Tools#

Core toolkit implementations.

pydantic model langchain.tools.AIPluginTool[source]#

field api_spec: str [Required]#

field args_schema: Type[AIPluginToolSchema] = <class 'langchain.tools.plugin.AIPluginToolSchema'>#: Pydantic model class to validate and parse the tool’s input arguments.

field plugin: AIPlugin [Required]#

classmethod from_plugin_url(url: str) → langchain.tools.plugin.AIPluginTool[source]#

pydantic model langchain.tools.APIOperation[source]#

A model for a single API operation.

field base_url: str [Required]#: The base URL of the operation.

field description: Optional[str] = None#: The description of the operation.

field method: langchain.tools.openapi.utils.openapi_utils.HTTPVerb [Required]#: The HTTP method of the operation.

field operation_id: str [Required]#: The unique identifier of the operation.

field path: str [Required]#: The path of the operation.

field properties: Sequence[langchain.tools.openapi.utils.api_models.APIProperty] [Required]#

field request_body: Optional[langchain.tools.openapi.utils.api_models.APIRequestBody] = None#: The request body of the operation.

classmethod from_openapi_spec(spec: langchain.tools.openapi.utils.openapi_utils.OpenAPISpec, path: str, method: str) → langchain.tools.openapi.utils.api_models.APIOperation[source]#: Create an APIOperation from an OpenAPI spec.

classmethod from_openapi_url(spec_url: str, path: str, method: str) → langchain.tools.openapi.utils.api_models.APIOperation[source]#: Create an APIOperation from an OpenAPI URL.

to_typescript() → str[source]#: Get typescript string representation of the operation.

static ts_type_from_python(type_: Union[str, Type, tuple, None, enum.Enum]) → str[source]#

property body_params: List[str]#

property path_params: List[str]#

property query_params: List[str]#

pydantic model langchain.tools.AzureCogsFormRecognizerTool[source]#

Tool that queries the Azure Cognitive Services Form Recognizer API.

In order to set this up, follow instructions at: https://learn.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/quickstarts/get-started-sdks-rest-api?view=form-recog-3.0.0&pivots=programming-language-python

pydantic model langchain.tools.AzureCogsImageAnalysisTool[source]#

Tool that queries the Azure Cognitive Services Image Analysis API.

In order to set this up, follow instructions at: https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40

pydantic model langchain.tools.AzureCogsSpeech2TextTool[source]#

Tool that queries the Azure Cognitive Services Speech2Text API.

In order to set this up, follow instructions at: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speech-to-text?pivots=programming-language-python

pydantic model langchain.tools.AzureCogsText2SpeechTool[source]#

Tool that queries the Azure Cognitive Services Text2Speech API.

In order to set this up, follow instructions at: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-text-to-speech?pivots=programming-language-python

pydantic model langchain.tools.BaseTool[source]#

Interface LangChain tools must implement.

field args_schema: Optional[Type[pydantic.main.BaseModel]] = None#: Pydantic model class to validate and parse the tool’s input arguments.

field callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None#: Deprecated. Please use callbacks instead.

field callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None#: Callbacks to be called during tool execution.

field description: str [Required]#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field handle_tool_error: Optional[Union[bool, str, Callable[[langchain.tools.base.ToolException], str]]] = False#: Handle the content of the ToolException thrown.

field name: str [Required]#: The unique name of the tool that clearly communicates its purpose.

field return_direct: bool = False#

Whether to return the tool’s output directly. Setting this to True means

that after the tool is called, the AgentExecutor will stop looping.

field verbose: bool = False#: Whether to log the tool’s progress.

async arun(tool_input: Union[str, Dict], verbose: Optional[bool] = None, start_color: Optional[str] = 'green', color: Optional[str] = 'green', callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Any[source]#: Run the tool asynchronously.

run(tool_input: Union[str, Dict], verbose: Optional[bool] = None, start_color: Optional[str] = 'green', color: Optional[str] = 'green', callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Any[source]#: Run the tool.

