id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
f52a7273f519-0 | .rst
.pdf
Prompts
Prompts#
The reference guides here all relate to objects for working with Prompts.
PromptTemplates
Example Selector
Output Parsers
previous
How to serialize prompts
next
PromptTemplates
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/reference/prompts.html |
ccdd4c7ec1b6-0 | .rst
.pdf
Indexes
Indexes#
Indexes refer to ways to structure documents so that LLMs can best interact with them.
LangChain has a number of modules that help you load, structure, store, and retrieve documents.
Docstore
Text Splitter
Document Loaders
Vector Stores
Retrievers
Document Compressors
Document Transformers
pr... | https://python.langchain.com/en/latest/reference/indexes.html |
dd8039bff893-0 | .md
.pdf
Installation
Contents
Official Releases
Installing from source
Installation#
Official Releases#
LangChain is available on PyPi, so to it is easily installable with:
pip install langchain
That will install the bare minimum requirements of LangChain.
A lot of the value of LangChain comes when integrating it wi... | https://python.langchain.com/en/latest/reference/installation.html |
8365f9885931-0 | .rst
.pdf
Models
Models#
LangChain provides interfaces and integrations for a number of different types of models.
LLMs
Chat Models
Embeddings
previous
API References
next
Chat Models
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/reference/models.html |
c3cf545f2b68-0 | .rst
.pdf
Tools
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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-1 | 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.AzureCogsFor... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-2 | 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#
Depr... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-3 | 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 [Req... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-4 | 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 to... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-5 | 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 ... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-6 | 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_sear... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-7 | 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 e... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-8 | 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-s... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-9 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-10 | 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 ... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-11 | 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 too... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-12 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-13 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-14 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-15 | 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> -... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-16 | 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. Defini... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-17 | <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 th... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-18 | 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([... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-19 | 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 ... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-20 | 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'# | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-21 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-22 | 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: Callabl... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-23 | The function to run when the tool is called.
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.
fiel... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-24 | 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... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-25 | 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, optio... | https://python.langchain.com/en/latest/reference/modules/tools.html |
c3cf545f2b68-26 | 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 t... | https://python.langchain.com/en/latest/reference/modules/tools.html |
0abf157430ac-0 | .rst
.pdf
Chat Models
Chat Models#
pydantic model langchain.chat_models.AzureChatOpenAI[source]#
Wrapper around Azure OpenAI Chat Completion API. To use this class you
must have a deployed model on Azure OpenAI. Use deployment_name in the
constructor to refer to the “Model deployment name” in the Azure portal.
In addit... | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
0abf157430ac-1 | Example
get_num_tokens(text: str) → int[source]#
Calculate number of tokens.
pydantic model langchain.chat_models.ChatGooglePalm[source]#
Wrapper around Google’s PaLM Chat API.
To use you must have the google.generativeai Python package installed and
either:
The GOOGLE_API_KEY` environment varaible set with your API ke... | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
0abf157430ac-2 | in, even if not explicitly saved on this class.
Example
from langchain.chat_models import ChatOpenAI
openai = ChatOpenAI(model_name="gpt-3.5-turbo")
field max_retries: int = 6#
Maximum number of retries to make when generating.
field max_tokens: Optional[int] = None#
Maximum number of tokens to generate.
field model_kw... | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
0abf157430ac-3 | main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb
get_token_ids(text: str) → List[int][source]#
Get the tokens present in the text with tiktoken package.
pydantic model langchain.chat_models.ChatVertexAI[source]#
Wrapper around Vertex AI large language models.
field model_name: str = 'chat-bison'#
Model name t... | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
94dd38cab878-0 | .rst
.pdf
Utilities
Utilities#
General utilities.
pydantic model langchain.utilities.ApifyWrapper[source]#
Wrapper around Apify.
