in the prompt (so that the agent ... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-2 | Question: {input}
{agent_scratchpad}"""
# Set up a prompt template
class CustomPromptTemplate(StringPromptTemplate):
# The template to use
template: str
# The list of tools available
tools: List[Tool]
def format(self, **kwargs) -> str:
# Get the intermediate steps (AgentAction, Observat... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-3 | class CustomOutputParser(AgentOutputParser):
def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:
# Check if agent should finish
if "Final Answer:" in llm_output:
return AgentFinish(
# Return values is generally always a dictionary with a single `outp... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-4 | # LLM chain consisting of the LLM and a prompt
llm_chain = LLMChain(llm=llm, prompt=prompt)
tool_names = [tool.name for tool in tools]
agent = LLMSingleActionAgent(
llm_chain=llm_chain,
output_parser=output_parser,
stop=["\nObservation:"],
allowed_tools=tool_names
)
Use the Agent#
Now we can use it!
a... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-5 | 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 repeat N times)
Thought: I now know... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
b9400845cef9-6 | 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 now know the final answer
Final Answer:... | https://python.langchain.com/en/latest/modules/agents/agents/custom_llm_agent.html |
3adcc1a519ed-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... | https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html |
3adcc1a519ed-1 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html |
1b7fae33f2b0-0 | .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... | https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
1b7fae33f2b0-1 | 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
from langchain import OpenAI, SerpAPIWrapper, LLM... | https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
1b7fae33f2b0-2 | 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 lots of "Args"
Question: {input}
{agent_scratchpad}
Note that we are able to feed agents a self-defined prompt template, i.e. not restricted to the p... | https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
1b7fae33f2b0-3 | Multiple inputs#
Agents can also work with prompts that require multiple inputs.
prefix = """Answer the following questions as best you can. You have access to the following tools:"""
suffix = """When answering, you MUST speak in the following language: {language}.
Question: {input}
{agent_scratchpad}"""
prompt = ZeroS... | https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
1b7fae33f2b0-4 | Thought: I now know the final answer.
Final Answer: La popolazione del Canada è stata stimata a 39.566.248 il 1° gennaio 2023, dopo un record di crescita demografica di 1.050.110 persone dal 1° gennaio 2022 al 1° gennaio 2023.
> Finished chain.
'La popolazione del Canada è stata stimata a 39.566.248 il 1° gennaio 2023,... | https://python.langchain.com/en/latest/modules/agents/agents/custom_mrkl_agent.html |
ea3f63ef2b12-0 | .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... | https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
ea3f63ef2b12-1 | 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
Action Input: Thai food dinner recipes
Observation: 59 easy Thai recipes fo... | https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
ea3f63ef2b12-2 | > Finished chain.
'The last letter in your name is "b" and the winner of the 1978 World Cup was the Argentina national football team.'
agent_chain.run(input="whats the current temperature in pomfret?")
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: Current Search
Action Input: Curre... | https://python.langchain.com/en/latest/modules/agents/agents/examples/conversational_agent.html |
a106c4cb8c41-0 | .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... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
a106c4cb8c41-1 | mrkl.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
> Entering new AgentExecutor chain...
Thought: The first question requires a search, while the second question requires a calculator.
Action:
```
{
"action": "Search",
"action_input": "Leo DiCaprio girlfriend"
}
```
Obse... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
a106c4cb8c41-2 | 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...
Question: What is the full name of the artist who recently released an alb... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
a106c4cb8c41-3 | sample_rows = connection.execute(command)
SELECT "Title" FROM "Album" WHERE "ArtistId" IN (SELECT "ArtistId" FROM "Artist" WHERE "Name" = 'Alanis Morissette') LIMIT 5;
SQLResult: [('Jagged Little Pill',)]
Answer: Alanis Morissette has the album Jagged Little Pill in the database.
> Finished chain.
Observation: Alanis... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl_chat.html |
79619975543b-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... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
79619975543b-1 | > Entering new AgentExecutor chain...
