id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 59 127 |
|---|---|---|
ed4adcbf338f-12 | previous
Spark SQL Agent
next
Vectorstore Agent
Contents
Initialization
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
Example: describing a table
Example: describing a table, recovering from an error
Example: running queries
Recovering from an error
By Harrison Chase
© Copyright 2023, Harrison... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html |
68108dd505d5-0 | .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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/powerbi.html |
68108dd505d5-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/powerbi.html |
68108dd505d5-2 | 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
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/powerbi.html |
e64ab912084b-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: ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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(
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
e64ab912084b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark_sql.html |
805b1a25a4e7-0 | .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 d... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-1 | 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 ty... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-2 | 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/L... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-3 | 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/Lib... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-4 | '[{"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 vi... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-6 | 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 fi... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-7 | 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 Africa... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-8 | {"innerText": "Bureaucracy stalling at least one family\\u2019s 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 speci... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-9 | 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"}]' | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-10 | # 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. T... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
805b1a25a4e7-11 | ```
{
"action": "get_elements",
"action_input": {
"selector": "h1, h2, h3, h4, h5, h6"
}
}
```
Observation: []
Thought: Thought: I need to navigate to langchain.com to see the headers
Action:
```
{
"action": "navigate_browser",
"action_input": "https://langchain.com/"
}
```
Observation: Navigating to http... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/playwright.html |
6302e75ce9d7-0 | .ipynb
.pdf
Azure Cognitive Services Toolkit
Contents
Create the Toolkit
Use within an Agent
Azure Cognitive Services Toolkit#
This toolkit is used to interact with the Azure Cognitive Services API to achieve some multimodal capabilities.
Currently There are four tools bundled in this toolkit:
AzureCogsImageAnalysisT... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/azure_cognitive_services.html |
6302e75ce9d7-1 | [tool.name for tool in toolkit.get_tools()]
['Azure Cognitive Services Image Analysis',
'Azure Cognitive Services Form Recognizer',
'Azure Cognitive Services Speech2Text',
'Azure Cognitive Services Text2Speech']
Use within an Agent#
from langchain import OpenAI
from langchain.agents import initialize_agent, AgentTyp... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/azure_cognitive_services.html |
6302e75ce9d7-2 | audio_file = agent.run("Tell me a joke and read it out for me.")
> Entering new AgentExecutor chain...
Action:
```
{
"action": "Azure Cognitive Services Text2Speech",
"action_input": "Why did the chicken cross the playground? To get to the other slide!"
}
```
Observation: /tmp/tmpa3uu_j6b.wav
Thought: I have the au... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/azure_cognitive_services.html |
34841874c7d6-0 | .ipynb
.pdf
Pandas Dataframe Agent
Contents
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
Multi DataFrame Example
Pandas Dataframe Agent#
This notebook shows how to use agents to interact with a pandas dataframe. It is mostly optimized for question answering.
NOTE: this agent calls the Python agent under t... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/pandas.html |
34841874c7d6-1 | > Entering new AgentExecutor chain...
Thought: I need to count the number of people with more than 3 siblings
Action: python_repl_ast
Action Input: df[df['SibSp'] > 3].shape[0]
Observation: 30
Thought: I now know the final answer
Final Answer: 30 people have more than 3 siblings.
> Finished chain.
'30 people have more ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/pandas.html |
34841874c7d6-2 | df1["Age"] = df1["Age"].fillna(df1["Age"].mean())
agent = create_pandas_dataframe_agent(OpenAI(temperature=0), [df, df1], verbose=True)
agent.run("how many rows in the age column are different?")
> Entering new AgentExecutor chain...
Thought: I need to compare the age columns in both dataframes
Action: python_repl_ast
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/pandas.html |
f73d2c679031-0 | .ipynb
.pdf
Python Agent
Contents
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/python.html |
f73d2c679031-1 | return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
fibonacci(10)`
The 10th Fibonacci number is 55.
> Finished chain.