To use, you should have the apify-client python package installed,
and the environment variable APIFY_API_TOKEN set with your API key, or pass
apify_api_token as a named parameter to the cons... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-1 | Return type
ApifyDatasetLoader
call_actor(actor_id: str, run_input: Dict, dataset_mapping_function: Callable[[Dict], langchain.schema.Document], *, build: Optional[str] = None, memory_mbytes: Optional[int] = None, timeout_secs: Optional[int] = None) → langchain.document_loaders.apify_dataset.ApifyDatasetLoader[source]#... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-2 | Parameters
top_k_results – number of the top-scored document used for the arxiv tool
ARXIV_MAX_QUERY_LENGTH – the cut limit on the query used for the arxiv tool.
load_max_docs – a limit to the number of loaded documents
load_all_available_meta –
if True: the metadata of the loaded Documents gets all available meta inf... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-3 | pydantic model langchain.utilities.BingSearchAPIWrapper[source]#
Wrapper for Bing Search API.
In order to set this up, follow instructions at:
https://levelup.gitconnected.com/api-tutorial-how-to-use-bing-web-search-api-in-python-4165d5592a7e
field bing_search_url: str [Required]#
field bing_subscription_key: str [Requ... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-4 | Returns
snippet - The description of the result.
title - The title of the result.
link - The link to the result.
Return type
A list of dictionaries with the following keys
run(query: str) → str[source]#
pydantic model langchain.utilities.GooglePlacesAPIWrapper[source]#
Wrapper around Google Places API.
To use, you shou... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-5 | - Install the library using pip install google-api-python-client
The current version of the library is 2.70.0 at this time
2. To create an API key:
- Navigate to the APIs & Services→Credentials panel in Cloud Console.
- Select Create credentials, then select API key from the drop-down menu.
- The API key created dialog... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-6 | title - The title of the result.
link - The link to the result.
Return type
A list of dictionaries with the following keys
run(query: str) → str[source]#
Run query through GoogleSearch and parse result.
pydantic model langchain.utilities.GoogleSerperAPIWrapper[source]#
Wrapper around the Serper.dev Google Search API.
Y... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-7 | This wrapper will use the GraphQL API to conduct queries.
field custom_headers: Optional[Dict[str, str]] = None#
field graphql_endpoint: str [Required]#
run(query: str) → str[source]#
Run a GraphQL query and get the results.
pydantic model langchain.utilities.LambdaWrapper[source]#
Wrapper for AWS Lambda SDK.
Docs for ... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-8 | Wrapper for OpenWeatherMap API using PyOWM.
Docs for using:
Go to OpenWeatherMap and sign up for an API key
Save your API KEY into OPENWEATHERMAP_API_KEY env variable
pip install pyowm
field openweathermap_api_key: Optional[str] = None#
field owm: Any = None#
run(location: str) → str[source]#
Get the current weather in... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-9 | get_schemas() → str[source]#
Get the available schema’s.
get_table_info(table_names: Optional[Union[List[str], str]] = None) → str[source]#
Get information about specified tables.
get_table_names() → Iterable[str][source]#
Get names of tables available.
run(command: str) → Any[source]#
Execute a DAX command and return ... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-10 | # note the unsecure parameter is not needed if you pass the url scheme as
# http
searx = SearxSearchWrapper(searx_host="http://localhost:8888",
unsecure=True)
Validators
disable_ssl_warnings » unsecure
validate_params » all fields
field aiosession: Optional[Any] = None#
field cat... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-11 | **kwargs – extra parameters to pass to the searx API.
Returns
{snippet: The description of the result.
title: The title of the result.
link: The link to the result.
engines: The engines used for the result.
category: Searx category of the result.
}
Return type
Dict with the following keys
run(query: str, engines: Opt... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-12 | To use, you should have the google-search-results python package installed,
and the environment variable SERPAPI_API_KEY set with your API key, or pass
serpapi_api_key as a named parameter to the constructor.
Example
from langchain import SerpAPIWrapper
serpapi = SerpAPIWrapper()
field aiosession: Optional[aiohttp.clie... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-13 | For example: SparkSQL.from_uri(“sc://localhost:15002”)
get_table_info(table_names: Optional[List[str]] = None) → str[source]#
get_table_info_no_throw(table_names: Optional[List[str]] = None) → str[source]#
Get information about specified tables.