property args: dict#

property is_single_input: bool#: Whether the tool only accepts a single input.

pydantic model langchain.tools.BingSearchResults[source]#

Tool that has capability to query the Bing Search API and get back json.

field api_wrapper: langchain.utilities.bing_search.BingSearchAPIWrapper [Required]#

field num_results: int = 4#

pydantic model langchain.tools.BingSearchRun[source]#

Tool that adds the capability to query the Bing search API.

field api_wrapper: langchain.utilities.bing_search.BingSearchAPIWrapper [Required]#

pydantic model langchain.tools.BraveSearch[source]#

field search_wrapper: BraveSearchWrapper [Required]#

classmethod from_api_key(api_key: str, search_kwargs: Optional[dict] = None, **kwargs: Any) → langchain.tools.brave_search.tool.BraveSearch[source]#

pydantic model langchain.tools.ClickTool[source]#

field args_schema: Type[BaseModel] = <class 'langchain.tools.playwright.click.ClickToolInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Click on an element with the given CSS selector'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'click_element'#: The unique name of the tool that clearly communicates its purpose.

field playwright_strict: bool = False#: Whether to employ Playwright’s strict mode when clicking on elements.

field playwright_timeout: float = 1000#: Timeout (in ms) for Playwright to wait for element to be ready.

field visible_only: bool = True#: Whether to consider only visible elements.

pydantic model langchain.tools.CopyFileTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.copy.FileCopyInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Create a copy of a file in a specified location'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'copy_file'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.CurrentWebPageTool[source]#

field args_schema: Type[BaseModel] = <class 'pydantic.main.BaseModel'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Returns the URL of the current page'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'current_webpage'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.DeleteFileTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.delete.FileDeleteInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Delete a file'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'file_delete'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.DuckDuckGoSearchResults[source]#

Tool that queries the Duck Duck Go Search API and get back json.

field api_wrapper: langchain.utilities.duckduckgo_search.DuckDuckGoSearchAPIWrapper [Optional]#

field num_results: int = 4#

pydantic model langchain.tools.DuckDuckGoSearchRun[source]#

Tool that adds the capability to query the DuckDuckGo search API.

field api_wrapper: langchain.utilities.duckduckgo_search.DuckDuckGoSearchAPIWrapper [Optional]#

pydantic model langchain.tools.ExtractHyperlinksTool[source]#

Extract all hyperlinks on the page.

field args_schema: Type[BaseModel] = <class 'langchain.tools.playwright.extract_hyperlinks.ExtractHyperlinksToolInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Extract all hyperlinks on the current webpage'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'extract_hyperlinks'#: The unique name of the tool that clearly communicates its purpose.

static scrape_page(page: Any, html_content: str, absolute_urls: bool) → str[source]#

pydantic model langchain.tools.ExtractTextTool[source]#

field args_schema: Type[BaseModel] = <class 'pydantic.main.BaseModel'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Extract all the text on the current webpage'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'extract_text'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.FileSearchTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.file_search.FileSearchInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Recursively search for files in a subdirectory that match the regex pattern'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'file_search'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GetElementsTool[source]#

field args_schema: Type[BaseModel] = <class 'langchain.tools.playwright.get_elements.GetElementsToolInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Retrieve elements in the current web page matching the given CSS selector'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'get_elements'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GmailCreateDraft[source]#

field args_schema: Type[langchain.tools.gmail.create_draft.CreateDraftSchema] = <class 'langchain.tools.gmail.create_draft.CreateDraftSchema'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Use this tool to create a draft email with the provided message fields.'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'create_gmail_draft'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GmailGetMessage[source]#

field args_schema: Type[langchain.tools.gmail.get_message.SearchArgsSchema] = <class 'langchain.tools.gmail.get_message.SearchArgsSchema'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Use this tool to fetch an email by message ID. Returns the thread ID, snipet, body, subject, and sender.'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'get_gmail_message'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GmailGetThread[source]#