'The 10th Fibonacci number is 55.'
Training neural net#
This example was created by Samee Ur Rehman.
agent_executor.run("""Understand, write a single neur... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/python.html |
f73d2c679031-2 | > Entering new chain...
Could not parse tool input: {'name': 'python', 'arguments': 'import torch\nimport torch.nn as nn\nimport torch.optim as optim\n\n# Define the neural network\nclass SingleNeuron(nn.Module):\n def __init__(self):\n super(SingleNeuron, self).__init__()\n self.linear = nn.Linear(1,... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/python.html |
f73d2c679031-3 | Invoking: `Python_REPL` with `import torch
import torch.nn as nn
import torch.optim as optim
# Define the neural network
class SingleNeuron(nn.Module):
def __init__(self):
super(SingleNeuron, self).__init__()
self.linear = nn.Linear(1, 1)
def forward(self, x):
return self.linear... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/python.html |
f73d2c679031-4 | Epoch 200: Loss = 0.02100197970867157
Epoch 300: Loss = 0.01152981910854578
Epoch 400: Loss = 0.006329738534986973
Epoch 500: Loss = 0.0034749575424939394
Epoch 600: Loss = 0.0019077073084190488
Epoch 700: Loss = 0.001047312980517745
Epoch 800: Loss = 0.0005749554838985205
Epoch 900: Loss = 0.0003156439634039998
Epoch ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/python.html |
06fffc39337b-0 | .ipynb
.pdf
Spark Dataframe Agent
Contents
Spark Connect Example
Spark Dataframe Agent#
This notebook shows how to use agents to interact with a Spark dataframe and Spark Connect. It is mostly optimized for question answering.
NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-4 | only showing top 20 rows
agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)
agent.run("how many rows are there?")
> Entering new AgentExecutor chain...
Thought: I need to find out how many rows are in the dataframe
Action: python_repl_ast
Action Input: df.count()
Observation: 891
Thoug... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-5 | Thought: I now have the math library imported, I can get the square root
Action: python_repl_ast
Action Input: math.sqrt(29.69911764705882)
Observation: 5.449689683556195
Thought: I now know the final answer
Final Answer: 5.449689683556195
> Finished chain.
'5.449689683556195'
spark.stop()
Spark Connect Example#
# in a... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-6 | df.show()
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
|PassengerId|Survived|Pclass| Name| Sex| Age|SibSp|Parch| Ticket| Fare|Cabin|Embarked|
+-----------+--------+------+--------------------+------+----+-----+-----+------... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-7 | | 6| 0| 3| Moran, Mr. James| male|null| 0| 0| 330877| 8.4583| null| Q|
| 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-8 | | 13| 0| 3|Saundercock, Mr. ...| male|20.0| 0| 0| A/5. 2151| 8.05| null| S|
| 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
06fffc39337b-9 | | 20| 1| 3|Masselmani, Mrs. ...|female|null| 0| 0| 2649| 7.225| null| C|
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
only showing top 20 rows
from langchain.agents import create_spark_dataframe_agent
from la... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/spark.html |
a664f63e805d-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/jira.html |
a664f63e805d-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/jira.html |
0143e874a04e-0 | .ipynb
.pdf
Gmail Toolkit
Contents
Create the Toolkit
Customizing Authentication
Use within an Agent
Gmail Toolkit#
This notebook walks through connecting a LangChain email to the Gmail API.