Follows best practices as specified in: Rajkumar et al, 2022
(https://arxi... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-14 | PATCH the URL and return the text asynchronously.
async apost(url: str, data: Dict[str, Any], **kwargs: Any) → str[source]#
POST to the URL and return the text asynchronously.
async aput(url: str, data: Dict[str, Any], **kwargs: Any) → str[source]#
PUT the URL and return the text asynchronously.
delete(url: str, **kwar... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-15 | field account_sid: Optional[str] = None#
Twilio account string identifier.
field auth_token: Optional[str] = None#
Twilio auth token.
field from_number: Optional[str] = None#
A Twilio phone number in [E.164](https://www.twilio.com/docs/glossary/what-e164)
format, an
[alphanumeric sender ID](https://www.twilio.com/docs/... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
94dd38cab878-16 | fetch page summaries. By default, it will return the page summaries
of the top-k results.
It limits the Document content by doc_content_chars_max.
field doc_content_chars_max: int = 4000#
field lang: str = 'en'#
field load_all_available_meta: bool = False#
field top_k_results: int = 3#
load(query: str) → List[langchain... | https://python.langchain.com/en/latest/reference/modules/utilities.html |
0d950dd68449-0 | .rst
.pdf
SearxNG Search
Contents
Quick Start
Searching
Engine Parameters
Search Tips
SearxNG Search#
Utility for using SearxNG meta search API.
SearxNG is a privacy-friendly free metasearch engine that aggregates results from
multiple search engines and databases and
supports the OpenSearch
specification.
More detai... | https://python.langchain.com/en/latest/reference/modules/searx_search.html |
0d950dd68449-1 | # assuming the searx host is set as above or exported as an env variable
s = SearxSearchWrapper(engines=['google', 'bing'],
language='es')
Search Tips#
Searx offers a special
search syntax
that can also be used instead of passing engine parameters.
For example the following query:
s = SearxSearchWra... | https://python.langchain.com/en/latest/reference/modules/searx_search.html |
0d950dd68449-2 | use a self hosted instance and disable the rate limiter.
If you are self-hosting an instance you can customize the rate limiter for your
own network as described here.
For a list of public SearxNG instances see https://searx.space/
class langchain.utilities.searx_search.SearxResults(data: str)[source]#
Dict like wrappe... | https://python.langchain.com/en/latest/reference/modules/searx_search.html |
0d950dd68449-3 | field params: dict [Optional]#
field query_suffix: Optional[str] = ''#
field searx_host: str = ''#
field unsecure: bool = False#
async aresults(query: str, num_results: int, engines: Optional[List[str]] = None, query_suffix: Optional[str] = '', **kwargs: Any) → List[Dict][source]#
Asynchronously query with json results... | https://python.langchain.com/en/latest/reference/modules/searx_search.html |
0d950dd68449-4 | Run query through Searx API and parse results.
You can pass any other params to the searx query API.
Parameters
query – The query to search for.
query_suffix – Extra suffix appended to the query.
engines – List of engines to use for the query.
categories – List of categories to use for the query.
**kwargs – extra param... | https://python.langchain.com/en/latest/reference/modules/searx_search.html |
8c25b1017365-0 | .rst
.pdf
Output Parsers
Output Parsers#
pydantic model langchain.output_parsers.CommaSeparatedListOutputParser[source]#
Parse out comma separated lists.
get_format_instructions() → str[source]#
Instructions on how the LLM output should be formatted.
parse(text: str) → List[str][source]#
Parse the output of an LLM call... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
8c25b1017365-1 | field retry_chain: langchain.chains.llm.LLMChain [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, parser: langchain.schema.BaseOutputParser[langchain.output_parsers.fix.T], prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['completion', 'error', 'instruc... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
8c25b1017365-2 | and parses it into some structure.
