id stringlengths 14 15 | text stringlengths 17 2.72k | source stringlengths 47 115 |
|---|---|---|
4bf4e892bacb-6 | > Finished chain.
Observation: Some basic advice for improving communication skills would be to make sure to listen.
Thought:I am finished executing the plan and have the information the user asked for.
Final Answer: A short piece of advice for improving communication skills is to make sure to listen.
> Finished chain.
'A short piece of advice for improving communication skills is to make sure to listen.'
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 list the keys of a json object and another tool to get the value for a given key. The other toolkit comprises requests wrappers to send GET and POST requests. This agent consumes a lot calls to the language model, but does a surprisingly decent job.
with open("openai_openapi.yaml") as f:
data = yaml.load(f, Loader=yaml.FullLoader)
json_spec = JsonSpec(dict_=data, max_value_length=4000)
openapi_toolkit = OpenAPIToolkit.from_llm(
OpenAI(temperature=0), json_spec, openai_requests_wrapper, verbose=True
)
openapi_agent_executor = create_openapi_agent(
llm=OpenAI(temperature=0), toolkit=openapi_toolkit, verbose=True
)
> Entering new AgentExecutor chain...
Action: json_explorer
Action Input: What is the base url for the API?
> Entering new AgentExecutor chain...
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"][0]` is not a dict, get the value directly.')
Thought: I should get the value of the servers key
Action: json_spec_get_value
Action Input: data["servers"][0]
Observation: {'url': 'https://api.openai.com/v1'}
Thought: I now know the base url for the API
Final Answer: The base url for the API is https://api.openai.com/v1
> Finished chain. | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-7 | > Finished chain.
Observation: The base url for the API is https://api.openai.com/v1
Thought: I should find the path for the /completions endpoint.
Action: json_explorer
Action Input: What is the path for the /completions endpoint?
> Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
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', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']
Thought: I now know the path for the /completions endpoint
Final Answer: The path for the /completions endpoint is data["paths"][2]
> Finished chain.
Observation: The path for the /completions endpoint is data["paths"][2]
Thought: I should find the required parameters for the POST request.
Action: json_explorer
Action Input: What are the required parameters for a POST request to the /completions endpoint? | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-8 | > Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
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', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']
Thought: I should look at the /completions endpoint to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]
Observation: ['post']
Thought: I should look at the post key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]
Observation: ['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']
Thought: I should look at the requestBody key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]
Observation: ['required', 'content']
Thought: I should look at the content key to see what parameters are required
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"]["content"]["application/json"]
Observation: ['schema'] | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-9 | 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"]["content"]["application/json"]["schema"]
Observation: ['$ref']
Thought: I should look at the $ref key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"]
Observation: ValueError('Value at path `data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"]` is not a dict, get the value directly.')
Thought: I should look at the $ref key to get the value directly
Action: json_spec_get_value
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]["schema"]["$ref"]
Observation: #/components/schemas/CreateCompletionRequest
Thought: I should look at the CreateCompletionRequest schema to see what parameters are required
Action: json_spec_list_keys
Action Input: data["components"]["schemas"]["CreateCompletionRequest"]
Observation: ['type', 'properties', 'required']
Thought: I should look at the required key to see what parameters are required
Action: json_spec_get_value
Action Input: data["components"]["schemas"]["CreateCompletionRequest"]["required"]
Observation: ['model']
Thought: I now know the final answer
Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'. | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-10 | > 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" } }
Observation: {"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":4,"completion_tokens":16,"total_tokens":20}}
Thought: I now know the final answer.
Final Answer: 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":4,"completion_tokens":16,"total_tokens":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":4,"completion_tokens":16,"total_tokens":20}}' | https://python.langchain.com/docs/integrations/toolkits/openapi |
460b8e35d6d0-0 | Pandas Dataframe
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 the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.
from langchain.agents import create_pandas_dataframe_agent
from langchain.chat_models import ChatOpenAI
from langchain.agents.agent_types import AgentType
from langchain.llms import OpenAI
import pandas as pd
df = pd.read_csv("titanic.csv")
Using ZERO_SHOT_REACT_DESCRIPTION
This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type. Note that this is an alternative to the above.
agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)
Using OpenAI Functions
This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above.
agent = create_pandas_dataframe_agent(
ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
df,
verbose=True,
agent_type=AgentType.OPENAI_FUNCTIONS,
)
agent.run("how many rows are there?")
> Entering new chain...
Invoking: `python_repl_ast` with `df.shape[0]`
891There are 891 rows in the dataframe.
> Finished chain.
'There are 891 rows in the dataframe.'
agent.run("how many people have more than 3 siblings")
> 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 than 3 siblings.'
agent.run("whats the square root of the average age?") | https://python.langchain.com/docs/integrations/toolkits/pandas |
460b8e35d6d0-1 | > 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 now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: NameError("name 'math' is not defined")
Thought: I need to import the math library
Action: python_repl_ast
Action Input: import math
Observation:
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: 5.449689683556195
Thought: I now know the final answer
Final Answer: The square root of the average age is 5.449689683556195.
> Finished chain.
'The square root of the average age is 5.449689683556195.'
Multi DataFrame Example
This next part shows how the agent can interact with multiple dataframes passed in as a list.
df1 = df.copy()
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
Action Input: len(df1[df1['Age'] != df2['Age']])
Observation: 177
Thought: I now know the final answer
Final Answer: 177 rows in the age column are different.
> Finished chain.
'177 rows in the age column are different.' | https://python.langchain.com/docs/integrations/toolkits/pandas |
31dbda54a9f3-0 | This toolkit is used to interact with the browser. While other tools (like the Requests tools) are fine for static sites, PlayWright Browser toolkits let your agent navigate the web and interact with dynamically rendered sites.
[ClickTool(name='click_element', description='Click on an element with the given CSS selector', args_schema=<class 'langchain.tools.playwright.click.ClickToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
NavigateTool(name='navigate_browser', description='Navigate a browser to the specified URL', args_schema=<class 'langchain.tools.playwright.navigate.NavigateToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
NavigateBackTool(name='previous_webpage', description='Navigate back to the previous page in the browser history', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
ExtractTextTool(name='extract_text', description='Extract all the text on the current webpage', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>), | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-1 | ExtractHyperlinksTool(name='extract_hyperlinks', description='Extract all hyperlinks on the current webpage', args_schema=<class 'langchain.tools.playwright.extract_hyperlinks.ExtractHyperlinksToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
GetElementsTool(name='get_elements', description='Retrieve elements in the current web page matching the given CSS selector', args_schema=<class 'langchain.tools.playwright.get_elements.GetElementsToolInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>),
CurrentWebPageTool(name='current_webpage', description='Returns the URL of the current page', args_schema=<class 'pydantic.main.BaseModel'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, sync_browser=None, async_browser=<Browser type=<BrowserType name=chromium executable_path=/Users/wfh/Library/Caches/ms-playwright/chromium-1055/chrome-mac/Chromium.app/Contents/MacOS/Chromium> version=112.0.5615.29>)] | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-2 | '[{"innerText": "These Ukrainian veterinarians are risking their lives to care for dogs and cats in the war zone"}, {"innerText": "Life in the ocean\\u2019s \\u2018twilight zone\\u2019 could disappear due to the climate crisis"}, {"innerText": "Clashes renew in West Darfur as food and water shortages worsen in Sudan violence"}, {"innerText": "Thai policeman\\u2019s wife investigated over alleged murder and a dozen other poison cases"}, {"innerText": "American teacher escaped Sudan on French evacuation plane, with no help offered back home"}, {"innerText": "Dubai\\u2019s emerging hip-hop scene is finding its voice"}, {"innerText": "How an underwater film inspired a marine protected area off Kenya\\u2019s coast"}, {"innerText": "The Iranian drones deployed by Russia in Ukraine are powered by stolen Western technology, research reveals"}, {"innerText": "India says border violations erode \\u2018entire basis\\u2019 of ties with China"}, {"innerText": "Australian police sift through 3,000 tons of trash for missing woman\\u2019s remains"}, {"innerText": "As US and Philippine defense ties grow, China warns over Taiwan tensions"}, {"innerText": "Don McLean offers duet with South Korean president who sang \\u2018American Pie\\u2019 to Biden"}, {"innerText": "Almost two-thirds of elephant habitat lost across Asia, study finds"}, {"innerText": "\\u2018We don\\u2019t sleep \\u2026 I would call it fainting\\u2019: Working as a doctor in Sudan\\u2019s crisis"}, {"innerText": "Kenya arrests second pastor to face criminal charges \\u2018related to mass killing of his followers\\u2019"}, {"innerText": "Russia launches deadly wave of strikes across Ukraine"}, {"innerText": "Woman forced to leave her forever home or \\u2018walk to your death\\u2019 she says"}, {"innerText": "U.S. House Speaker Kevin McCarthy weighs in on Disney-DeSantis feud"}, {"innerText": "Two sides agree to extend Sudan ceasefire"}, {"innerText": "Spanish Leopard 2 tanks are on their way to Ukraine, defense minister confirms"}, {"innerText": "Flamb\\u00e9ed pizza thought to have sparked deadly Madrid restaurant fire"}, {"innerText": "Another bomb found in Belgorod just | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-3 | to have sparked deadly Madrid restaurant fire"}, {"innerText": "Another bomb found in Belgorod just days after Russia accidentally struck the city"}, {"innerText": "A Black teen\\u2019s murder sparked a crisis over racism in British policing. Thirty years on, little has changed"}, {"innerText": "Belgium destroys shipment of American beer after taking issue with \\u2018Champagne of Beer\\u2019 slogan"}, {"innerText": "UK Prime Minister Rishi Sunak rocked by resignation of top ally Raab over bullying allegations"}, {"innerText": "Iran\\u2019s Navy seizes Marshall Islands-flagged ship"}, {"innerText": "A divided Israel stands at a perilous crossroads on its 75th birthday"}, {"innerText": "Palestinian reporter breaks barriers by reporting in Hebrew on Israeli TV"}, {"innerText": "One-fifth of water pollution comes from textile dyes. But a shellfish-inspired solution could clean it up"}, {"innerText": "\\u2018People sacrificed their lives for just\\u00a010 dollars\\u2019: At least 78 killed in Yemen crowd surge"}, {"innerText": "Israeli police say two men shot near Jewish tomb in Jerusalem in suspected \\u2018terror attack\\u2019"}, {"innerText": "King Charles III\\u2019s coronation: Who\\u2019s performing at the ceremony"}, {"innerText": "The week in 33 photos"}, {"innerText": "Hong Kong\\u2019s endangered turtles"}, {"innerText": "In pictures: Britain\\u2019s Queen Camilla"}, {"innerText": "Catastrophic drought that\\u2019s pushed millions into crisis made 100 times more likely by climate change, analysis finds"}, {"innerText": "For years, a UK mining giant was untouchable in Zambia for pollution until a former miner\\u2019s son took them on"}, {"innerText": "Former Sudanese minister Ahmed Haroun wanted on war crimes charges freed from Khartoum prison"}, {"innerText": "WHO warns of \\u2018biological risk\\u2019 after Sudan fighters seize lab, as violence mars US-brokered ceasefire"}, {"innerText": "How Colombia\\u2019s Petro, a former leftwing guerrilla, found his opening in Washington"}, {"innerText": "Bolsonaro accidentally created Facebook post questioning Brazil election results, say his attorneys"}, {"innerText": "Crowd kills | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-4 | accidentally created Facebook post questioning Brazil election results, say his attorneys"}, {"innerText": "Crowd kills over a dozen suspected gang members in Haiti"}, {"innerText": "Thousands of tequila bottles containing liquid meth seized"}, {"innerText": "Why send a US stealth submarine to South Korea \\u2013 and tell the world about it?"