To use this toolkit, you will need to set up your credentials explained in the Gmail API docs. Once you’ve downloaded the crede... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/gmail.html |
0143e874a04e-1 | tools = toolkit.get_tools()
tools
[GmailCreateDraft(name='create_gmail_draft', description='Use this tool to create a draft email with the provided message fields.', args_schema=<class 'langchain.tools.gmail.create_draft.CreateDraftSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/gmail.html |
0143e874a04e-2 | GmailGetThread(name='get_gmail_thread', description=('Use this tool to search for email messages. The input must be a valid Gmail query. The output is a JSON list of messages.',), args_schema=<class 'langchain.tools.gmail.get_thread.GetThreadSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/gmail.html |
0143e874a04e-3 | WARNING:root:Failed to persist run: {"detail":"Not Found"}
"The latest email in your drafts is from hopefulparrot@gmail.com with the subject 'Collaboration Opportunity'. The body of the email reads: 'Dear [Friend], I hope this letter finds you well. I am writing to you in the hopes of rekindling our friendship and to d... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/gmail.html |
76464081f6eb-0 | .ipynb
.pdf
OpenAPI agents
Contents
1st example: hierarchical planning agent
To start, let’s collect some OpenAPI specs.
How big is this spec?
Let’s see some examples!
Try another API.
2nd example: “json explorer” agent
OpenAPI agents#
We can construct agents to consume arbitrary APIs, here APIs conformant to the Ope... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-1 | !mv openapi.yaml spotify_openapi.yaml
--2023-03-31 15:45:56-- https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercont... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-2 | --2023-03-31 15:45:57-- https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|18... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-3 | You’ll have to set up an application in the Spotify developer console, documented here, to get credentials: CLIENT_ID, CLIENT_SECRET, and REDIRECT_URI.
To get an access tokens (and keep them fresh), you can implement the oauth flows, or you can use spotipy. If you’ve set your Spotify creedentials as environment variabl... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-4 | from langchain.agents.agent_toolkits.openapi import planner
llm = OpenAI(model_name="gpt-4", temperature=0.0)
/Users/jeremywelborn/src/langchain/langchain/llms/openai.py:169: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: `from langchain.chat_mo... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-5 | Action: api_controller
Action Input: 1. GET /search to search for the album "Kind of Blue"
2. GET /albums/{id}/tracks to get the tracks from the "Kind of Blue" album
3. GET /me to get the current user's information
4. POST /users/{user_id}/playlists to create a new playlist named "Machine Blues" for the current user
5.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-6 | Observation: 7lzoEi44WOISnFYlrAIqyX
Thought:Action: requests_post
Action Input: {"url": "https://api.spotify.com/v1/playlists/7lzoEi44WOISnFYlrAIqyX/tracks", "data": {"uris": ["spotify:track:7q3kkfAVpmcZ8g6JUThi3o"]}, "output_instructions": "Confirm that the track was added to the playlist"}
Observation: The track was ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-7 | Observation: 1. GET /me to get the current user's information
2. GET /recommendations/available-genre-seeds to retrieve a list of available genres
3. GET /recommendations with the seed_genre parameter set to "blues" to get a blues song recommendation for the user
Thought:I have the plan, now I need to execute the API c... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-8 | Observation: acoustic, afrobeat, alt-rock, alternative, ambient, anime, black-metal, bluegrass, blues, bossanova, brazil, breakbeat, british, cantopop, chicago-house, children, chill, classical, club, comedy, country, dance, dancehall, death-metal, deep-house, detroit-techno, disco, disney, drum-and-bass, dub, dubstep,... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-9 | Observation: [
{
id: '03lXHmokj9qsXspNsPoirR',
name: 'Get Away Jordan'
}
]
Thought:I am finished executing the plan.
Final Answer: The recommended blues song for user Jeremy Welborn (ID: 22rhrz4m4kvpxlsb5hezokzwi) is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.
> Finished chain.
Observation:... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-10 | openai_agent.run(user_query)
> Entering new AgentExecutor chain...
Action: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice
Observation: 1. GET /engines to retrieve the list of available engines
2. POST /completions with the selected engine and a prompt for generating a s... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-11 | Thought:I will use the "davinci" engine to generate a short piece of advice.
Action: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"engine": "davinci", "prompt": "Give me a short piece of advice on how to be more productive."}, "output_instructions": "Extract the text from the fi... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-12 | > Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.openai.com/v1/models", "output_instructions": "Extract the ids of the available models"}
Observation: babbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-13 | 3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice
Thought:I have an updated plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /models to retrieve the list of available models
2. Choose a suitable mod... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-14 | > Finished chain.
'A short piece of advice for improving communication skills is to make sure to listen.'