field args_schema: Type[langchain.tools.gmail.get_thread.GetThreadSchema] = <class 'langchain.tools.gmail.get_thread.GetThreadSchema'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Use this tool to search for email messages. The input must be a valid Gmail query. The output is a JSON list of messages.'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'get_gmail_thread'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GmailSearch[source]#

field args_schema: Type[langchain.tools.gmail.search.SearchArgsSchema] = <class 'langchain.tools.gmail.search.SearchArgsSchema'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Use this tool to search for email messages or threads. The input must be a valid Gmail query. The output is a JSON list of the requested resource.'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'search_gmail'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GmailSendMessage[source]#

field description: str = 'Use this tool to send email messages. The input is the message, recipents'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'send_gmail_message'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.GooglePlacesTool[source]#

Tool that adds the capability to query the Google places API.

field api_wrapper: langchain.utilities.google_places_api.GooglePlacesAPIWrapper [Optional]#

pydantic model langchain.tools.GoogleSearchResults[source]#

Tool that has capability to query the Google Search API and get back json.

field api_wrapper: langchain.utilities.google_search.GoogleSearchAPIWrapper [Required]#

field num_results: int = 4#

pydantic model langchain.tools.GoogleSearchRun[source]#

Tool that adds the capability to query the Google search API.

field api_wrapper: langchain.utilities.google_search.GoogleSearchAPIWrapper [Required]#

pydantic model langchain.tools.GoogleSerperResults[source]#

Tool that has capability to query the Serper.dev Google Search API and get back json.

field api_wrapper: langchain.utilities.google_serper.GoogleSerperAPIWrapper [Optional]#

pydantic model langchain.tools.GoogleSerperRun[source]#

Tool that adds the capability to query the Serper.dev Google search API.

field api_wrapper: langchain.utilities.google_serper.GoogleSerperAPIWrapper [Required]#

pydantic model langchain.tools.HumanInputRun[source]#

Tool that adds the capability to ask user for input.

field input_func: Callable [Optional]#

field prompt_func: Callable[[str], None] [Optional]#

pydantic model langchain.tools.IFTTTWebhook[source]#

IFTTT Webhook.

Parameters

name – name of the tool
description – description of the tool
url – url to hit with the json event.

field url: str [Required]#

pydantic model langchain.tools.InfoPowerBITool[source]#

Tool for getting metadata about a PowerBI Dataset.

field powerbi: langchain.utilities.powerbi.PowerBIDataset [Required]#

pydantic model langchain.tools.ListDirectoryTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'List files and directories in a specified folder'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'list_directory'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.ListPowerBITool[source]#

Tool for getting tables names.

field powerbi: langchain.utilities.powerbi.PowerBIDataset [Required]#

pydantic model langchain.tools.MetaphorSearchResults[source]#

Tool that has capability to query the Metaphor Search API and get back json.

field api_wrapper: langchain.utilities.metaphor_search.MetaphorSearchAPIWrapper [Required]#

pydantic model langchain.tools.MoveFileTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.move.FileMoveInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Move or rename a file from one location to another'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'move_file'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.NavigateBackTool[source]#

Navigate back to the previous page in the browser history.

field args_schema: Type[BaseModel] = <class 'pydantic.main.BaseModel'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Navigate back to the previous page in the browser history'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'previous_webpage'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.NavigateTool[source]#

field args_schema: Type[BaseModel] = <class 'langchain.tools.playwright.navigate.NavigateToolInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Navigate a browser to the specified URL'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'navigate_browser'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.OpenAPISpec[source]#

OpenAPI Model that removes misformatted parts of the spec.

classmethod from_file(path: Union[str, pathlib.Path]) → langchain.tools.openapi.utils.openapi_utils.OpenAPISpec[source]#: Get an OpenAPI spec from a file path.