}, {"innerText": "Fukushima\\u2019s fishing industry survived a nuclear disaster. 12 years on, it fears Tokyo\\u2019s next move may finish it off"}, {"innerText": "Singapore executes man for trafficking two pounds of cannabis"}, {"innerText": "Conservative Thai party looks to woo voters with promise to legalize sex toys"}, {"innerText": "Inside the Italian village being repopulated by Americans"}, {"innerText": "Strikes, soaring airfares and yo-yoing hotel fees: A traveler\\u2019s guide to the coronation"}, {"innerText": "A year in Azerbaijan: From spring\\u2019s Grand Prix to winter ski adventures"}, {"innerText": "The bicycle mayor peddling a two-wheeled revolution in Cape Town"}, {"innerText": "Tokyo ramen shop bans customers from using their phones while eating"}, {"innerText": "South African opera star will perform at coronation of King Charles III"}, {"innerText": "Luxury loot under the hammer: France auctions goods seized from drug dealers"}, {"innerText": "Judy Blume\\u2019s books were formative for generations of readers. Here\\u2019s why they endure"}, {"innerText": "Craft, salvage and sustainability take center stage at Milan Design Week"}, {"innerText": "Life-sized chocolate King Charles III sculpture unveiled to celebrate coronation"}, {"innerText": "Severe storms to strike the South again as millions in Texas could see damaging winds and hail"}, {"innerText": "The South is in the crosshairs of severe weather again, as the multi-day threat of large hail and tornadoes continues"}, {"innerText": "Spring snowmelt has cities along the Mississippi bracing for flooding in homes and businesses"}, {"innerText": "Know the difference between a tornado watch, a tornado warning and a tornado emergency"}, {"innerText": "Reporter spotted familiar face covering Sudan evacuation. See what happened next"}, {"innerText": "This country will soon become the world\\u2019s most populated"}, {"innerText": "April 27, 2023 - Russia-Ukraine news"}, | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-5 | most populated"}, {"innerText": "April 27, 2023 - Russia-Ukraine news"}, {"innerText": "\\u2018Often they shoot at each other\\u2019: Ukrainian drone operator details chaos in Russian ranks"}, {"innerText": "Hear from family members of Americans stuck in Sudan frustrated with US response"}, {"innerText": "U.S. talk show host Jerry Springer dies at 79"}, {"innerText": "Bureaucracy stalling at least one family\\u2019s evacuation from Sudan"}, {"innerText": "Girl to get life-saving treatment for rare immune disease"}, {"innerText": "Haiti\\u2019s crime rate more than doubles in a year"}, {"innerText": "Ocean census aims to discover 100,000 previously unknown marine species"}, {"innerText": "Wall Street Journal editor discusses reporter\\u2019s arrest in Moscow"}, {"innerText": "Can Tunisia\\u2019s democracy be saved?"}, {"innerText": "Yasmeen Lari, \\u2018starchitect\\u2019 turned social engineer, wins one of architecture\\u2019s most coveted prizes"}, {"innerText": "A massive, newly restored Frank Lloyd Wright mansion is up for sale"}, {"innerText": "Are these the most sustainable architectural projects in the world?"}, {"innerText": "Step inside a $72 million London townhouse in a converted army barracks"}, {"innerText": "A 3D-printing company is preparing to build on the lunar surface. But first, a moonshot at home"}, {"innerText": "Simona Halep says \\u2018the stress is huge\\u2019 as she battles to return to tennis following positive drug test"}, {"innerText": "Barcelona reaches third straight Women\\u2019s Champions League final with draw against Chelsea"}, {"innerText": "Wrexham: An intoxicating tale of Hollywood glamor and sporting romance"}, {"innerText": "Shohei Ohtani comes within inches of making yet more MLB history in Angels win"}, {"innerText": "This CNN Hero is recruiting recreational divers to help rebuild reefs in Florida one coral at a time"}, {"innerText": "This CNN Hero offers judgment-free veterinary care for the pets of those experiencing homelessness"}, {"innerText": "Don\\u2019t give up on milestones: A CNN Hero\\u2019s message for Autism Awareness Month"}, {"innerText": "CNN Hero of the Year Nelly | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-6 | message for Autism Awareness Month"}, {"innerText": "CNN Hero of the Year Nelly Cheboi returned to Kenya with plans to lift more students out of poverty"}]' | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-7 | Several of the browser tools are StructuredTool's, meaning they expect multiple arguments. These aren't compatible (out of the box) with agents older than the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION
from langchain.agents import initialize_agent, AgentType
from langchain.chat_models import ChatAnthropic | https://python.langchain.com/docs/integrations/toolkits/playwright |
31dbda54a9f3-8 | llm = ChatAnthropic(temperature=0) # or any other LLM, e.g., ChatOpenAI(), OpenAI()
agent_chain = initialize_agent(
tools,
llm,
agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
verbose=True,
) | https://python.langchain.com/docs/integrations/toolkits/playwright |
e0c06f26f562-0 | This notebook showcases an agent interacting with a Power BI Dataset. The agent is answering more general questions about a dataset, as well as recover from errors.
Note that, as this agent is in active development, all answers might not be correct. It runs against the executequery endpoint, which does not allow deletes.
from langchain.agents.agent_toolkits import create_pbi_agent
from langchain.agents.agent_toolkits import PowerBIToolkit
from langchain.utilities.powerbi import PowerBIDataset
from langchain.chat_models import ChatOpenAI
from langchain.agents import AgentExecutor
from azure.identity import DefaultAzureCredential
fast_llm = ChatOpenAI(
temperature=0.5, max_tokens=1000, model_name="gpt-3.5-turbo", verbose=True
)
smart_llm = ChatOpenAI(temperature=0, max_tokens=100, model_name="gpt-4", verbose=True)
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,
)
In this example, the agent actually figures out the correct query to get a row count of the table.
# fictional example
few_shots = """
Question: How many rows are in the table revenue?
DAX: EVALUATE ROW("Number of rows", COUNTROWS(revenue_details))
----
Question: How many rows are in the table revenue where year is not empty?
DAX: EVALUATE ROW("Number of rows", COUNTROWS(FILTER(revenue_details, revenue_details[year] <> "")))
----
Question: What was the average of value in revenue in dollars?
DAX: EVALUATE ROW("Average", AVERAGE(revenue_details[dollar_value]))
----
"""
toolkit = PowerBIToolkit(
powerbi=PowerBIDataset(
dataset_id="<dataset_id>",
table_names=["table1", "table2"],
credential=DefaultAzureCredential(),
),
llm=smart_llm,
examples=few_shots,
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
) | https://python.langchain.com/docs/integrations/toolkits/powerbi |
6e2660f52980-0 | This notebook showcases an agent designed to write and execute Python code to answer a question.
This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type.
This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above.
agent_executor = create_python_agent(
llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
tool=PythonREPLTool(),
verbose=True,
agent_type=AgentType.OPENAI_FUNCTIONS,
agent_executor_kwargs={"handle_parsing_errors": True},
) | https://python.langchain.com/docs/integrations/toolkits/python |
6e2660f52980-1 | > 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, 1)\n \n def forward(self, x):\n return self.linear(x)\n\n# Create the synthetic data\nx_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)\ny_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)\n\n# Create the neural network\nmodel = SingleNeuron()\n\n# Define the loss function and optimizer\ncriterion = nn.MSELoss()\noptimizer = optim.SGD(model.parameters(), lr=0.01)\n\n# Train the neural network\nfor epoch in range(1, 1001):\n # Forward pass\n y_pred = model(x_train)\n \n # Compute loss\n loss = criterion(y_pred, y_train)\n \n # Backward pass and optimization\n optimizer.zero_grad()\n loss.backward()\n optimizer.step()\n \n # Print the loss every 100 epochs\n if epoch % 100 == 0:\n print(f"Epoch {epoch}: Loss = {loss.item()}")\n\n# Make a prediction for x = 5\nx_test = torch.tensor([[5.0]], dtype=torch.float32)\ny_pred = model(x_test)\ny_pred.item()'} because the `arguments` is not valid JSON.Invalid or incomplete response
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(x) | https://python.langchain.com/docs/integrations/toolkits/python |
6e2660f52980-2 | def forward(self, x):
return self.linear(x)
# Create the synthetic data
x_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)
y_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)
# Create the neural network
model = SingleNeuron()
# Define the loss function and optimizer
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)
# Train the neural network
for epoch in range(1, 1001):
# Forward pass
y_pred = model(x_train)
# Compute loss
loss = criterion(y_pred, y_train)
# Backward pass and optimization
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Print the loss every 100 epochs
if epoch % 100 == 0:
print(f"Epoch {epoch}: Loss = {loss.item()}")
# Make a prediction for x = 5
x_test = torch.tensor([[5.0]], dtype=torch.float32)
y_pred = model(x_test)
y_pred.item()`
Epoch 100: Loss = 0.03825576975941658
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 1000: Loss = 0.00017328384274151176
Invoking: `Python_REPL` with `x_test.item()`
The prediction for x = 5 is 10.000173568725586.
> Finished chain.
'The prediction for x = 5 is 10.000173568725586.' | https://python.langchain.com/docs/integrations/toolkits/python |
40144eca471f-0 | 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 code - this can be bad if the LLM generated Python code is harmful. Use cautiously.
23/05/15 20:33:10 WARN Utils: Your hostname, Mikes-Mac-mini.local resolves to a loopback address: 127.0.0.1; using 192.168.68.115 instead (on interface en1)
23/05/15 20:33:10 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
23/05/15 20:33:10 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable | https://python.langchain.com/docs/integrations/toolkits/spark |
40144eca471f-1 | +-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
|PassengerId|Survived|Pclass| Name| Sex| Age|SibSp|Parch| Ticket| Fare|Cabin|Embarked|
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
| 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|71.2833| C85| C|
| 3| 1| 3|Heikkinen, Miss. ...|female|26.0| 0| 0|STON/O2. 3101282| 7.925| null| S|
| 4| 1| 1|Futrelle, Mrs. Ja...|female|35.0| 1| 0| 113803| 53.1| C123| S|
| 5| 0| 3|Allen, Mr. Willia...| male|35.0| 0| 0| 373450| 8.05| null| S|
| 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| 21.075| null| S|
| 9| 1| 3|Johnson, Mrs. Osc...|female|27.0| 0| 2| 347742|11.1333| null| S| | https://python.langchain.com/docs/integrations/toolkits/spark |
40144eca471f-2 | | 10| 1| 2|Nasser, Mrs. Nich...|female|14.0| 1| 0| 237736|30.0708| null| C|
| 11| 1| 3|Sandstrom, Miss. ...|female| 4.0| 1| 1| PP 9549| 16.7| G6| S|
| 12| 1| 1|Bonnell, Miss. El...|female|58.0| 0| 0| 113783| 26.55| C103| S|
| 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| 7.8542| null| S|
| 16| 1| 2|Hewlett, Mrs. (Ma...|female|55.0| 0| 0| 248706| 16.0| null| S|
| 17| 0| 3|Rice, Master. Eugene| male| 2.0| 4| 1| 382652| 29.125| null| Q|
| 18| 1| 2|Williams, Mr. Cha...| male|null| 0| 0| 244373| 13.0| null| S|
| 19| 0| 3|Vander Planke, Mr...|female|31.0| 1| 0| 345763| 18.0| null| S|
| 20| 1| 3|Masselmani, Mrs. ...|female|null| 0| 0| 2649| 7.225| null| C| | https://python.langchain.com/docs/integrations/toolkits/spark |
40144eca471f-3 | +-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
only showing top 20 rows | https://python.langchain.com/docs/integrations/toolkits/spark |
683e9e2d25de-0 | Vectorstore
This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources.