Takes awhile to get there!
2nd example: “json explorer” agent#
Here’s an agent that’s not particularly practical, but neat! The agent has access to 2 toolkits. One comprises tools to interact with json: one tool to... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-15 | Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
Thought: I should look at the servers key to see what the base url is
Action: json_spec_list_keys
Action Input: data["servers"][0]
Observation: ValueError('Value at path `data["servers"... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-16 | Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-17 | Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-18 | Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]
Observation: ['schema']
Thought: I should look at the schema key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-19 | > Finished chain.
Observation: The required parameters for a POST request to the /completions endpoint are 'model'.
Thought: I now know the parameters needed to make the request.
Action: requests_post
Action Input: { "url": "https://api.openai.com/v1/completions", "data": { "model": "davinci", "prompt": "tell me a joke... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
76464081f6eb-20 | > Finished chain.
'The response of the POST request is {"id":"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv","object":"text_completion","created":1680307139,"model":"davinci","choices":[{"text":" with mummy not there”\\n\\nYou dig deep and come up with,","index":0,"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi.html |
179faf895f47-0 | .ipynb
.pdf
Vectorstore Agent
Contents
Create the Vectorstores
Initialize Toolkit and Agent
Examples
Multiple Vectorstores
Examples
Vectorstore Agent#
This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources.
Create the Vectorstores#
from langchai... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
179faf895f47-1 | )
vectorstore_info = VectorStoreInfo(
name="state_of_union_address",
description="the most recent state of the Union adress",
vectorstore=state_of_union_store
)
toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)
agent_executor = create_vectorstore_agent(
llm=llm,
toolkit=toolkit,
ve... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
179faf895f47-2 | Action Input: What did biden say about ketanji brown jackson
Observation: {"answer": " Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n", "s... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
179faf895f47-3 | toolkit=router_toolkit,
verbose=True
)
Examples#
agent_executor.run("What did biden say about ketanji brown jackson in the state of the union address?")
> Entering new AgentExecutor chain...
I need to use the state_of_union_address tool to answer this question.
Action: state_of_union_address
Action Input: What did... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
179faf895f47-4 | Thought: I now know the final answer
Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb
> Finished chain.
'Ruff is integrated into nbQA, a tool for running... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
179faf895f47-5 | previous
SQL Database Agent
next
Agent Executors
Contents
Create the Vectorstores
Initialize Toolkit and Agent
Examples
Multiple Vectorstores
Examples
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/vectorstore.html |
2953fa091fda-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-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.
Create the Agent#
# Slightly twe... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-2 | Action: Open_AI_Klarna_product_Api.productsUsingGET
Action Input: Italian clothes
Observation: The API response contains two products from the Alé brand in Italian Blue. The first is the Alé Colour Block Short Sleeve Jersey Men - Italian Blue, which costs $86.49, and the second is the Alé Dolid Flash Jersey Men - Itali... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-3 | llm,
"https://spoonacular.com/application/frontend/downloads/spoonacular-openapi-3.json",
requests=requests,
max_text_length=1800, # If you want to truncate the response text
)
Attempting to load an OpenAPI 3.0.0 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for be... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-4 | Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Content-Type. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-5 | Action: spoonacular_API.searchRecipes
Action Input: Italian
Observation: The API response contains 10 Italian recipes, including Turkey Tomato Cheese Pizza, Broccolini Quinoa Pilaf, Bruschetta Style Pork & Pasta, Salmon Quinoa Risotto, Italian Tuna Pasta, Roasted Brussels Sprouts With Garlic, Asparagus Lemon Risotto, I... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
2953fa091fda-6 | > Finished chain.