I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.
Action: Search
Action Input: "Who is Leo DiCaprio's girlfriend?"
Observation: DiCaprio met actor Camila Morrone in December 2017, when she was 20 and he was 43. They were spott... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
79619975543b-2 | > Entering new AgentExecutor chain...
I need to find out the artist's full name and then search the FooBar database for their albums.
Action: Search
Action Input: "The Storm Before the Calm" artist
Observation: The Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album b... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
79619975543b-3 | Thought: I now know the final answer.
Final Answer: The artist who released the album 'The Storm Before the Calm' is Alanis Morissette and the albums of hers in the FooBar database are Jagged Little Pill.
> Finished chain.
"The artist who released the album 'The Storm Before the Calm' is Alanis Morissette and the album... | https://python.langchain.com/en/latest/modules/agents/agents/examples/mrkl.html |
d0ea7d2dad59-0 | .ipynb
.pdf
Structured Tool Chat Agent
Contents
Initialize Tools
Adding in memory
Structured Tool Chat Agent#
This notebook walks through using a chat agent capable of using multi-input tools.
Older agents are configured to specify an action input as a single string, but this agent can use the provided tools’ args_sc... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-1 | print(response)
> Entering new AgentExecutor chain...
Action:
```
{
"action": "Final Answer",
"action_input": "Hello Erica, how can I assist you today?"
}
```
> Finished chain.
Hello Erica, how can I assist you today?
response = await agent_chain.arun(input="Don't need help really just chatting.")
print(response)
>... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-2 | We recently open-sourced an auto-evaluator tool for grading LLM question-answer chains. We are now releasing an open source, free to use hosted app and API to expand usability. Below we discuss a few opportunities to further improve May 1, 2023 5 min read Callbacks Improvements TL;DR: We're announcing improvements to o... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-3 | discussions around a single agent. If multiple Apr 28, 2023 4 min read Gradio & LLM Agents Editor's note: this is a guest blog post from Freddy Boulton, a software engineer at Gradio. We're excited to share this post because it brings a large number of exciting new tools into the ecosystem. Agents are largely defined b... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-4 | 💡 TL;DR: We’ve introduced a new abstraction and a new document Retriever to facilitate the post-processing of retrieved documents. Specifically, the new abstraction makes it easy to take a set of retrieved documents and extract from them Apr 20, 2023 3 min read Autonomous Agents & Agent Simulations Over the past two w... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-5 | Context
Originally we designed LangChain.js to run in Node.js, which is the Apr 11, 2023 3 min read LangChain x Supabase Supabase is holding an AI Hackathon this week. Here at LangChain we are big fans of both Supabase and hackathons, so we thought this would be a perfect time to highlight the multiple ways you can use... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-6 | The reason we like Supabase so much is that Apr 8, 2023 2 min read Announcing our $10M seed round led by Benchmark It was only six months ago that we released the first version of LangChain, but it seems like several years. When we launched, generative AI was starting to go mainstream: stable diffusion had just been re... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-7 | This is done with the goals of (1) allowing retrievers constructed elsewhere to be used more easily in LangChain, (2) encouraging more experimentation with alternative Mar 23, 2023 4 min read LangChain + Zapier Natural Language Actions (NLA) We are super excited to team up with Zapier and integrate their new Zapier NLA... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-8 | Ingham and Jon Luo are two of the community members leading the change on the SQL integrations. We’re really excited to write this blog post with them going over all the tips and tricks they’ve learned doing so. We’re even more excited to announce that we’ Mar 13, 2023 8 min read Origin Web Browser [Editor's Note]: Thi... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-9 | Authors: Parth Asawa (pgasawa@), Ayushi Batwara (ayushi.batwara@), Jason Mar 8, 2023 4 min read Prompt Selectors One common complaint we've heard is that the default prompt templates do not work equally well for all models. This became especially pronounced this past week when OpenAI released a ChatGPT API. This new AP... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-10 | What does this mean? It means that all your favorite prompts, chains, and agents are all recreatable in TypeScript natively. Both the Python version and TypeScript version utilize the same serializable format, meaning that artifacts can seamlessly be shared between languages. As an Feb 17, 2023 2 min read Streaming Sup... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-11 | "url": "https://xkcd.com/"
}
}
```
Observation: Navigating to https://xkcd.com/ returned status code 200
Thought:I can extract the latest comic title and alt text using CSS selectors.