classmethod from_spec_dict(spec_dict: dict) → langchain.tools.openapi.utils.openapi_utils.OpenAPISpec[source]#: Get an OpenAPI spec from a dict.

classmethod from_text(text: str) → langchain.tools.openapi.utils.openapi_utils.OpenAPISpec[source]#: Get an OpenAPI spec from a text.

classmethod from_url(url: str) → langchain.tools.openapi.utils.openapi_utils.OpenAPISpec[source]#: Get an OpenAPI spec from a URL.

static get_cleaned_operation_id(operation: openapi_schema_pydantic.v3.v3_1_0.operation.Operation, path: str, method: str) → str[source]#: Get a cleaned operation id from an operation id.

get_methods_for_path(path: str) → List[str][source]#: Return a list of valid methods for the specified path.

get_operation(path: str, method: str) → openapi_schema_pydantic.v3.v3_1_0.operation.Operation[source]#: Get the operation object for a given path and HTTP method.

get_parameters_for_operation(operation: openapi_schema_pydantic.v3.v3_1_0.operation.Operation) → List[openapi_schema_pydantic.v3.v3_1_0.parameter.Parameter][source]#: Get the components for a given operation.

get_referenced_schema(ref: openapi_schema_pydantic.v3.v3_1_0.reference.Reference) → openapi_schema_pydantic.v3.v3_1_0.schema.Schema[source]#: Get a schema (or nested reference) or err.

get_request_body_for_operation(operation: openapi_schema_pydantic.v3.v3_1_0.operation.Operation) → Optional[openapi_schema_pydantic.v3.v3_1_0.request_body.RequestBody][source]#: Get the request body for a given operation.

classmethod parse_obj(obj: dict) → langchain.tools.openapi.utils.openapi_utils.OpenAPISpec[source]#

property base_url: str#: Get the base url.

pydantic model langchain.tools.OpenWeatherMapQueryRun[source]#

Tool that adds the capability to query using the OpenWeatherMap API.

field api_wrapper: langchain.utilities.openweathermap.OpenWeatherMapAPIWrapper [Optional]#

pydantic model langchain.tools.QueryPowerBITool[source]#

Tool for querying a Power BI Dataset.

Validators

raise_deprecation » all fields
validate_llm_chain_input_variables » llm_chain

field examples: Optional[str] = '\nQuestion: How many rows are in the table <table>?\nDAX: EVALUATE ROW("Number of rows", COUNTROWS(<table>))\n----\nQuestion: How many rows are in the table <table> where <column> is not empty?\nDAX: EVALUATE ROW("Number of rows", COUNTROWS(FILTER(<table>, <table>[<column>] <> "")))\n----\nQuestion: What was the average of <column> in <table>?\nDAX: EVALUATE ROW("Average", AVERAGE(<table>[<column>]))\n----\n'#