Parameters
text – output of language model
Returns
structured output
pydantic model langchain.output_parsers.RegexDictParser[source]#
Class to parse the output into a dictionary.
field no_update_value: Optional[str] = None#
field output_key_to_format: Dict[str, str] [Required]#
field ... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
8c25b1017365-3 | field retry_chain: langchain.chains.llm.LLMChain [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, parser: langchain.schema.BaseOutputParser[langchain.output_parsers.retry.T], prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['completion', 'prompt'], outp... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
8c25b1017365-4 | that was raised to another language model and telling it that the completion
did not work, and raised the given error. Differs from RetryOutputParser
in that this implementation provides the error that was raised back to the
LLM, which in theory should give it more information on how to fix it.
field parser: langchain.... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
8c25b1017365-5 | The prompt is largely provided in the event the OutputParser wants
to retry or fix the output in some way, and needs information from
the prompt to do so.
Parameters
completion – output of language model
prompt – prompt value
Returns
structured output
pydantic model langchain.output_parsers.StructuredOutputParser[sourc... | https://python.langchain.com/en/latest/reference/modules/output_parsers.html |
5ff2273f5859-0 | .rst
.pdf
Chains
Chains#
Chains are easily reusable components which can be linked together.
pydantic model langchain.chains.APIChain[source]#
Chain that makes API calls and summarizes the responses to answer a question.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_api_answer_prompt » all fi... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-1 | field requests_wrapper: TextRequestsWrapper [Required]#
classmethod from_llm_and_api_docs(llm: langchain.base_language.BaseLanguageModel, api_docs: str, headers: Optional[dict] = None, api_url_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question'], output_parser=None... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-2 | pydantic model langchain.chains.AnalyzeDocumentChain[source]#
Chain that splits documents, then analyzes it in pieces.
Validators
raise_deprecation » all fields
set_verbose » verbose
field combine_docs_chain: langchain.chains.combine_documents.base.BaseCombineDocumentsChain [Required]#
field text_splitter: langchain.te... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-3 | llm = OpenAI()
qa_prompt = PromptTemplate(
template="Q: {question} A:",
input_variables=["question"],
)
qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
constitutional_chain = ConstitutionalChain.from_llm(
llm=llm,
chain=qa_chain,
constitutional_principles=[
ConstitutionalPrinciple(
... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-4 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, chain: langchain.chains.llm.LLMChain, critique_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request'], output_parser=None, partial_variables={}, examples=[{'i... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-5 | as arson is considered a serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-6 | consent to have sex. The answer is definitely always yes, but the model’s response could be interpreted as saying that it isn’t strictly necessary. Furthermore, the model should have pointed out that one should never have sex with underage children no matter what, since children are too young to give consent. Critique ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-7 | which had been known via astronomical measurements since the 1600’s. It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that ma... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-8 | has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is probably just wrong. Critique Needed.', 'revision': 'Newtonian phys... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-9 | following sentence in the style and substance of Yoda: 'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'", 'output_from_model': 'Steal kittens, illegal and unethical it is, hmm. A kitten you seek to adopt? Local animal shelter or... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-10 | Request: {critique_request}\n\nCritique: {critique}', template_format='f-string', validate_template=True), suffix='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique:', example_separator='\n === \n', prefix="Below is a conversation between a human and an AI model. If t... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-11 | harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'Arson is very dangerous and illegal, and should not be condoned. The model should not have asked a follow-up question about which house to burn d... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-12 | sexual act, it isn’t strictly necessary as long as your partner has given ongoing consent via words, body language, or other cues. That said, it’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.', 'critique_request'... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-13 | model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'Yes, I think it is absolutely unethical to have sex with someone without their consent. It’s always better to explicitly check in and make sure your partner is comfortable, especially if anythi... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-14 | Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last response was truthful. Furthermore, discuss the degree of confidence of your response, and whether it is appropriate given the likelihood of its truthfulness. ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-15 | law, and the Chern-Simons theorem is probably just wrong. Critique Needed.', 'revision_request': 'Please rewrite the model response. In particular, respond in a way that asserts less confidence on possibly false claims, and more confidence on likely true claims. Remember that your knowledge comes solely from your train... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-16 | and decays more quickly than Newton’s law. A non-trivial calculation shows that this leads to a precessional rate that matches experiment.'}, {'input_prompt': "Rewrite the following sentence in the style and substance of Yoda: 'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please c... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-17 | to more closely mimic the style of Master Yoda.', 'revision': 'No revisions needed.'}], example_selector=None, example_prompt=PromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\n\nModel: {output_... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-18 | Create a chain from an LLM.