Action:
```
{
"action": "get_elements",
"action_input": {
"selector": "#ctitle, #comic img",
"attributes": ["alt", "src"]
... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
d0ea7d2dad59-12 | Action:
```
{
"action": "Final Answer",
"action_input": "Hi Erica! How can I assist you today?"
}
```
> Finished chain.
Hi Erica! How can I assist you today?
response = await agent_chain.arun(input="whats my name?")
print(response)
> Entering new AgentExecutor chain...
Your name is Erica.
> Finished chain.
Your nam... | https://python.langchain.com/en/latest/modules/agents/agents/examples/structured_chat.html |
da59f7c3f1da-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... | https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
da59f7c3f1da-1 | > Entering new AgentExecutor chain...
{
"action": "Final Answer",
"action_input": "Hello Bob! How can I assist you today?"
}
> Finished chain.
'Hello Bob! How can I assist you today?'
agent_chain.run(input="what's my name?")
> Entering new AgentExecutor chain...
{
"action": "Final Answer",
"action_input... | https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
da59f7c3f1da-2 | > Entering new AgentExecutor chain...
{
"action": "Final Answer",
"action_input": "The last letter in your name is 'b'. Argentina won the World Cup in 1978."
}
> Finished chain.
"The last letter in your name is 'b'. Argentina won the World Cup in 1978."
agent_chain.run(input="whats the weather like in pomfret?"... | https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html |
c8317f7889ba-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(... | https://python.langchain.com/en/latest/modules/agents/agents/examples/self_ask_with_search.html |
ce4ecc308bb5-0 | .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())... | https://python.langchain.com/en/latest/modules/agents/agents/examples/react.html |
ce4ecc308bb5-1 | 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... | https://python.langchain.com/en/latest/modules/agents/agents/examples/react.html |
474b1399adc6-0 | .ipynb
.pdf
Jira
Jira#
This notebook goes over how to use the Jira tool.
The Jira tool allows agents to interact with a given Jira instance, performing actions such as searching for issues and creating issues, the tool wraps the atlassian-python-api library, for more see: https://atlassian-python-api.readthedocs.io/jir... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
474b1399adc6-1 | Observation: None
Thought: I now know the final answer
Final Answer: A new issue has been created in project PW with the summary "Make more fried rice" and description "Reminder to make more fried rice".
> Finished chain.
'A new issue has been created in project PW with the summary "Make more fried rice" and descriptio... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
853049187113-0 | .ipynb
.pdf
Spark SQL Agent
Contents
Initialization
Example: describing a table
Example: running queries
Spark SQL Agent#
This notebook shows how to use agents to interact with a Spark SQL. Similar to SQL Database Agent, it is designed to address general inquiries about Spark SQL and facilitate error recovery.