field llm_chain: langchain.chains.llm.LLMChain [Required]#

field max_iterations: int = 5#

field powerbi: langchain.utilities.powerbi.PowerBIDataset [Required]#

field session_cache: Dict[str, Any] [Optional]#

field template: Optional[str] = '\nAnswer the question below with a DAX query that can be sent to Power BI. DAX queries have a simple syntax comprised of just one required keyword, EVALUATE, and several optional keywords: ORDER BY, START AT, DEFINE, MEASURE, VAR, TABLE, and COLUMN. Each keyword defines a statement used for the duration of the query. Any time < or > are used in the text below it means that those values need to be replaced by table, columns or other things. If the question is not something you can answer with a DAX query, reply with "I cannot answer this" and the question will be escalated to a human.\n\nSome DAX functions return a table instead of a scalar, and must be wrapped in a function that evaluates the table and returns a scalar; unless the table is a single column, single row table, then it is treated as a scalar value. Most DAX functions require one or more arguments, which can include tables, columns, expressions, and values. However, some functions, such as PI, do not require any arguments, but always require parentheses to indicate the null argument. For example, you must always type PI(), not PI. You can also nest functions within other functions. \n\nSome commonly used functions are:\nEVALUATE <table> - At the most basic level, a DAX query is an EVALUATE statement containing a table expression. At least one EVALUATE statement is required, however, a query can contain any number of EVALUATE statements.\nEVALUATE <table> ORDER BY <expression> ASC or DESC - The optional ORDER BY keyword defines one or more expressions used to sort query results. Any expression that can be evaluated for each row of the result is valid.\nEVALUATE <table> ORDER BY <expression> ASC or DESC START AT <value> or <parameter> - The optional START AT keyword is used inside an ORDER BY clause. It defines the value at which the query results begin.\nDEFINE MEASURE | VAR; EVALUATE <table> - The optional DEFINE keyword introduces one or more calculated entity definitions that exist only for the duration of the query. Definitions precede the EVALUATE statement and are valid for all EVALUATE statements in the query. Definitions can be variables, measures, tables1, and columns1. Definitions can reference other definitions that appear before or after the current definition. At least one definition is required if the DEFINE keyword is included in a query.\nMEASURE <table name>[<measure name>] = <scalar expression> - Introduces a measure definition in a DEFINE statement of a DAX query.\nVAR <name> = <expression> - Stores the result of an expression as a named variable, which can then be passed as an argument to other measure expressions. Once resultant values have been calculated for a variable expression, those values do not change, even if the variable is referenced in another expression.\n\nFILTER(<table>,<filter>) - Returns a table that represents a subset of another table or expression, where <filter> is a Boolean expression that is to be evaluated for each row of the table. For example, [Amount] > 0 or [Region] = "France"\nROW(<name>, <expression>) - Returns a table with a single row containing values that result from the expressions given to each column.\nDISTINCT(<column>) - Returns a one-column table that contains the distinct values from the specified column. In other words, duplicate values are removed and only unique values are returned. This function cannot be used to Return values into a cell or column on a worksheet; rather, you nest the DISTINCT function within a formula, to get a list of distinct values that can be passed to another function and then counted, summed, or used for other operations.\nDISTINCT(<table>) - Returns a table by removing duplicate rows from another table or expression.\n\nAggregation functions, names with a A in it, handle booleans and empty strings in appropriate ways, while the same function without A only uses the numeric values in a column. Functions names with an X in it can include a expression as an argument, this will be evaluated for each row in the table and the result will be used in the regular function calculation, these are the functions:\nCOUNT(<column>), COUNTA(<column>), COUNTX(<table>,<expression>), COUNTAX(<table>,<expression>), COUNTROWS([<table>]), COUNTBLANK(<column>), DISTINCTCOUNT(<column>), DISTINCTCOUNTNOBLANK (<column>) - these are all variantions of count functions.\nAVERAGE(<column>), AVERAGEA(<column>), AVERAGEX(<table>,<expression>) - these are all variantions of average functions.\nMAX(<column>), MAXA(<column>), MAXX(<table>,<expression>) - these are all variantions of max functions.\nMIN(<column>), MINA(<column>), MINX(<table>,<expression>) - these are all variantions of min functions.\nPRODUCT(<column>), PRODUCTX(<table>,<expression>) - these are all variantions of product functions.\nSUM(<column>), SUMX(<table>,<expression>) - these are all variantions of sum functions.\n\nDate and time functions:\nDATE(year, month, day) - Returns a date value that represents the specified year, month, and day.\nDATEDIFF(date1, date2, <interval>) - Returns the difference between two date values, in the specified interval, that can be SECOND, MINUTE, HOUR, DAY, WEEK, MONTH, QUARTER, YEAR.\nDATEVALUE(<date_text>) - Returns a date value that represents the specified date.\nYEAR(<date>), QUARTER(<date>), MONTH(<date>), DAY(<date>), HOUR(<date>), MINUTE(<date>), SECOND(<date>) - Returns the part of the date for the specified date.\n\nFinally, make sure to escape double quotes with a single backslash, and make sure that only table names have single quotes around them, while names of measures or the values of columns that you want to compare against are in escaped double quotes. Newlines are not necessary and can be skipped. The queries are serialized as json and so will have to fit be compliant with json syntax. Sometimes you will get a question, a DAX query and a error, in that case you need to rewrite the DAX query to get the correct answer.\n\nThe following tables exist: {tables}\n\nand the schema\'s for some are given here:\n{schemas}\n\nExamples:\n{examples}\n\nQuestion: {tool_input}\nDAX: \n'#