Create Vectorstores
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain import OpenAI, VectorDBQA
llm = OpenAI(temperature=0)
from langchain.document_loaders import TextLoader
loader = TextLoader("../../../state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
state_of_union_store = Chroma.from_documents(
texts, embeddings, collection_name="state-of-union"
)
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
from langchain.document_loaders import WebBaseLoader
loader = WebBaseLoader("https://beta.ruff.rs/docs/faq/")
docs = loader.load()
ruff_texts = text_splitter.split_documents(docs)
ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name="ruff")
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
First, we'll create an agent with a single vectorstore.
from langchain.agents.agent_toolkits import (
create_vectorstore_agent,
VectorStoreToolkit,
VectorStoreInfo,
)
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, verbose=True)
Examples
agent_executor.run(
"What did biden say about ketanji brown jackson in the state of the union address?"
) | https://python.langchain.com/docs/integrations/toolkits/vectorstore |
683e9e2d25de-1 | > Entering new AgentExecutor chain...
I need to find the answer in the state of the union address
Action: state_of_union_address
Action Input: What did biden say about ketanji brown jackson
Observation: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.
Thought: I now know the final answer
Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.
> Finished chain.
"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence."
agent_executor.run(
"What did biden say about ketanji brown jackson in the state of the union address? List the source."
)
> Entering new AgentExecutor chain...
I need to use the state_of_union_address_with_sources tool to answer this question.
Action: state_of_union_address_with_sources
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", "sources": "../../state_of_the_union.txt"}
Thought: I now know the final answer
Final 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. Sources: ../../state_of_the_union.txt
> Finished chain. | https://python.langchain.com/docs/integrations/toolkits/vectorstore |
683e9e2d25de-2 | > Finished chain.
"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. Sources: ../../state_of_the_union.txt"
Multiple Vectorstores
We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer.
from langchain.agents.agent_toolkits import (
create_vectorstore_router_agent,
VectorStoreRouterToolkit,
VectorStoreInfo,
)
ruff_vectorstore_info = VectorStoreInfo(
name="ruff",
description="Information about the Ruff python linting library",
vectorstore=ruff_store,
)
router_toolkit = VectorStoreRouterToolkit(
vectorstores=[vectorstore_info, ruff_vectorstore_info], llm=llm
)
agent_executor = create_vectorstore_router_agent(
llm=llm, 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 biden say about ketanji brown jackson
Observation: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.
Thought: I now know the final answer
Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.
> Finished chain.
"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence."
agent_executor.run("What tool does ruff use to run over Jupyter Notebooks?") | https://python.langchain.com/docs/integrations/toolkits/vectorstore |
683e9e2d25de-3 | > Entering new AgentExecutor chain...
I need to find out what tool ruff uses to run over Jupyter Notebooks
Action: ruff
Action Input: What tool does ruff use to run over Jupyter Notebooks?
Observation: 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.html
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.html
> Finished chain.
'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.html'
agent_executor.run(
"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?"
)
> Entering new AgentExecutor chain...
I need to find out what tool ruff uses and if the president mentioned it in the state of the union.
Action: ruff
Action Input: What tool does ruff use to run over Jupyter Notebooks?
Observation: 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.html
Thought: I need to find out if the president mentioned nbQA in the state of the union.
Action: state_of_union_address
Action Input: Did the president mention nbQA in the state of the union?
Observation: No, the president did not mention nbQA in the state of the union.
Thought: I now know the final answer.
Final Answer: No, the president did not mention nbQA in the state of the union.
> Finished chain.
'No, the president did not mention nbQA in the state of the union.' | https://python.langchain.com/docs/integrations/toolkits/vectorstore |
78c68b42b7e1-0 | This notebook shows how to use agents to interact with Spark SQL. Similar to SQL Database Agent, it is designed to address general inquiries about Spark SQL and facilitate error recovery.
NOTE: Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your Spark cluster given certain questions. Be careful running it on sensitive data!
# 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(llm=llm, toolkit=toolkit, verbose=True)
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input:
Observation: titanic
Thought:I found the titanic table. Now I need to get the schema and sample rows for the titanic table.
Action: schema_sql_db
Action Input: titanic
Observation: CREATE TABLE langchain_example.titanic (
PassengerId INT,
Survived INT,
Pclass INT,
Name STRING,
Sex STRING,
Age DOUBLE,
SibSp INT,
Parch INT,
Ticket STRING,
Fare DOUBLE,
Cabin STRING,
Embarked STRING)
; | https://python.langchain.com/docs/integrations/toolkits/spark_sql |
78c68b42b7e1-1 | /*
3 rows from titanic table:
PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.25 None S
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 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 (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table:
1. PassengerId: 1, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S
2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C
3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S
> Finished chain. | https://python.langchain.com/docs/integrations/toolkits/spark_sql |
78c68b42b7e1-2 | > 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, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S\n2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C\n3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S' | https://python.langchain.com/docs/integrations/toolkits/spark_sql |
bec26ae393e2-0 | SQL Database
This notebook showcases an agent designed to interact with a SQL databases. The agent builds off of SQLDatabaseChain and is designed to answer more general questions about a database, as well as recover from errors.
Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your database given certain questions. Be careful running it on sensitive data!
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.
Initialization
from langchain.agents import create_sql_agent
from langchain.agents.agent_toolkits import SQLDatabaseToolkit
from langchain.sql_database import SQLDatabase
from langchain.llms.openai import OpenAI
from langchain.agents import AgentExecutor
from langchain.agents.agent_types import AgentType
from langchain.chat_models import ChatOpenAI
db = SQLDatabase.from_uri("sqlite:///../../../../../notebooks/Chinook.db")
toolkit = SQLDatabaseToolkit(db=db, llm=OpenAI(temperature=0))
Using ZERO_SHOT_REACT_DESCRIPTION
This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type.
agent_executor = create_sql_agent(
llm=OpenAI(temperature=0),
toolkit=toolkit,
verbose=True,
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
)
Using OpenAI Functions
This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above.
# agent_executor = create_sql_agent(
# llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
# toolkit=toolkit,
# verbose=True,
# agent_type=AgentType.OPENAI_FUNCTIONS
# )
Disclamer ⚠️
The query chain may generate insert/update/delete queries. When this is not expected, use a custom prompt or create a SQL users without write permissions.
The final user might overload your SQL database by asking a simple question such as "run the biggest query possible". The generated query might look like:
SELECT * FROM "public"."users" | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-1 | SELECT * FROM "public"."users"
JOIN "public"."user_permissions" ON "public"."users".id = "public"."user_permissions".user_id
JOIN "public"."projects" ON "public"."users".id = "public"."projects".user_id
JOIN "public"."events" ON "public"."projects".id = "public"."events".project_id;
For a transactional SQL database, if one of the table above contains millions of rows, the query might cause trouble to other applications using the same database.
Most datawarehouse oriented databases support user-level quota, for limiting resource usage.
Example: describing a table
agent_executor.run("Describe the playlisttrack table") | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-2 | > Entering new chain...
Invoking: `list_tables_sql_db` with `{}`
Album, Artist, Track, PlaylistTrack, InvoiceLine, sales_table, Playlist, Genre, Employee, Customer, Invoice, MediaType
Invoking: `schema_sql_db` with `PlaylistTrack`
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")
)
/*
3 rows from PlaylistTrack table:
PlaylistId TrackId
1 3402
1 3389
1 3390
*/The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks.
Here is the schema of the `PlaylistTrack` table:
```
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")
)
```
Here are three sample rows from the `PlaylistTrack` table:
```
PlaylistId TrackId
1 3402
1 3389
1 3390
```
Please let me know if there is anything else I can help you with.
> Finished chain. | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-3 | > Finished chain.
'The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \n\nHere is the schema of the `PlaylistTrack` table:\n\n```\nCREATE TABLE "PlaylistTrack" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\tPRIMARY KEY ("PlaylistId", "TrackId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n```\n\nHere are three sample rows from the `PlaylistTrack` table:\n\n```\nPlaylistId TrackId\n1 3402\n1 3389\n1 3390\n```\n\nPlease let me know if there is anything else I can help you with.'
Example: describing a table, recovering from an error
In this example, the agent tries to search for a table that doesn't exist, but finds the next best result
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
Action: schema_sql_db
Action Input: "PlaylistSong"
Observation: Error: table_names {'PlaylistSong'} not found in database
Thought: I should check the spelling of the table
Action: list_tables_sql_db
Action Input: ""
Observation: Genre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist
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("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
) | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-4 | SELECT * FROM 'PlaylistTrack' LIMIT 3;
PlaylistId TrackId
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 integers and are used to link Playlist and Track tables.'
Example: running queries
agent_executor.run(
"List the total sales per country. Which country's customers spent the most?"
)
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: Invoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer
Thought: I should look at the schema of the relevant tables to see what columns I can use.
Action: schema_sql_db
Action Input: "Invoice, Customer"
Observation:
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"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" ("EmployeeId")
) | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-5 | SELECT * FROM 'Customer' LIMIT 3;
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"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")
) | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-6 | 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
2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
Thought: I should query the Invoice and Customer tables to get the total sales per country.
Action: query_sql_db
Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10
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)]
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 result."
) | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-7 | > Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: Invoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer
Thought: I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.
Action: schema_sql_db
Action Input: "Playlist, PlaylistTrack"
Observation:
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
SELECT * FROM 'Playlist' LIMIT 3;
PlaylistId Name
1 Music
2 Movies
3 TV Shows
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")
)
SELECT * FROM 'PlaylistTrack' LIMIT 3;
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.PlaylistId GROUP BY Playlist.Name
Observation: | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-8 | SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name
Thought: The query looks correct, I can now execute it.
Action: query_sql_db
Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10
Observation: [('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', 6580), ('Music Videos', 1)]
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' (6580), 'Music Videos' (1).
> Finished chain.
"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' (6580), 'Music Videos' (1)."
Recovering from an error
In this example, the agent is able to recover from an error after initially trying to access an attribute (Track.ArtistId) which doesn't exist.
agent_executor.run("Who are the top 3 best selling artists?") | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-9 | > Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: MediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist
Thought: I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.
Action: schema_sql_db
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 NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL,
"GenreId" INTEGER,
"Composer" NVARCHAR(220),
"Milliseconds" INTEGER NOT NULL,
"Bytes" INTEGER,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("TrackId"),
FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
SELECT * FROM 'Track' LIMIT 3;
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99
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 | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-10 | CREATE TABLE "InvoiceLine" (
"InvoiceLineId" INTEGER NOT NULL,
"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;
InvoiceLineId InvoiceId TrackId UnitPrice Quantity
1 1 2 0.99 1
2 1 4 0.99 1
3 2 6 0.99 1
Thought: I should query the database to get the top 3 best selling artists.
Action: query_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 BY TotalQuantity DESC LIMIT 3
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 DESC LIMIT 3]
(Background on this error at: https://sqlalche.me/e/14/e3q8)
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 BY TotalQuantity DESC LIMIT 3
Observation: | https://python.langchain.com/docs/integrations/toolkits/sql_database |
bec26ae393e2-11 | 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 DESC
LIMIT 3;
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 BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3
Observation: [('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]
Thought: I now know the final answer.
Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.
> Finished chain.
'The top 3 best selling artists are Iron Maiden, U2, and Metallica.' | https://python.langchain.com/docs/integrations/toolkits/sql_database |
0a55f954a7b5-0 | Nuclia Understanding
Nuclia automatically indexes your unstructured data from any internal and external source, providing optimized search results and generative answers. It can handle video and audio transcription, image content extraction, and document parsing.
The Nuclia Understanding API supports the processing of unstructured data, including text, web pages, documents, and audio/video contents. It extracts all texts wherever it is (using speech-to-text or OCR when needed), it identifies entities, it aslo extracts metadata, embedded files (like images in a PDF), and web links. It also provides a summary of the content.
To use the Nuclia Understanding API, you need to have a Nuclia account. You can create one for free at https://nuclia.cloud, and then create a NUA key.