NOTE: ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-1 | +-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
| 1| 0| 3|Braund, Mr. Owen ...| male|22.0| 1| 0| A/5 21171| 7.25| null| S|
| 2| 1| 1|Cumings, Mrs. Joh...|female|38.0| 1| 0| PC 17599... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-2 | | 7| 0| 1|McCarthy, Mr. Tim...| male|54.0| 0| 0| 17463|51.8625| E46| S|
| 8| 0| 3|Palsson, Master. ...| male| 2.0| 3| 1| 349909| 21.075| null| S|
| 9| 1| 3|Johnson, Mrs. Osc...|female|27.0| 0| 2| 347742... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-3 | | 14| 0| 3|Andersson, Mr. An...| male|39.0| 1| 5| 347082| 31.275| null| S|
| 15| 0| 3|Vestrom, Miss. Hu...|female|14.0| 0| 0| 350406| 7.8542| null| S|
| 16| 1| 2|Hewlett, Mrs. (Ma...|female|55.0| 0| 0| 248706... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-4 | only showing top 20 rows
# Note, you can also connect to Spark via Spark connect. For example:
# db = SparkSQL.from_uri("sc://localhost:15002", schema=schema)
spark_sql = SparkSQL(schema=schema)
llm = ChatOpenAI(temperature=0)
toolkit = SparkSQLToolkit(db=spark_sql, llm=llm)
agent_executor = create_spark_sql_agent(
... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-5 | 3 1 3 Heikkinen, Miss. Laina female 26.0 0 0 STON/O2. 3101282 7.925 None S
*/
Thought:I now know the schema and sample rows for the titanic table.
Final Answer: The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (IN... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-6 | > Finished chain.
'The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table: \n\n1. PassengerId: 1, Su... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-7 | Action: list_tables_sql_db
Action Input:
Observation: titanic
Thought:I should check the schema of the titanic table to see if there is an age column.
Action: schema_sql_db
Action Input: titanic
Observation: CREATE TABLE langchain_example.titanic (
PassengerId INT,
Survived INT,
Pclass INT,
Name STRING,
Sex ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-8 | SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic
Thought:The query is correct, so I can execute it to find the square root of the average age.
Action: query_sql_db
Action Input: SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic
Observation: [('5.449689683556195',)]
Thought:I now know the final an... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
853049187113-9 | 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38.0 1 0 PC 17599 71.2833 C85 C
3 1 3 Heikkinen, Miss. Laina female 26.0 0 0 STON/O2. 3101282 7.925 None S
*/
Thought:I can use the titanic table to find the oldest survived passenger. I will query the Name and Age columns, filtering by Survived and order... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark_sql.html |
341968d71521-0 | .ipynb
.pdf
PowerBI Dataset Agent
Contents
Some notes
Initialization
Example: describing a table
Example: simple query on a table
Example: running queries
Example: add your own few-shot prompts
PowerBI Dataset Agent#
This notebook showcases an agent designed to interact with a Power BI Dataset. The agent is designed ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
341968d71521-1 | toolkit = PowerBIToolkit(
powerbi=PowerBIDataset(dataset_id="<dataset_id>", table_names=['table1', 'table2'], credential=DefaultAzureCredential()),
llm=smart_llm
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
Example: describing a table#
agent_executor.run("Desc... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
341968d71521-2 | examples=few_shots,
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
agent_executor.run("What was the maximum of value in revenue in dollars in 2022?")
previous
PlayWright Browser Toolkit
next
Python Agent
Contents
Some notes
Initialization
Example: describing a table
... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
e19942e6076d-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... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-1 | Action: schema_sql_db
Action Input: "PlaylistTrack"
Observation:
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId"... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-2 | Thought: The table is called PlaylistTrack
Action: schema_sql_db
Action Input: "PlaylistTrack"
Observation:
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("Playl... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-3 | "Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("Emplo... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-4 | "BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
SELECT * FROM 'Invoice' LIMIT 3;
InvoiceId CustomerId Invoice... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-5 | Observation: [('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]
Th... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-6 | "TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
SELECT * FROM 'PlaylistTrack' LIMIT 3;
PlaylistId TrackId
1 3402
1 3389
1 3390
Thought: I can use a SELECT statement to get the... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-7 | 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' (... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-8 | 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 NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-9 | "InvoiceId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
"Quantity" INTEGER NOT NULL,
PRIMARY KEY ("InvoiceLineId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)
SELECT * FROM 'InvoiceLine' LIMIT 3;... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
e19942e6076d-10 | Thought: I should double check my query before executing it.
Action: query_checker_sql_db
Action Input: 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... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.