pydantic model langchain.tools.ReadFileTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.read.ReadFileInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Read file from disk'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'read_file'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.SceneXplainTool[source]#

Tool that adds the capability to explain images.

field api_wrapper: langchain.utilities.scenexplain.SceneXplainAPIWrapper [Optional]#

pydantic model langchain.tools.ShellTool[source]#

Tool to run shell commands.

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.shell.tool.ShellInput'>#: Schema for input arguments.

field description: str = 'Run shell commands on this Linux machine.'#: Description of tool.

field name: str = 'terminal'#: Name of tool.

field process: langchain.utilities.bash.BashProcess [Optional]#: Bash process to run commands.

pydantic model langchain.tools.SteamshipImageGenerationTool[source]#

field model_name: ModelName [Required]#

field return_urls: Optional[bool] = False#

field size: Optional[str] = '512x512'#

field steamship: Steamship [Required]#

pydantic model langchain.tools.StructuredTool[source]#

Tool that can operate on any number of inputs.

field args_schema: Type[pydantic.main.BaseModel] [Required]#

The input arguments’ schema.

The tool schema.

field coroutine: Optional[Callable[[...], Awaitable[Any]]] = None#: The asynchronous version of the function.

field description: str = ''#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field func: Callable[[...], Any] [Required]#: The function to run when the tool is called.

classmethod from_function(func: Callable, name: Optional[str] = None, description: Optional[str] = None, return_direct: bool = False, args_schema: Optional[Type[pydantic.main.BaseModel]] = None, infer_schema: bool = True, **kwargs: Any) → langchain.tools.base.StructuredTool[source]#

property args: dict#: The tool’s input arguments.

pydantic model langchain.tools.Tool[source]#

Tool that takes in function or coroutine directly.

field args_schema: Optional[Type[pydantic.main.BaseModel]] = None#: Pydantic model class to validate and parse the tool’s input arguments.

field callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None#: Deprecated. Please use callbacks instead.

field callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None#: Callbacks to be called during tool execution.

field coroutine: Optional[Callable[[...], Awaitable[str]]] = None#: The asynchronous version of the function.

field description: str = ''#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field func: Callable[[...], str] [Required]#: The function to run when the tool is called.

field handle_tool_error: Optional[Union[bool, str, Callable[[langchain.tools.base.ToolException], str]]] = False#: Handle the content of the ToolException thrown.

field name: str [Required]#: The unique name of the tool that clearly communicates its purpose.

field return_direct: bool = False#

Whether to return the tool’s output directly. Setting this to True means

that after the tool is called, the AgentExecutor will stop looping.

field verbose: bool = False#: Whether to log the tool’s progress.

classmethod from_function(func: Callable, name: str, description: str, return_direct: bool = False, args_schema: Optional[Type[pydantic.main.BaseModel]] = None, **kwargs: Any) → langchain.tools.base.Tool[source]#: Initialize tool from a function.

property args: dict#: The tool’s input arguments.

pydantic model langchain.tools.VectorStoreQATool[source]#

Tool for the VectorDBQA chain. To be initialized with name and chain.

static get_description(name: str, description: str) → str[source]#

pydantic model langchain.tools.VectorStoreQAWithSourcesTool[source]#

Tool for the VectorDBQAWithSources chain.

static get_description(name: str, description: str) → str[source]#

pydantic model langchain.tools.WikipediaQueryRun[source]#

Tool that adds the capability to search using the Wikipedia API.