#!pip install --upgrade protobuf
#!pip install nucliadb-protos
import os
os.environ["NUCLIA_ZONE"] = "<YOUR_ZONE>" # e.g. europe-1
os.environ["NUCLIA_NUA_KEY"] = "<YOUR_API_KEY>"
from langchain.tools.nuclia import NucliaUnderstandingAPI
nua = NucliaUnderstandingAPI(enable_ml=False)
You can push files to the Nuclia Understanding API using the push action. As the processing is done asynchronously, the results might be returned in a different order than the files were pushed. That is why you need to provide an id to match the results with the corresponding file.
nua.run({"action": "push", "id": "1", "path": "./report.docx"})
nua.run({"action": "push", "id": "2", "path": "./interview.mp4"})
You can now call the pull action in a loop until you get the JSON-formatted result.
import time
pending = True
data = None
while pending:
time.sleep(15)
data = nua.run({"action": "pull", "id": "1", "path": None})
if data:
print(data)
pending = False
else:
print("waiting...")
You can also do it in one step in async mode, you only need to do a push, and it will wait until the results are pulled:
import asyncio
async def process():
data = await nua.arun(
{"action": "push", "id": "1", "path": "./talk.mp4", "text": None}
)
print(data) | https://python.langchain.com/docs/integrations/tools/nuclia |
0a55f954a7b5-1 | asyncio.run(process())
Retrieved information
Nuclia returns the following information:
file metadata
extracted text
nested text (like text in an embedded image)
a summary (only when enable_ml is set to True)
paragraphs and sentences splitting (defined by the position of their first and last characters, plus start time and end time for a video or audio file)
named entities: people, dates, places, organizations, etc. (only when enable_ml is set to True)
links
a thumbnail
embedded files
the vector representations of the text (only when enable_ml is set to True)
Note:
Generated files (thumbnail, extracted embedded files, etc.) are provided as a token. You can download them with the /processing/download endpoint.
Also at any level, if an attribute exceeds a certain size, it will be put in a downloadable file and will be replaced in the document by a file pointer. This will consist of {"file": {"uri": "JWT_TOKEN"}}. The rule is that if the size of the message is greater than 1000000 characters, the biggest parts will be moved to downloadable files. First, the compression process will target vectors. If that is not enough, it will target large field metadata, and finally it will target extracted text. | https://python.langchain.com/docs/integrations/tools/nuclia |
18d0ee06de5d-0 | Xorbits
This notebook shows how to use agents to interact with Xorbits Pandas dataframe and Xorbits Numpy ndarray. It is mostly optimized for question answering.
NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.
Pandas examples
import xorbits.pandas as pd
from langchain.agents import create_xorbits_agent
from langchain.llms import OpenAI
data = pd.read_csv("titanic.csv")
agent = create_xorbits_agent(OpenAI(temperature=0), data, verbose=True)
0%| | 0.00/100 [00:00<?, ?it/s]
agent.run("How many rows and columns are there?")
> Entering new chain...
Thought: I need to count the number of rows and columns
Action: python_repl_ast
Action Input: data.shape
Observation: (891, 12)
Thought: I now know the final answer
Final Answer: There are 891 rows and 12 columns.
> Finished chain.
'There are 891 rows and 12 columns.'
agent.run("How many people are in pclass 1?")
> Entering new chain...
0%| | 0.00/100 [00:00<?, ?it/s]
Thought: I need to count the number of people in pclass 1
Action: python_repl_ast
Action Input: data[data['Pclass'] == 1].shape[0]
Observation: 216
Thought: I now know the final answer
Final Answer: There are 216 people in pclass 1.
> Finished chain.
'There are 216 people in pclass 1.'
agent.run("whats the mean age?")
> Entering new chain...
Thought: I need to calculate the mean age
Action: python_repl_ast
Action Input: data['Age'].mean()
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: 29.69911764705882
Thought: I now know the final answer
Final Answer: The mean age is 29.69911764705882.
> Finished chain. | https://python.langchain.com/docs/integrations/toolkits/xorbits |
18d0ee06de5d-1 | > Finished chain.
'The mean age is 29.69911764705882.'
agent.run("Group the data by sex and find the average age for each group")
> Entering new chain...
Thought: I need to group the data by sex and then find the average age for each group
Action: python_repl_ast
Action Input: data.groupby('Sex')['Age'].mean()
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: Sex
female 27.915709
male 30.726645
Name: Age, dtype: float64
Thought: I now know the average age for each group
Final Answer: The average age for female passengers is 27.92 and the average age for male passengers is 30.73.
> Finished chain.
'The average age for female passengers is 27.92 and the average age for male passengers is 30.73.'
agent.run(
"Show the number of people whose age is greater than 30 and fare is between 30 and 50 , and pclass is either 1 or 2"
)
> Entering new chain...
0%| | 0.00/100 [00:00<?, ?it/s]
Thought: I need to filter the dataframe to get the desired result
Action: python_repl_ast
Action Input: data[(data['Age'] > 30) & (data['Fare'] > 30) & (data['Fare'] < 50) & ((data['Pclass'] == 1) | (data['Pclass'] == 2))].shape[0]
Observation: 20
Thought: I now know the final answer
Final Answer: 20
> Finished chain.
'20'
Numpy examples
import xorbits.numpy as np
from langchain.agents import create_xorbits_agent
from langchain.llms import OpenAI
arr = np.array([1, 2, 3, 4, 5, 6])
agent = create_xorbits_agent(OpenAI(temperature=0), arr, verbose=True)
0%| | 0.00/100 [00:00<?, ?it/s]
agent.run("Give the shape of the array ") | https://python.langchain.com/docs/integrations/toolkits/xorbits |
18d0ee06de5d-2 | > Entering new chain...
Thought: I need to find out the shape of the array
Action: python_repl_ast
Action Input: data.shape
Observation: (6,)
Thought: I now know the final answer
Final Answer: The shape of the array is (6,).
> Finished chain.
'The shape of the array is (6,).'
agent.run("Give the 2nd element of the array ")
> Entering new chain...
Thought: I need to access the 2nd element of the array
Action: python_repl_ast
Action Input: data[1]
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: 2
Thought: I now know the final answer
Final Answer: 2
> Finished chain.
'2'
agent.run(
"Reshape the array into a 2-dimensional array with 2 rows and 3 columns, and then transpose it"
)
> Entering new chain...
Thought: I need to reshape the array and then transpose it
Action: python_repl_ast
Action Input: np.reshape(data, (2,3)).T
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: [[1 4]
[2 5]
[3 6]]
Thought: I now know the final answer
Final Answer: The reshaped and transposed array is [[1 4], [2 5], [3 6]].
> Finished chain.
'The reshaped and transposed array is [[1 4], [2 5], [3 6]].'
agent.run(
"Reshape the array into a 2-dimensional array with 3 rows and 2 columns and sum the array along the first axis"
)
> Entering new chain...
Thought: I need to reshape the array and then sum it
Action: python_repl_ast
Action Input: np.sum(np.reshape(data, (3,2)), axis=0)
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: [ 9 12]
Thought: I now know the final answer
Final Answer: The sum of the array along the first axis is [9, 12]. | https://python.langchain.com/docs/integrations/toolkits/xorbits |
18d0ee06de5d-3 | > Finished chain.
'The sum of the array along the first axis is [9, 12].'
arr = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
agent = create_xorbits_agent(OpenAI(temperature=0), arr, verbose=True)
0%| | 0.00/100 [00:00<?, ?it/s]
agent.run("calculate the covariance matrix")
> Entering new chain...
Thought: I need to use the numpy covariance function
Action: python_repl_ast
Action Input: np.cov(data)
0%| | 0.00/100 [00:00<?, ?it/s]
Observation: [[1. 1. 1.]
[1. 1. 1.]
[1. 1. 1.]]
Thought: I now know the final answer
Final Answer: The covariance matrix is [[1. 1. 1.], [1. 1. 1.], [1. 1. 1.]].
> Finished chain.
'The covariance matrix is [[1. 1. 1.], [1. 1. 1.], [1. 1. 1.]].'
agent.run("compute the U of Singular Value Decomposition of the matrix")
> Entering new chain...
Thought: I need to use the SVD function
Action: python_repl_ast
Action Input: U, S, V = np.linalg.svd(data)
Observation:
Thought: I now have the U matrix
Final Answer: U = [[-0.70710678 -0.70710678]
[-0.70710678 0.70710678]]
> Finished chain.
'U = [[-0.70710678 -0.70710678]\n [-0.70710678 0.70710678]]' | https://python.langchain.com/docs/integrations/toolkits/xorbits |
b6c8afdd9100-0 | This notebook goes over how to use the OpenWeatherMap component to fetch weather information.
from langchain.llms import OpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
import os
os.environ["OPENAI_API_KEY"] = ""
os.environ["OPENWEATHERMAP_API_KEY"] = ""
llm = OpenAI(temperature=0)
tools = load_tools(["openweathermap-api"], llm)
agent_chain = initialize_agent(
tools=tools, llm=llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)
> Entering new AgentExecutor chain...
I need to find out the current weather in London.
Action: OpenWeatherMap
Action Input: London,GB
Observation: In London,GB, the current weather is as follows:
Detailed status: broken clouds
Wind speed: 2.57 m/s, direction: 240°
Humidity: 56%
Temperature:
- Current: 20.11°C
- High: 21.75°C
- Low: 18.68°C
- Feels like: 19.64°C
Rain: {}
Heat index: None
Cloud cover: 75%
Thought: I now know the current weather in London.
Final Answer: The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.
> Finished chain.
'The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.' | https://python.langchain.com/docs/integrations/tools/openweathermap |
7bc1cb56c157-0 | This notebook goes over how to use PubMed as a tool.
'Published: <Year>2023</Year><Month>May</Month><Day>31</Day>\nTitle: Dermatology in the wake of an AI revolution: who gets a say?\nSummary: \n\nPublished: <Year>2023</Year><Month>May</Month><Day>30</Day>\nTitle: What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.\nSummary: \n\nPublished: <Year>2023</Year><Month>Jun</Month><Day>02</Day>\nTitle: The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.\nSummary: The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.' | https://python.langchain.com/docs/integrations/tools/pubmed |
9b287759b8f8-0 | The web contains a lot of information that LLMs do not have access to. In order to easily let LLMs interact with that information, we provide a wrapper around the Python Requests module that takes in a URL and fetches data from that URL.