'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 Tomato Cheese Pizza, Broccolini Quino... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/openapi_nla.html |
0fb84d3c40b8-0 | .ipynb
.pdf
JSON Agent
Contents
Initialization
Example: getting the required POST parameters for a request
JSON Agent#
This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that’s too large to fit in the context window of... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/json.html |
0fb84d3c40b8-1 | Thought: I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/json.html |
0fb84d3c40b8-2 | Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]
Observation: ['application/json']
Thought: I should look at the application/json key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/json.html |
0fb84d3c40b8-3 | Initialization
Example: getting the required POST parameters for a request
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/json.html |
1f8b27c186bf-0 | .ipynb
.pdf
CSV Agent
Contents
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
Multi CSV Example
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 Py... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/csv.html |
1f8b27c186bf-1 | agent.run("how many people have more than 3 siblings")
Error in on_chain_start callback: 'name'
Invoking: `python_repl_ast` with `df[df['SibSp'] > 3]['PassengerId'].count()`
30There are 30 people in the dataframe who have more than 3 siblings.
> Finished chain.
'There are 30 people in the dataframe who have more than 3... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/csv.html |
1f8b27c186bf-2 | -1There is 1 row in the age column that is different between the two dataframes.
> Finished chain.
'There is 1 row in the age column that is different between the two dataframes.'
previous
Azure Cognitive Services Toolkit
next
Gmail Toolkit
Contents
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
Multi CSV... | rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/csv.html |
bdcd3a012add-0 | .md
.pdf
Deployments
Contents
Anyscale
Streamlit
Gradio (on Hugging Face)
Chainlit
Beam
Vercel
FastAPI + Vercel
Kinsta
Fly.io
Digitalocean App Platform
Google Cloud Run
SteamShip
Langchain-serve
BentoML
Databutton
Deployments#
So, you’ve created a really cool chain - now what? How do you deploy it and make it easily ... | rtdocs_stable/api.python.langchain.com/en/stable/ecosystem/deployments.html |
bdcd3a012add-1 | This is heavily influenced by James Weaver’s excellent examples.
Chainlit#
This repo is a cookbook explaining how to visualize and deploy LangChain agents with Chainlit.
You create ChatGPT-like UIs with Chainlit. Some of the key features include intermediary steps visualisation, element management & display (images, te... | rtdocs_stable/api.python.langchain.com/en/stable/ecosystem/deployments.html |
bdcd3a012add-2 | BentoML#
This repository provides an example of how to deploy a LangChain application with BentoML. BentoML is a framework that enables the containerization of machine learning applications as standard OCI images. BentoML also allows for the automatic generation of OpenAPI and gRPC endpoints. With BentoML, you can inte... | rtdocs_stable/api.python.langchain.com/en/stable/ecosystem/deployments.html |
21d345307eec-0 | Source code for langchain.requests
"""Lightweight wrapper around requests library, with async support."""
from contextlib import asynccontextmanager
from typing import Any, AsyncGenerator, Dict, Optional
import aiohttp
import requests
from pydantic import BaseModel, Extra
class Requests(BaseModel):
"""Wrapper aroun... | rtdocs_stable/api.python.langchain.com/en/stable/_modules/langchain/requests.html |
21d345307eec-1 | def delete(self, url: str, **kwargs: Any) -> requests.Response:
"""DELETE the URL and return the text."""
return requests.delete(url, headers=self.headers, **kwargs)
@asynccontextmanager
async def _arequest(
self, method: str, url: str, **kwargs: Any
) -> AsyncGenerator[aiohttp.Clien... | rtdocs_stable/api.python.langchain.com/en/stable/_modules/langchain/requests.html |
21d345307eec-2 | """PATCH the URL and return the text asynchronously."""
async with self._arequest("PATCH", url, **kwargs) as response:
yield response
@asynccontextmanager
async def aput(
self, url: str, data: Dict[str, Any], **kwargs: Any
) -> AsyncGenerator[aiohttp.ClientResponse, None]:
... | rtdocs_stable/api.python.langchain.com/en/stable/_modules/langchain/requests.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.