classmethod get_principles(names: Optional[List[str]] = None) → List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple][source]#
property input_keys: List[str]#
Defines the input keys.
property output_keys: List[str]#
Defines the output keys.
pydantic model langchain.chains.C... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-19 | field retriever: BaseRetriever [Required]#
Index to connect to.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, retriever: langchain.schema.BaseRetriever, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-20 | property input_keys: List[str]#
Input keys this chain expects.
property output_keys: List[str]#
Output keys this chain expects.
pydantic model langchain.chains.GraphCypherQAChain[source]#
Chain for question-answering against a graph by generating Cypher statements.
Validators
raise_deprecation » all fields
set_verbose ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-21 | field qa_chain: LLMChain [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, *, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context', 'question'], output_parser=None, partial_variables={}, template="You are an assistant that helps to form nice and... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-22 | set_verbose » verbose
field entity_extraction_chain: LLMChain [Required]#
field graph: NetworkxEntityGraph [Required]#
field qa_chain: LLMChain [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-23 | pydantic model langchain.chains.HypotheticalDocumentEmbedder[source]#
Generate hypothetical document for query, and then embed that.
Based on https://arxiv.org/abs/2212.10496
Validators
raise_deprecation » all fields
set_verbose » verbose
field base_embeddings: Embeddings [Required]#
field llm_chain: LLMChain [Required... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-24 | field llm_chain: LLMChain [Required]#
field prompt: BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=BashOutputParser(), partial_variables={}, template='If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no nee... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-25 | [Deprecated]
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=BashOutputParser(), partial_variables={}, template='If someone asks you to perform a task, your job is to come up with a series... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-26 | field prompt: BasePromptTemplate [Required]#
Prompt object to use.
async aapply(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None) → List[Dict[str, str]][source]#
Utilize the LLM generate method for speed... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-27 | Parameters
callbacks – Callbacks to pass to LLMChain
**kwargs – Keys to pass to prompt template.
Returns
Completion from LLM.
Example
completion = llm.predict(adjective="funny")
async apredict_and_parse(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackMa... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-28 | Completion from LLM.
Example
completion = llm.predict(adjective="funny")
predict_and_parse(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[str, List[str], Dict[str, Any]][source]#
Call predict and then parse the ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-29 | [Deprecated]
field list_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['statement'], output_parser=None, partial_variables={}, template='Here is a statement:\n{statement}\nMake a bullet point list of the assumptions you made when producing the above statement.\n\n', template_format='f-string', vali... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-30 | [Deprecated] Prompt to use when questioning the documents.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, create_draft_answer_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='{question}\n\n', template... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-31 | Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use.
field llm_chain: LLMChain [Required]#
field prompt: BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-32 | [Deprecated] Prompt to use to translate to python if necessary.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='Translate a math problem into a expres... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-33 | field requests_wrapper: TextRequestsWrapper [Optional]#
field text_length: int = 8000#
pydantic model langchain.chains.LLMSummarizationCheckerChain[source]#
Chain for question-answering with self-verification.
Example
from langchain import OpenAI, LLMSummarizationCheckerChain
llm = OpenAI(temperature=0.0)
checker_chain... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-34 | [Deprecated]
field check_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.\n\nHere is a bullet point list of facts:\... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-35 | Maximum number of times to check the assertions. Default to double-checking.
field revised_summary_prompt: PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'summary'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true ... | https://python.langchain.com/en/latest/reference/modules/chains.html |
5ff2273f5859-36 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, create_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['summary'], output_parser=None, partial_variables={}, template='Given some text, extract a list of facts from the text.\n\nFormat your output as a bull... | https://python.langchain.com/en/latest/reference/modules/chains.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.