Each requests tool contains a requests wrapper. You can work with these wrappers directly below | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-1 | '<!doctype html><html itemscope="" itemtype="http://schema.org/WebPage" lang="en"><head><meta content="Search the world\'s information, including webpages, images, videos and more. Google has many special features to help you find exactly what you\'re looking for." name="description"><meta content="noodp" name="robots"><meta content="text/html; charset=UTF-8" http-equiv="Content-Type"><meta content="/images/branding/googleg/1x/googleg_standard_color_128dp.png" itemprop="image"><title>Google</title><script | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-2 | nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google={kEI:\'TA9QZOa5EdTakPIPuIad-Ac\',kEXPI:\'0,1359409,6059,206,4804,2316,383,246,5,1129120,1197768,626,380097,16111,28687,22431,1361,12319,17581,4997,13228,37471,7692,2891,3926,213,7615,606,50058,8228,17728,432,3,346,1244,1,16920,2648,4,1528,2304,29062,9871,3194,13658,2980,1457,16786,5803,2554,4094,7596,1,42154,2,14022,2373,342,23024,6699,31123,4568,6258,23418,1252,5835,14967,4333,4239,3245,445,2,2,1,26632,239,7916,7321,60,2,3,15965,872,7830 | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-3 | 0,2,3,15965,872,7830,1796,10008,7,1922,9779,36154,6305,2007,17765,427,20136,14,82,2730,184,13600,3692,109,2412,1548,4308,3785,15175,3888,1515,3030,5628,478,4,9706,1804,7734,2738,1853,1032,9480,2995,576,1041,5648,3722,2058,3048,2130,2365,662,476,958,87,111,5807,2,975,1167,891,3580,1439,1128,7343,426,249,517,95,1102,14,696,1270,750,400,2208,274,2776,164,89,119,204,139,129,1710,2505,320,3,631,439,2,300,1645,172,1783,784,169,642,329,401,50,479,614,238,757,535,717,102,2,739,738,44,232,22,442,961,45,2 | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-4 | ,232,22,442,961,45,214,383,567,500,487,151,120,256,253,179,673,2,102,2,10,535,123,135,1685,5206695,190,2,20,50,198,5994221,2804424,3311,141,795,19735,1,1,346,5008,7,13,10,24,31,2,39,1,5,1,16,7,2,41,247,4,9,7,9,15,4,4,121,24,23944834,4042142,1964,16672,2894,6250,15739,1726,647,409,837,1411438,146986,23612960,7,84,93,33,101,816,57,532,163,1,441,86,1,951,73,31,2,345,178,243,472,2,148,962,455,167,178,29,702,1856,288,292,805,93,137,68,416,177,292,399,55,95,2566\',kBL:\'hw1A\',kOPI:89978449};google.sn | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-5 | :89978449};google.sn=\'webhp\';google.kHL=\'en\';})();(function(){\nvar | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-6 | h=this||self;function l(){return void 0!==window.google&&void 0!==window.google.kOPI&&0!==window.google.kOPI?window.google.kOPI:null};var m,n=[];function p(a){for(var b;a&&(!a.getAttribute||!(b=a.getAttribute("eid")));)a=a.parentNode;return b||m}function q(a){for(var b=null;a&&(!a.getAttribute||!(b=a.getAttribute("leid")));)a=a.parentNode;return b}function r(a){/^http:/i.test(a)&&"https:"===window.location.protocol&&(google.ml&&google.ml(Error("a"),!1,{src:a,glmm:1}),a="");return a}\nfunction t(a,b,c,d,k){var e="";-1===b.search("&ei=")&&(e="&ei="+p(d),-1===b.search("&lei=")&&(d=q(d))&&(e+="&lei="+d));d="";var g=-1===b.search("&cshid=")&&"slh"!==a,f=[];f.push(["zx",Date.now().toString()]);h._cshid&&g&&f.push(["cshid",h._cshid]);c=c();null!=c&&f.push(["opi",c.toString()]);for(c=0;c<f.length;c++){if(0===c||0<c)d+="&";d+=f[c][0]+"="+f[c][1]}return"/"+(k||"gen_204")+"?atyp=i&ct="+String(a)+"&cad="+(b+e+d)};m=google.kEI;google.getEI=p;google.getLEI=q;google.ml=function(){return null};google.log=function(a,b,c,d,k,e){e=void 0===e?l:e;c||(c=t(a,b,e,d,k));if(c=r(c)){a=new Image;var g=n.length;n[g]=a;a.onerror=a.onload=a.onabort=function(){delete n[g]};a.src=c}};google.logUrl=function(a,b){b=void 0===b?l:b;return t("",a,b)};}).call(this);(function(){google.y={};google.sy=[];google.x=function(a,b){if(a)var c=a.id;else{do | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-7 | c=a.id;else{do c=Math.random();while(google.y[c])}google.y[c]=[a,b];return!1};google.sx=function(a){google.sy.push(a)};google.lm=[];google.plm=function(a){google.lm.push.apply(google.lm,a)};google.lq=[];google.load=function(a,b,c){google.lq.push([[a],b,c])};google.loadAll=function(a,b){google.lq.push([a,b])};google.bx=!1;google.lx=function(){};}).call(this);google.f={};(function(){\ndocument.documentElement.addEventListener("submit",function(b){var a;if(a=b.target){var c=a.getAttribute("data-submitfalse");a="1"===c||"q"===c&&!a.elements.q.value?!0:!1}else a=!1;a&&(b.preventDefault(),b.stopPropagation())},!0);document.documentElement.addEventListener("click",function(b){var a;a:{for(a=b.target;a&&a!==document.documentElement;a=a.parentElement)if("A"===a.tagName){a="1"===a.getAttribute("data-nohref");break a}a=!1}a&&b.preventDefault()},!0);}).call(this);</script><style>#gbar,#guser{font-size:13px;padding-top:1px !important;}#gbar{height:22px}#guser{padding-bottom:7px !important;text-align:right}.gbh,.gbd{border-top:1px solid #c9d7f1;font-size:1px}.gbh{height:0;position:absolute;top:24px;width:100%}@media all{.gb1{height:22px;margin-right:.5em;vertical-align:top}#gbar{float:left}}a.gb1,a.gb4{text-decoration:underline !important}a.gb1,a.gb4{color:#00c !important}.gbi .gb4{color:#dd8e27 !important}.gbf .gb4{color:#900 !important}\n</style><style>body,td,a,p,.h{font-family:arial,sans-serif}body{margin:0;overflow-y:scroll}#gog{padding:3px 8px 0}td{line-height:.8em}.gac_m | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-8 | 8px 0}td{line-height:.8em}.gac_m td{line-height:17px}form{margin-bottom:20px}.h{color:#1558d6}em{font-weight:bold;font-style:normal}.lst{height:25px;width:496px}.gsfi,.lst{font:18px arial,sans-serif}.gsfs{font:17px arial,sans-serif}.ds{display:inline-box;display:inline-block;margin:3px 0 4px;margin-left:4px}input{font-family:inherit}body{background:#fff;color:#000}a{color:#4b11a8;text-decoration:none}a:hover,a:active{text-decoration:underline}.fl a{color:#1558d6}a:visited{color:#4b11a8}.sblc{padding-top:5px}.sblc a{display:block;margin:2px 0;margin-left:13px;font-size:11px}.lsbb{background:#f8f9fa;border:solid 1px;border-color:#dadce0 #70757a #70757a #dadce0;height:30px}.lsbb{display:block}#WqQANb a{display:inline-block;margin:0 12px}.lsb{background:url(/images/nav_logo229.png) 0 -261px repeat-x;border:none;color:#000;cursor:pointer;height:30px;margin:0;outline:0;font:15px arial,sans-serif;vertical-align:top}.lsb:active{background:#dadce0}.lst:focus{outline:none}</style><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google.erd={jsr:1,bv:1785,de:true};\nvar h=this||self;var k,l=null!=(k=h.mei)?k:1,n,p=null!=(n=h.sdo)?n:!0,q=0,r,t=google.erd,v=t.jsr;google.ml=function(a,b,d,m,e){e=void 0===e?2:e;b&&(r=a&&a.message);if(google.dl)return google.dl(a,e,d),null;if(0>v){window.console&&console.error(a,d);if(-2===v)throw a;b=!1}else | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-9 | a;b=!1}else b=!a||!a.message||"Error loading script"===a.message||q>=l&&!m?!1:!0;if(!b)return null;q++;d=d||{};b=encodeURIComponent;var c="/gen_204?atyp=i&ei="+b(google.kEI);google.kEXPI&&(c+="&jexpid="+b(google.kEXPI));c+="&srcpg="+b(google.sn)+"&jsr="+b(t.jsr)+"&bver="+b(t.bv);var f=a.lineNumber;void 0!==f&&(c+="&line="+f);var g=\na.fileName;g&&(0<g.indexOf("-extension:/")&&(e=3),c+="&script="+b(g),f&&g===window.location.href&&(f=document.documentElement.outerHTML.split("\\n")[f],c+="&cad="+b(f?f.substring(0,300):"No script found.")));c+="&jsel="+e;for(var u in d)c+="&",c+=b(u),c+="=",c+=b(d[u]);c=c+"&emsg="+b(a.name+": "+a.message);c=c+"&jsst="+b(a.stack||"N/A");12288<=c.length&&(c=c.substr(0,12288));a=c;m||google.log(0,"",a);return a};window.onerror=function(a,b,d,m,e){r!==a&&(a=e instanceof Error?e:Error(a),void 0===d||"lineNumber"in a||(a.lineNumber=d),void 0===b||"fileName"in a||(a.fileName=b),google.ml(a,!1,void 0,!1,"SyntaxError"===a.name||"SyntaxError"===a.message.substring(0,11)||-1!==a.message.indexOf("Script error")?3:0));r=null;p&&q>=l&&(window.onerror=null)};})();</script></head><body bgcolor="#fff"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var src=\'/images/nav_logo229.png\';var iesg=false;document.body.onload = function(){window.n && window.n();if (document.images){new Image().src=src;}\nif | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-10 | && window.n();if (document.images){new Image().src=src;}\nif (!iesg){document.f&&document.f.q.focus();document.gbqf&&document.gbqf.q.focus();}\n}\n})();</script><div id="mngb"><div id=gbar><nobr><b class=gb1>Search</b> <a class=gb1 href="https://www.google.com/imghp?hl=en&tab=wi">Images</a> <a class=gb1 href="https://maps.google.com/maps?hl=en&tab=wl">Maps</a> <a class=gb1 href="https://play.google.com/?hl=en&tab=w8">Play</a> <a class=gb1 href="https://www.youtube.com/?tab=w1">YouTube</a> <a class=gb1 href="https://news.google.com/?tab=wn">News</a> <a class=gb1 href="https://mail.google.com/mail/?tab=wm">Gmail</a> <a class=gb1 href="https://drive.google.com/?tab=wo">Drive</a> <a class=gb1 style="text-decoration:none" href="https://www.google.com/intl/en/about/products?tab=wh"><u>More</u> »</a></nobr></div><div id=guser width=100%><nobr><span id=gbn class=gbi></span><span id=gbf class=gbf></span><span id=gbe></span><a href="http://www.google.com/history/optout?hl=en" class=gb4>Web History</a> | <a href="/preferences?hl=en" class=gb4>Settings</a> | <a target=_top id=gb_70 href="https://accounts.google.com/ServiceLogin?hl=en&passive=true&continue=https://www.google.com/&ec=GAZAAQ" class=gb4>Sign in</a></nobr></div><div class=gbh style=left:0></div><div class=gbh style=right:0></div></div><center><br clear="all" id="lgpd"><div id="lga"><img alt="Google" height="92" | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-11 | id="lgpd"><div id="lga"><img alt="Google" height="92" src="/images/branding/googlelogo/1x/googlelogo_white_background_color_272x92dp.png" style="padding:28px 0 14px" width="272" id="hplogo"><br><br></div><form action="/search" name="f"><table cellpadding="0" cellspacing="0"><tr valign="top"><td width="25%"> </td><td align="center" nowrap=""><input name="ie" value="ISO-8859-1" type="hidden"><input value="en" name="hl" type="hidden"><input name="source" type="hidden" value="hp"><input name="biw" type="hidden"><input name="bih" type="hidden"><div class="ds" style="height:32px;margin:4px 0"><input class="lst" style="margin:0;padding:5px 8px 0 6px;vertical-align:top;color:#000" autocomplete="off" value="" title="Google Search" maxlength="2048" name="q" size="57"></div><br style="line-height:0"><span class="ds"><span class="lsbb"><input class="lsb" value="Google Search" name="btnG" type="submit"></span></span><span class="ds"><span class="lsbb"><input class="lsb" id="tsuid_1" value="I\'m Feeling Lucky" name="btnI" type="submit"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var id=\'tsuid_1\';document.getElementById(id).onclick = function(){if (this.form.q.value){this.checked = 1;if (this.form.iflsig)this.form.iflsig.disabled = false;}\nelse top.location=\'/doodles/\';};})();</script><input value="AOEireoAAAAAZFAdXGKCXWBK5dlWxPhh8hNPQz1s9YT6" name="iflsig" type="hidden"></span></span></td><td class="fl sblc" align="left" nowrap="" width="25%"><a href="/advanced_search?hl=en&authuser=0">Advanced | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-12 | width="25%"><a href="/advanced_search?hl=en&authuser=0">Advanced search</a></td></tr></table><input id="gbv" name="gbv" type="hidden" value="1"><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var a,b="1";if(document&&document.getElementById)if("undefined"!