field api_wrapper: langchain.utilities.wikipedia.WikipediaAPIWrapper [Required]#

pydantic model langchain.tools.WolframAlphaQueryRun[source]#

Tool that adds the capability to query using the Wolfram Alpha SDK.

field api_wrapper: langchain.utilities.wolfram_alpha.WolframAlphaAPIWrapper [Required]#

pydantic model langchain.tools.WriteFileTool[source]#

field args_schema: Type[pydantic.main.BaseModel] = <class 'langchain.tools.file_management.write.WriteFileInput'>#: Pydantic model class to validate and parse the tool’s input arguments.

field description: str = 'Write file to disk'#

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

field name: str = 'write_file'#: The unique name of the tool that clearly communicates its purpose.

pydantic model langchain.tools.YouTubeSearchTool[source]#

pydantic model langchain.tools.ZapierNLAListActions[source]#

Returns a list of all exposed (enabled) actions associated with

current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return list can be empty if no actions exposed. Else will contain a list of action objects:

[{: “id”: str, “description”: str, “params”: Dict[str, str]

}]

params will always contain an instructions key, the only required param. All others optional and if provided will override any AI guesses (see “understanding the AI guessing flow” here: https://nla.zapier.com/api/v1/docs)

Parameters: None –

field api_wrapper: langchain.utilities.zapier.ZapierNLAWrapper [Optional]#

pydantic model langchain.tools.ZapierNLARunAction[source]#

Executes an action that is identified by action_id, must be exposed

(enabled) by the current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return JSON is guaranteed to be less than ~500 words (350 tokens) making it safe to inject into the prompt of another LLM call.

Parameters

action_id – a specific action ID (from list actions) of the action to execute (the set api_key must be associated with the action owner)
instructions – a natural language instruction string for using the action (eg. “get the latest email from Mike Knoop” for “Gmail: find email” action)
params – a dict, optional. Any params provided will override AI guesses from instructions (see “understanding the AI guessing flow” here: https://nla.zapier.com/api/v1/docs)

field action_id: str [Required]#

field api_wrapper: langchain.utilities.zapier.ZapierNLAWrapper [Optional]#

field base_prompt: str = 'A wrapper around Zapier NLA actions. The input to this tool is a natural language instruction, for example "get the latest email from my bank" or "send a slack message to the #general channel". Each tool will have params associated with it that are specified as a list. You MUST take into account the params when creating the instruction. For example, if the params are [\'Message_Text\', \'Channel\'], your instruction should be something like \'send a slack message to the #general channel with the text hello world\'. Another example: if the params are [\'Calendar\', \'Search_Term\'], your instruction should be something like \'find the meeting in my personal calendar at 3pm\'. Do not make up params, they will be explicitly specified in the tool description. If you do not have enough information to fill in the params, just say \'not enough information provided in the instruction, missing <param>\'. If you get a none or null response, STOP EXECUTION, do not try to another tool!This tool specifically used for: {zapier_description}, and has params: {params}'#

field params: Optional[dict] = None#

field params_schema: Dict[str, str] [Optional]#

field zapier_description: str [Required]#

langchain.tools.tool(*args: Union[str, Callable], return_direct: bool = False, args_schema: Optional[Type[pydantic.main.BaseModel]] = None, infer_schema: bool = True) → Callable[source]#

Make tools out of functions, can be used with or without arguments.

Parameters

*args – The arguments to the tool.
return_direct – Whether to return directly from the tool rather than continuing the agent loop.
args_schema – optional argument schema for user to specify
infer_schema – Whether to infer the schema of the arguments from the function’s signature. This also makes the resultant tool accept a dictionary input to its run() function.

Requires:

Function must be of type (str) -> str
Function must have a docstring

Examples

@tool
def search_api(query: str) -> str:
    # Searches the API for the query.
    return

@tool("search", return_direct=True)
def search_api(query: str) -> str:
    # Searches the API for the query.
    return