=typeof XMLHttpRequest)b="2";else if("undefined"!=typeof ActiveXObject){var c,d,e=["MSXML2.XMLHTTP.6.0","MSXML2.XMLHTTP.3.0","MSXML2.XMLHTTP","Microsoft.XMLHTTP"];for(c=0;d=e[c++];)try{new ActiveXObject(d),b="2"}catch(h){}}a=b;if("2"==a&&-1==location.search.indexOf("&gbv=2")){var f=google.gbvu,g=document.getElementById("gbv");g&&(g.value=a);f&&window.setTimeout(function(){location.href=f},0)};}).call(this);</script></form><div id="gac_scont"></div><div style="font-size:83%;min-height:3.5em"><br><div id="prm"><style>.szppmdbYutt__middle-slot-promo{font-size:small;margin-bottom:32px}.szppmdbYutt__middle-slot-promo a.ZIeIlb{display:inline-block;text-decoration:none}.szppmdbYutt__middle-slot-promo img{border:none;margin-right:5px;vertical-align:middle}</style><div class="szppmdbYutt__middle-slot-promo" data-ved="0ahUKEwjmj7fr6dT-AhVULUQIHThDB38QnIcBCAQ"><a class="NKcBbd" | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-13 | class="NKcBbd" href="https://www.google.com/url?q=https://blog.google/outreach-initiatives/diversity/asian-pacific-american-heritage-month-2023/%3Futm_source%3Dhpp%26utm_medium%3Downed%26utm_campaign%3Dapahm&source=hpp&id=19035152&ct=3&usg=AOvVaw1zrN82vzhoWl4hz1zZ4gLp&sa=X&ved=0ahUKEwjmj7fr6dT-AhVULUQIHThDB38Q8IcBCAU" rel="nofollow">Celebrate Asian Pacific American Heritage Month with Google</a></div></div></div><span id="footer"><div style="font-size:10pt"><div style="margin:19px auto;text-align:center" id="WqQANb"><a href="/intl/en/ads/">Advertising</a><a href="/services/">Business Solutions</a><a href="/intl/en/about.html">About Google</a></div></div><p style="font-size:8pt;color:#70757a">© 2023 - <a href="/intl/en/policies/privacy/">Privacy</a> - <a href="/intl/en/policies/terms/">Terms</a></p></span></center><script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){window.google.cdo={height:757,width:1440};(function(){var a=window.innerWidth,b=window.innerHeight;if(!a||!b){var c=window.document,d="CSS1Compat"==c.compatMode?c.documentElement:c.body;a=d.clientWidth;b=d.clientHeight}a&&b&&(a!=google.cdo.width||b!=google.cdo.height)&&google.log("","","/client_204?&atyp=i&biw="+a+"&bih="+b+"&ei="+google.kEI);}).call(this);})();</script> <script | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-14 | <script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){google.xjs={ck:\'xjs.hp.vUsZk7fd8do.L.X.O\',cs:\'ACT90oF8ktm8JGoaZ23megDhHoJku7YaGw\',excm:[]};})();</script> <script nonce="MXrF0nnIBPkxBza4okrgPA">(function(){var u=\'/xjs/_/js/k\\x3dxjs.hp.en.q0lHXBfs9JY.O/am\\x3dAAAA6AQAUABgAQ/d\\x3d1/ed\\x3d1/rs\\x3dACT90oE3ek6-fjkab6CsTH0wUEUUPhnExg/m\\x3dsb_he,d\';var amd=0;\nvar e=this||self,f=function(c){return c};var h;var n=function(c,g){this.g=g===l?c:""};n.prototype.toString=function(){return this.g+""};var l={};\nfunction p(){var c=u,g=function(){};google.lx=google.stvsc?g:function(){google.timers&&google.timers.load&&google.tick&&google.tick("load","xjsls");var a=document;var b="SCRIPT";"application/xhtml+xml"===a.contentType&&(b=b.toLowerCase());b=a.createElement(b);a=null===c?"null":void 0===c?"undefined":c;if(void 0===h){var d=null;var m=e.trustedTypes;if(m&&m.createPolicy){try{d=m.createPolicy("goog#html",{createHTML:f,createScript:f,createScriptURL:f})}catch(r){e.console&&e.console.error(r.message)}h=\nd}else h=d}a=(d=h)?d.createScriptURL(a):a;a=new n(a,l);b.src=a instanceof n&&a.constructor===n?a.g:"type_error:TrustedResourceUrl";var k,q;(k=(a=null==(q=(k=(b.ownerDocument&&b.ownerDocument.defaultView||window).document).querySelector)?void | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-15 | 0:q.call(k,"script[nonce]"))?a.nonce||a.getAttribute("nonce")||"":"")&&b.setAttribute("nonce",k);document.body.appendChild(b);google.psa=!0;google.lx=g};google.bx||google.lx()};google.xjsu=u;e._F_jsUrl=u;setTimeout(function(){0<amd?google.caft(function(){return p()},amd):p()},0);})();window._ = window._ || {};window._DumpException = _._DumpException = function(e){throw e;};window._s = window._s || {};_s._DumpException = _._DumpException;window._qs = window._qs || {};_qs._DumpException = _._DumpException;function _F_installCss(c){}\n(function(){google.jl={blt:\'none\',chnk:0,dw:false,dwu:true,emtn:0,end:0,ico:false,ikb:0,ine:false,injs:\'none\',injt:0,injth:0,injv2:false,lls:\'default\',pdt:0,rep:0,snet:true,strt:0,ubm:false,uwp:true};})();(function(){var pmc=\'{\\x22d\\x22:{},\\x22sb_he\\x22:{\\x22agen\\x22:true,\\x22cgen\\x22:true,\\x22client\\x22:\\x22heirloom-hp\\x22,\\x22dh\\x22:true,\\x22ds\\x22:\\x22\\x22,\\x22fl\\x22:true,\\x22host\\x22:\\x22google.com\\x22,\\x22jsonp\\x22:true,\\x22msgs\\x22:{\\x22cibl\\x22:\\x22Clear Search\\x22,\\x22dym\\x22:\\x22Did you mean:\\x22,\\x22lcky\\x22:\\x22I\\\\u0026#39;m Feeling Lucky\\x22,\\x22lml\\x22:\\x22Learn more\\x22,\\x22psrc\\x22:\\x22This search was removed from your \\\\u003Ca | https://python.langchain.com/docs/integrations/tools/requests |
9b287759b8f8-16 | 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:{},\\x22pq\\x22:\\x22\\x22,\\x22rfs\\x22:[],\\x22sbas\\x22:\\x220 3px 8px 0 rgba(0,0,0,0.2),0 0 0 1px rgba(0,0,0,0.08)\\x22,\\x22stok\\x22:\\x22C3TIBpTor6RHJfEIn2nbidnhv50\\x22}}\';google.pmc=JSON.parse(pmc);})();</script> </body></html>' | https://python.langchain.com/docs/integrations/tools/requests |
c91eb2525dca-0 | SceneXplain is an ImageCaptioning service accessible through the SceneXplain Tool.
To use this tool, you'll need to make an account and fetch your API Token from the website. Then you can instantiate the tool.
Or directly instantiate the tool.
from langchain.llms import OpenAI
from langchain.agents import initialize_agent
from langchain.memory import ConversationBufferMemory
llm = OpenAI(temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history")
agent = initialize_agent(
tools, llm, memory=memory, agent="conversational-react-description", verbose=True
)
output = agent.run(
input=(
"What is in this image https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png. "
"Is it movie or a game? If it is a movie, what is the name of the movie?"
)
)
print(output)
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: Image Explainer
Action Input: https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png
Observation: In a charmingly whimsical scene, a young girl is seen braving the rain alongside her furry companion, the lovable Totoro. The two are depicted standing on a bustling street corner, where they are sheltered from the rain by a bright yellow umbrella. The girl, dressed in a cheerful yellow frock, holds onto the umbrella with both hands while gazing up at Totoro with an expression of wonder and delight.
Totoro, meanwhile, stands tall and proud beside his young friend, holding his own umbrella aloft to protect them both from the downpour. His furry body is rendered in rich shades of grey and white, while his large ears and wide eyes lend him an endearing charm. | https://python.langchain.com/docs/integrations/tools/sceneXplain |
c91eb2525dca-1 | In the background of the scene, a street sign can be seen jutting out from the pavement amidst a flurry of raindrops. A sign with Chinese characters adorns its surface, adding to the sense of cultural diversity and intrigue. Despite the dreary weather, there is an undeniable sense of joy and camaraderie in this heartwarming image.
Thought: Do I need to use a tool? No
AI: This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro.
> Finished chain.
This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro. | https://python.langchain.com/docs/integrations/tools/sceneXplain |
41237be97d08-0 | This notebook shows off usage of various search tools.
First, let's try to use the Google Serper API tool.
Now, let's use the SerpAPI tool.
Now, let's use the official Google Search API Wrapper.
> Entering new AgentExecutor chain...
I should look up the current weather conditions.
Action: Google Search
Action Input: "weather in Pomfret"
Observation: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Hourly Weather-Pomfret, CT. As of 12:52 am EST. Special Weather Statement +2 ... Hazardous Weather Conditions. Special Weather Statement ... Pomfret CT. Tonight ... National Digital Forecast Database Maximum Temperature Forecast. Pomfret Center Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Pomfret, CT 12 hour by hour weather forecast includes precipitation, temperatures, sky conditions, rain chance, dew-point, relative humidity, wind direction ... North Pomfret Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Today's Weather - Pomfret, CT. Dec 31, 2022 4:00 PM. Putnam MS. --. Weather forecast icon. Feels like --. Hi --. Lo --. Pomfret, CT temperature trend for the next 14 Days. Find daytime highs and nighttime lows from TheWeatherNetwork.com. Pomfret, MD Weather Forecast Date: 332 PM EST Wed Dec 28 2022. The area/counties/county of: Charles, including the cites of: St. Charles and Waldorf.
Thought: I now know the current weather conditions in Pomfret.
Final Answer: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.
> Finished AgentExecutor chain. | https://python.langchain.com/docs/integrations/tools/search_tools |
41237be97d08-1 | '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%.'
Here we will be using a self hosted SearxNG meta search engine. | https://python.langchain.com/docs/integrations/tools/search_tools |
250ae4ac54fb-0 | This notebook goes over how to use a self hosted SearxNG search API to search the web.
For some engines, if a direct answer is available the warpper will print the answer instead of the full list of search results. You can use the results method of the wrapper if you want to obtain all the results.
SearxNG supports 135 search engines. You can also customize the Searx wrapper with arbitrary named parameters that will be passed to the Searx search API . In the below example we will making a more interesting use of custom search parameters from searx search api.
In this example we will be looking for scientific paper using the categories parameter and limiting the results to a time_range (not all engines support the time range option).
We also would like to obtain the results in a structured way including metadata. For this we will be using the results method of the wrapper.
[{'snippet': '… on natural language instructions, large language models (… the '
'prompt used to steer the model, and most effective prompts … to '
'prompt engineering, we propose Automatic Prompt …',
'title': 'Large language models are human-level prompt engineers',
'link': 'https://arxiv.org/abs/2211.01910',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Large language models (LLMs) have introduced new possibilities '
'for prototyping with AI [18]. Pre-trained on a large amount of '
'text data, models … language instructions called prompts. …',
'title': 'Promptchainer: Chaining large language model prompts through '
'visual programming',
'link': 'https://dl.acm.org/doi/abs/10.1145/3491101.3519729',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… can introspect the large prompt model. We derive the view '
'ϕ0(X) and the model h0 from T01. However, instead of fully '
'fine-tuning T0 during co-training, we focus on soft prompt '
'tuning, …',
'title': 'Co-training improves prompt-based learning for large language '
'models', | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-1 | 'title': 'Co-training improves prompt-based learning for large language '
'models',
'link': 'https://proceedings.mlr.press/v162/lang22a.html',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… With the success of large language models (LLMs) of code and '
'their use as … prompt design process become important. In this '
'work, we propose a framework called Repo-Level Prompt …',
'title': 'Repository-level prompt generation for large language models of '
'code',
'link': 'https://arxiv.org/abs/2206.12839',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Figure 2 | The benefits of different components of a prompt '
'for the largest language model (Gopher), as estimated from '
'hierarchical logistic regression. Each point estimates the '
'unique …',
'title': 'Can language models learn from explanations in context?',
'link': 'https://arxiv.org/abs/2204.02329',
'engines': ['google scholar'],
'category': 'science'}]
[{'snippet': 'Thanks to the advanced improvement of large pre-trained language '
'models, prompt-based fine-tuning is shown to be effective on a '
'variety of downstream tasks. Though many prompting methods have '
'been investigated, it remains unknown which type of prompts are '
'the most effective among three types of prompts (i.e., '
'human-designed prompts, schema prompts and null prompts). In '
'this work, we empirically compare the three types of prompts '
'under both few-shot and fully-supervised settings. Our '
'experimental results show that schema prompts are the most '
'effective in general. Besides, the performance gaps tend to '
'diminish when the scale of training data grows large.',
'title': 'Do Prompts Solve NLP Tasks Using Natural Language?',
'link': 'http://arxiv.org/abs/2203.00902v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Cross-prompt automated essay scoring (AES) requires the system ' | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-2 | {'snippet': 'Cross-prompt automated essay scoring (AES) requires the system '
'to use non target-prompt essays to award scores to a '
'target-prompt essay. Since obtaining a large quantity of '
'pre-graded essays to a particular prompt is often difficult and '
'unrealistic, the task of cross-prompt AES is vital for the '
'development of real-world AES systems, yet it remains an '
'under-explored area of research. Models designed for '
'prompt-specific AES rely heavily on prompt-specific knowledge '
'and perform poorly in the cross-prompt setting, whereas current '
'approaches to cross-prompt AES either require a certain quantity '
'of labelled target-prompt essays or require a large quantity of '
'unlabelled target-prompt essays to perform transfer learning in '
'a multi-step manner. To address these issues, we introduce '
'Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES. Our '
'method requires no access to labelled or unlabelled '
'target-prompt data during training and is a single-stage '
'approach. PAES is easy to apply in practice and achieves '
'state-of-the-art performance on the Automated Student Assessment '
'Prize (ASAP) dataset.',
'title': 'Prompt Agnostic Essay Scorer: A Domain Generalization Approach to '
'Cross-prompt Automated Essay Scoring',
'link': 'http://arxiv.org/abs/2008.01441v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Research on prompting has shown excellent performance with '
'little or even no supervised training across many tasks. '
'However, prompting for machine translation is still '
'under-explored in the literature. We fill this gap by offering a '
'systematic study on prompting strategies for translation, '
'examining various factors for prompt template and demonstration '
'example selection. We further explore the use of monolingual '
'data and the feasibility of cross-lingual, cross-domain, and '
'sentence-to-document transfer learning in prompting. Extensive '
'experiments with GLM-130B (Zeng et al., 2022) as the testbed ' | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-3 | 'show that 1) the number and the quality of prompt examples '
'matter, where using suboptimal examples degenerates translation; '
'2) several features of prompt examples, such as semantic '
'similarity, show significant Spearman correlation with their '
'prompting performance; yet, none of the correlations are strong '
'enough; 3) using pseudo parallel prompt examples constructed '
'from monolingual data via zero-shot prompting could improve '
'translation; and 4) improved performance is achievable by '
'transferring knowledge from prompt examples selected in other '
'settings. We finally provide an analysis on the model outputs '
'and discuss several problems that prompting still suffers from.',
'title': 'Prompting Large Language Model for Machine Translation: A Case '
'Study',
'link': 'http://arxiv.org/abs/2301.07069v2',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Large language models can perform new tasks in a zero-shot '
'fashion, given natural language prompts that specify the desired '
'behavior. Such prompts are typically hand engineered, but can '
'also be learned with gradient-based methods from labeled data. '
'However, it is underexplored what factors make the prompts '
'effective, especially when the prompts are natural language. In '
'this paper, we investigate common attributes shared by effective '
'prompts. We first propose a human readable prompt tuning method '
'(F LUENT P ROMPT) based on Langevin dynamics that incorporates a '
'fluency constraint to find a diverse distribution of effective '
'and fluent prompts. Our analysis reveals that effective prompts '
'are topically related to the task domain and calibrate the prior '
'probability of label words. Based on these findings, we also '
'propose a method for generating prompts using only unlabeled '
'data, outperforming strong baselines by an average of 7.0% '
'accuracy across three tasks.',
'title': "Toward Human Readable Prompt Tuning: Kubrick's The Shining is a "
'good movie, and a good prompt too?', | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-4 | 'good movie, and a good prompt too?',
'link': 'http://arxiv.org/abs/2212.10539v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Prevailing methods for mapping large generative language models '
"to supervised tasks may fail to sufficiently probe models' novel "
'capabilities. Using GPT-3 as a case study, we show that 0-shot '
'prompts can significantly outperform few-shot prompts. We '
'suggest that the function of few-shot examples in these cases is '
'better described as locating an already learned task rather than '
'meta-learning. This analysis motivates rethinking the role of '
'prompts in controlling and evaluating powerful language models. '
'In this work, we discuss methods of prompt programming, '
'emphasizing the usefulness of considering prompts through the '
'lens of natural language. We explore techniques for exploiting '
'the capacity of narratives and cultural anchors to encode '
'nuanced intentions and techniques for encouraging deconstruction '
'of a problem into components before producing a verdict. '
'Informed by this more encompassing theory of prompt programming, '
'we also introduce the idea of a metaprompt that seeds the model '
'to generate its own natural language prompts for a range of '
'tasks. Finally, we discuss how these more general methods of '
'interacting with language models can be incorporated into '
'existing and future benchmarks and practical applications.',
'title': 'Prompt Programming for Large Language Models: Beyond the Few-Shot '
'Paradigm',
'link': 'http://arxiv.org/abs/2102.07350v1',
'engines': ['arxiv'],
'category': 'science'}]
In this example we query for large language models under the it category. We then filter the results that come from github.
We could also directly query for results from github and other source forges.
[{'snippet': "Implementation of 'A Watermark for Large Language Models' paper "
'by Kirchenbauer & Geiping et. al.',
'title': 'Peutlefaire / LMWatermark',
'link': 'https://gitlab.com/BrianPulfer/LMWatermark', | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-5 | 'link': 'https://gitlab.com/BrianPulfer/LMWatermark',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Guide to using pre-trained large language models of source code',
'title': 'Code-LMs',
'link': 'https://github.com/VHellendoorn/Code-LMs',
'engines': ['github'],
'category': 'it'},
{'snippet': '',
'title': 'Simen Burud / Large-scale Language Models for Conversational '
'Speech Recognition',
'link': 'https://gitlab.com/BrianPulfer',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Dramatron uses large language models to generate coherent '
'scripts and screenplays.',
'title': 'dramatron',
'link': 'https://github.com/deepmind/dramatron',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for loralib, an implementation of "LoRA: Low-Rank '
'Adaptation of Large Language Models"',
'title': 'LoRA',
'link': 'https://github.com/microsoft/LoRA',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for the paper "Evaluating Large Language Models Trained on '
'Code"',
'title': 'human-eval',
'link': 'https://github.com/openai/human-eval',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A trend starts from "Chain of Thought Prompting Elicits '
'Reasoning in Large Language Models".',
'title': 'Chain-of-ThoughtsPapers',
'link': 'https://github.com/Timothyxxx/Chain-of-ThoughtsPapers',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Mistral: A strong, northwesterly wind: Framework for transparent '
'and accessible large-scale language model training, built with '
'Hugging Face 🤗 Transformers.',
'title': 'mistral', | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-6 | 'Hugging Face 🤗 Transformers.',
'title': 'mistral',
'link': 'https://github.com/stanford-crfm/mistral',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A prize for finding tasks that cause large language models to '
'show inverse scaling',
'title': 'prize',
'link': 'https://github.com/inverse-scaling/prize',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Optimus: the first large-scale pre-trained VAE language model',
'title': 'Optimus',
'link': 'https://github.com/ChunyuanLI/Optimus',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Seminar on Large Language Models (COMP790-101 at UNC Chapel '
'Hill, Fall 2022)',
'title': 'llm-seminar',
'link': 'https://github.com/craffel/llm-seminar',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A central, open resource for data and tools related to '
'chain-of-thought reasoning in large language models. Developed @ '
'Samwald research group: https://samwald.info/',
'title': 'ThoughtSource',
'link': 'https://github.com/OpenBioLink/ThoughtSource',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A comprehensive list of papers using large language/multi-modal '
'models for Robotics/RL, including papers, codes, and related '
'websites',
'title': 'Awesome-LLM-Robotics',
'link': 'https://github.com/GT-RIPL/Awesome-LLM-Robotics',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Tools for curating biomedical training data for large-scale '
'language modeling',
'title': 'biomedical',
'link': 'https://github.com/bigscience-workshop/biomedical',
'engines': ['github'],
'category': 'it'}, | https://python.langchain.com/docs/integrations/tools/searx_search |
250ae4ac54fb-7 | 'engines': ['github'],
'category': 'it'},
{'snippet': 'ChatGPT @ Home: Large Language Model (LLM) chatbot application, '
'written by ChatGPT',
'title': 'ChatGPT-at-Home',
'link': 'https://github.com/Sentdex/ChatGPT-at-Home',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Design and Deploy Large Language Model Apps',
'title': 'dust',
'link': 'https://github.com/dust-tt/dust',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Polyglot: Large Language Models of Well-balanced Competence in '
'Multi-languages',
'title': 'polyglot',
'link': 'https://github.com/EleutherAI/polyglot',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code release for "Learning Video Representations from Large '
'Language Models"',
'title': 'LaViLa',
'link': 'https://github.com/facebookresearch/LaViLa',
'engines': ['github'],
'category': 'it'},
{'snippet': 'SmoothQuant: Accurate and Efficient Post-Training Quantization '
'for Large Language Models',
'title': 'smoothquant',
'link': 'https://github.com/mit-han-lab/smoothquant',
'engines': ['github'],
'category': 'it'},
{'snippet': 'This repository contains the code, data, and models of the paper '
'titled "XL-Sum: Large-Scale Multilingual Abstractive '
'Summarization for 44 Languages" published in Findings of the '
'Association for Computational Linguistics: ACL-IJCNLP 2021.',
'title': 'xl-sum',
'link': 'https://github.com/csebuetnlp/xl-sum',
'engines': ['github'],
'category': 'it'}] | https://python.langchain.com/docs/integrations/tools/searx_search |
96e04baf56c0-0 | SerpAPI
This notebook goes over how to use the SerpAPI component to search the web.
from langchain.utilities import SerpAPIWrapper
search = SerpAPIWrapper()
search.run("Obama's first name?")
'Barack Hussein Obama II'
Custom Parameters
You can also customize the SerpAPI wrapper with arbitrary parameters. For example, in the below example we will use bing instead of google.
params = {
"engine": "bing",
"gl": "us",
"hl": "en",
}
search = SerpAPIWrapper(params=params)
search.run("Obama's first name?")
'Barack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American presi…New content will be added above the current area of focus upon selectionBarack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American president of the United States. He previously served as a U.S. senator from Illinois from 2005 to 2008 and as an Illinois state senator from 1997 to 2004, and previously worked as a civil rights lawyer before entering politics.Wikipediabarackobama.com'
from langchain.agents import Tool
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=search.run,
) | https://python.langchain.com/docs/integrations/tools/serpapi |
081604928ae0-0 | Twilio
This notebook goes over how to use the Twilio API wrapper to send a message through SMS or Twilio Messaging Channels.
Twilio Messaging Channels facilitates integrations with 3rd party messaging apps and lets you send messages through WhatsApp Business Platform (GA), Facebook Messenger (Public Beta) and Google Business Messages (Private Beta).
Setup
To use this tool you need to install the Python Twilio package twilio
You'll also need to set up a Twilio account and get your credentials. You'll need your Account String Identifier (SID) and your Auth Token. You'll also need a number to send messages from.
You can either pass these in to the TwilioAPIWrapper as named parameters account_sid, auth_token, from_number, or you can set the environment variables TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, TWILIO_FROM_NUMBER.
Sending an SMS
from langchain.utilities.twilio import TwilioAPIWrapper
twilio = TwilioAPIWrapper(
# account_sid="foo",
# auth_token="bar",
# from_number="baz,"
)
twilio.run("hello world", "+16162904619")
Sending a WhatsApp Message
You'll need to link your WhatsApp Business Account with Twilio. You'll also need to make sure that the number to send messages from is configured as a WhatsApp Enabled Sender on Twilio and registered with WhatsApp.
from langchain.utilities.twilio import TwilioAPIWrapper
twilio = TwilioAPIWrapper(
# account_sid="foo",
# auth_token="bar",
# from_number="whatsapp: baz,"
)
twilio.run("hello world", "whatsapp: +16162904619") | https://python.langchain.com/docs/integrations/tools/twilio |
f214ca03c2e5-0 | This example demonstrates the use of the SQLDatabaseChain for answering questions over a SQL database.
Under the hood, LangChain uses SQLAlchemy to connect to SQL databases. The SQLDatabaseChain can therefore be used with any SQL dialect supported by SQLAlchemy, such as MS SQL, MySQL, MariaDB, PostgreSQL, Oracle SQL, Databricks and SQLite. Please refer to the SQLAlchemy documentation for more information about requirements for connecting to your database. For example, a connection to MySQL requires an appropriate connector such as PyMySQL. A URI for a MySQL connection might look like: mysql+pymysql://user:pass@some_mysql_db_address/db_name.
This demonstration uses SQLite and 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.
NOTE: For data-sensitive projects, you can specify return_direct=True in the SQLDatabaseChain initialization to directly return the output of the SQL query without any additional formatting. This prevents the LLM from seeing any contents within the database. Note, however, the LLM still has access to the database scheme (i.e. dialect, table and key names) by default.
Sometimes the Language Model generates invalid SQL with small mistakes that can be self-corrected using the same technique used by the SQL Database Agent to try and fix the SQL using the LLM. You can simply specify this option when creating the chain:
You can also customize the prompt that is used. Here is an example prompting it to understand that foobar is the same as the Employee table
from langchain.prompts.prompt import PromptTemplate
_DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.
Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
{table_info}
If someone asks for the table foobar, they really mean the employee table. | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-1 | If someone asks for the table foobar, they really mean the employee table.
Question: {input}"""
PROMPT = PromptTemplate(
input_variables=["input", "table_info", "dialect"], template=_DEFAULT_TEMPLATE
)
You can also return the intermediate steps of the SQLDatabaseChain. This allows you to access the SQL statement that was generated, as well as the result of running that against the SQL Database.
> Entering new SQLDatabaseChain chain...
How many employees are there in the foobar table?
SQLQuery:SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer:There are 8 employees in the foobar table.
> Finished chain. | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-2 | [{'input': 'How many employees are there in the foobar table?\nSQLQuery:SELECT COUNT(*) FROM Employee;\nSQLResult: [(8,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite', | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-3 | 'table_info': '\nCREATE TABLE "Artist" (\n\t"ArtistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("ArtistId")\n)\n\n/*\n3 rows from Artist table:\nArtistId\tName\n1\tAC/DC\n2\tAccept\n3\tAerosmith\n*/\n\n\nCREATE TABLE "Employee" (\n\t"EmployeeId" INTEGER NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"FirstName" NVARCHAR(20) NOT NULL, \n\t"Title" NVARCHAR(30), \n\t"ReportsTo" INTEGER, \n\t"BirthDate" DATETIME, \n\t"HireDate" DATETIME, \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60), \n\tPRIMARY KEY ("EmployeeId"), \n\tFOREIGN KEY("ReportsTo") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Employee table:\nEmployeeId\tLastName\tFirstName\tTitle\tReportsTo\tBirthDate\tHireDate\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\n1\tAdams\tAndrew\tGeneral Manager\tNone\t1962-02-18 00:00:00\t2002-08-14 00:00:00\t11120 Jasper Ave NW\tEdmonton\tAB\tCanada\tT5K 2N1\t+1 (780) 428-9482\t+1 (780) 428-3457\tandrew@chinookcorp.com\n2\tEdwards\tNancy\tSales Manager\t1\t1958-12-08 00:00:00\t2002-05-01 00:00:00\t825 8 Ave SW\tCalgary\tAB\tCanada\tT2P 2T3\t+1 (403) 262-3443\t+1 (403) | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-4 | (403) 262-3443\t+1 (403) 262-3322\tnancy@chinookcorp.com\n3\tPeacock\tJane\tSales Support Agent\t2\t1973-08-29 00:00:00\t2002-04-01 00:00:00\t1111 6 Ave SW\tCalgary\tAB\tCanada\tT2P 5M5\t+1 (403) 262-3443\t+1 (403) 262-6712\tjane@chinookcorp.com\n*/\n\n\nCREATE TABLE "Genre" (\n\t"GenreId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("GenreId")\n)\n\n/*\n3 rows from Genre table:\nGenreId\tName\n1\tRock\n2\tJazz\n3\tMetal\n*/\n\n\nCREATE TABLE "MediaType" (\n\t"MediaTypeId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("MediaTypeId")\n)\n\n/*\n3 rows from MediaType table:\nMediaTypeId\tName\n1\tMPEG audio file\n2\tProtected AAC audio file\n3\tProtected MPEG-4 video file\n*/\n\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n3 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n3\tTV Shows\n*/\n\n\nCREATE TABLE "Album" (\n\t"AlbumId" INTEGER NOT NULL, \n\t"Title" NVARCHAR(160) NOT NULL, \n\t"ArtistId" INTEGER NOT NULL, \n\tPRIMARY KEY ("AlbumId"), \n\tFOREIGN KEY("ArtistId") REFERENCES "Artist" ("ArtistId")\n)\n\n/*\n3 rows from Album table:\nAlbumId\tTitle\tArtistId\n1\tFor Those About To Rock We Salute You\t1\n2\tBalls to the Wall\t2\n3\tRestless and Wild\t2\n*/\n\n\nCREATE TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-5 | TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, \n\t"FirstName" NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60) NOT NULL, \n\t"SupportRepId" INTEGER, \n\tPRIMARY KEY ("CustomerId"), \n\tFOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\tluisg@embraer.com.br\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n*/\n\n\nCREATE TABLE "Invoice" (\n\t"InvoiceId" INTEGER NOT NULL, \n\t"CustomerId" INTEGER NOT NULL, \n\t"InvoiceDate" DATETIME NOT NULL, \n\t"BillingAddress" NVARCHAR(70), \n\t"BillingCity" NVARCHAR(40), | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-6 | NVARCHAR(70), \n\t"BillingCity" NVARCHAR(40), \n\t"BillingState" NVARCHAR(40), \n\t"BillingCountry" NVARCHAR(40), \n\t"BillingPostalCode" NVARCHAR(10), \n\t"Total" NUMERIC(10, 2) NOT NULL, \n\tPRIMARY KEY ("InvoiceId"), \n\tFOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")\n)\n\n/*\n3 rows from Invoice table:\nInvoiceId\tCustomerId\tInvoiceDate\tBillingAddress\tBillingCity\tBillingState\tBillingCountry\tBillingPostalCode\tTotal\n1\t2\t2009-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n2\t4\t2009-01-02 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n3\t8\t2009-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n*/\n\n\nCREATE TABLE "Track" (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL, \n\t"AlbumId" INTEGER, \n\t"MediaTypeId" INTEGER NOT NULL, \n\t"GenreId" INTEGER, \n\t"Composer" NVARCHAR(220), \n\t"Milliseconds" INTEGER NOT NULL, \n\t"Bytes" INTEGER, \n\t"UnitPrice" NUMERIC(10, 2) NOT NULL, \n\tPRIMARY KEY ("TrackId"), \n\tFOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"), \n\tFOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"), \n\tFOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")\n)\n\n/*\n3 rows from Track table:\nTrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-7 | Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\n*/\n\n\nCREATE TABLE "InvoiceLine" (\n\t"InvoiceLineId" INTEGER NOT NULL, \n\t"InvoiceId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\t"UnitPrice" NUMERIC(10, 2) NOT NULL, \n\t"Quantity" INTEGER NOT NULL, \n\tPRIMARY KEY ("InvoiceLineId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")\n)\n\n/*\n3 rows from InvoiceLine table:\nInvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n1\t1\t2\t0.99\t1\n2\t1\t4\t0.99\t1\n3\t2\t6\t0.99\t1\n*/\n\n\nCREATE TABLE "PlaylistTrack" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\tPRIMARY KEY ("PlaylistId", "TrackId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n\n/*\n3 rows from PlaylistTrack table:\nPlaylistId\tTrackId\n1\t3402\n1\t3389\n1\t3390\n*/', | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-8 | 'stop': ['\nSQLResult:']},
'SELECT COUNT(*) FROM Employee;',
{'query': 'SELECT COUNT(*) FROM Employee;', 'dialect': 'sqlite'},
'SELECT COUNT(*) FROM Employee;',
'[(8,)]']
If you are querying for several rows of a table you can select the maximum number of results you want to get by using the 'top_k' parameter (default is 10). This is useful for avoiding query results that exceed the prompt max length or consume tokens unnecessarily.
Sometimes, the format of the data is not obvious and it is optimal to include a sample of rows from the tables in the prompt to allow the LLM to understand the data before providing a final query. Here we will use this feature to let the LLM know that artists are saved with their full names by providing two rows from the Track table.
The sample rows are added to the prompt after each corresponding table's column information: | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-9 | > Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name", "Composer" FROM "Track" WHERE "Composer" LIKE '%Bach%' LIMIT 5
SQLResult: [('American Woman', 'B. Cummings/G. Peterson/M.J. Kale/R. Bachman'), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach'), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata', 'Johann Sebastian Bach')]
Answer:Tracks by Bach include 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.
> Finished chain. | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-10 | 'Tracks by Bach include \'American Woman\', \'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\', \'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\', \'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\', and \'Toccata and Fugue in D Minor, BWV 565: I. Toccata\'.'
In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first sample_rows_in_table_info sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns.
This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let's provide a custom definition and sample rows for the Track table with only a few columns:
custom_table_info = {
"Track": """CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer of all time
*/"""
}
Note how our custom table definition and sample rows for Track overrides the sample_rows_in_table_info parameter. Tables that are not overridden by custom_table_info, in this example Playlist, will have their table info gathered automatically as usual. | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-11 | > Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)] | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-12 | Answer:text='You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.\nUnless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.\nNever query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.\nPay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n\nUse the following format:\n\nQuestion: "Question here"\nSQLQuery: "SQL Query to run"\nSQLResult: "Result of the SQLQuery"\nAnswer: "Final answer here"\n\nOnly use the following tables:\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/\n\nQuestion: What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-13 | Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:' | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-14 | You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table. | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-15 | Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
2 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
*/
CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer of all time
*/ | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-16 | Question: What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
Answer: | https://python.langchain.com/docs/integrations/tools/sqlite |
f214ca03c2e5-17 | Answer:
{'input': 'What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:', 'top_k': '5', 'dialect': 'sqlite', 'table_info': '\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/', 'stop': ['\nSQLResult:']}
Examples of tracks by Bach include "American Woman", "Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace", "Aria Mit 30 Veränderungen, BWV 988 'Goldberg Variations': Aria", "Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude", and "Toccata and Fugue in D Minor, BWV 565: I. Toccata".
> Finished chain. | https://python.langchain.com/docs/integrations/tools/sqlite |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.