docstrings cleanup (#8311)

- added missed docstrings
 - changed docstrings into consistent format
  
@baskaryan

libs/experimental/langchain_experimental/autonomous_agents/autogpt/prompt.py

@@ -13,6 +13,8 @@ from langchain_experimental.autonomous_agents.autogpt.prompt_generator import ge
 
 
 class AutoGPTPrompt(BaseChatPromptTemplate, BaseModel):
+    """Prompt for AutoGPT."""
+
     ai_name: str
     ai_role: str
     tools: List[BaseTool]

libs/langchain/langchain/agents/agent_iterator.py

@@ -38,6 +38,8 @@ logger = logging.getLogger(__name__)
 
 
 class BaseAgentExecutorIterator(ABC):
+    """Base class for AgentExecutorIterator."""
+
     @abstractmethod
     def build_callback_manager(self) -> None:
         pass
@@ -57,6 +59,8 @@ def rebuild_callback_manager_on_set(
 
 
 class AgentExecutorIterator(BaseAgentExecutorIterator):
+    """Iterator for AgentExecutor."""
+
     def __init__(
         self,
         agent_executor: AgentExecutor,

libs/langchain/langchain/callbacks/base.py

@@ -468,7 +468,7 @@ class AsyncCallbackHandler(BaseCallbackHandler):
 
 
 class BaseCallbackManager(CallbackManagerMixin):
-    """Base callback manager that can be used to handle callbacks from LangChain."""
+    """Base callback manager that handles callbacks from LangChain."""
 
     def __init__(
         self,

libs/langchain/langchain/callbacks/flyte_callback.py

@@ -93,7 +93,7 @@ def analyze_text(
 
 
 class FlyteCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
-    """This callback handler is designed specifically for usage within a Flyte task."""
+    """This callback handler that is used within a Flyte task."""
 
     def __init__(self) -> None:
         """Initialize callback handler."""

libs/langchain/langchain/callbacks/manager.py

@@ -1004,7 +1004,7 @@ class AsyncCallbackManagerForRetrieverRun(
 
 
 class CallbackManager(BaseCallbackManager):
-    """Callback manager that can be used to handle callbacks from langchain."""
+    """Callback manager that handles callbacks from langchain."""
 
     def on_llm_start(
         self,
@@ -1273,7 +1273,7 @@ class CallbackManager(BaseCallbackManager):
 
 
 class AsyncCallbackManager(BaseCallbackManager):
-    """Async callback manager that can be used to handle callbacks from LangChain."""
+    """Async callback manager that handles callbacks from LangChain."""
 
     @property
     def is_async(self) -> bool:

libs/langchain/langchain/callbacks/streamlit/__init__.py

@@ -22,7 +22,9 @@ def StreamlitCallbackHandler(
     collapse_completed_thoughts: bool = True,
     thought_labeler: Optional[LLMThoughtLabeler] = None,
 ) -> BaseCallbackHandler:
-    """Construct a new StreamlitCallbackHandler. This CallbackHandler is geared towards
+    """Callback Handler that writes to a Streamlit app.
+
+    This CallbackHandler is geared towards
     use with a LangChain Agent; it displays the Agent's LLM and tool-usage "thoughts"
     inside a series of Streamlit expanders.
 

libs/langchain/langchain/callbacks/tracers/schemas.py

@@ -31,7 +31,7 @@ class TracerSessionV1(TracerSessionV1Base):
 
 
 class TracerSessionBase(TracerSessionV1Base):
-    """A creation class for TracerSession."""
+    """Base class for TracerSession."""
 
     tenant_id: UUID
 

libs/langchain/langchain/chains/graph_qa/neptune_cypher.py

@@ -20,6 +20,7 @@ INTERMEDIATE_STEPS_KEY = "intermediate_steps"
 
 
 def extract_cypher(text: str) -> str:
+    """Extract Cypher code from text using Regex."""
     # The pattern to find Cypher code enclosed in triple backticks
     pattern = r"```(.*?)```"
 

libs/langchain/langchain/chains/transform.py

@@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
 
 
 class TransformChain(Chain):
-    """Chain transform chain output.
+    """Chain that transforms the chain output.
 
     Example:
         .. code-block:: python

libs/langchain/langchain/chat_models/anthropic.py

@@ -22,7 +22,7 @@ from langchain.schema.output import ChatGenerationChunk
 
 
 class ChatAnthropic(BaseChatModel, _AnthropicCommon):
-    r"""Wrapper around Anthropic's large language model.
+    """Anthropic's large language chat model.
 
     To use, you should have the ``anthropic`` python package installed, and the
     environment variable ``ANTHROPIC_API_KEY`` set with your API key, or pass

libs/langchain/langchain/chat_models/azure_openai.py

@@ -14,7 +14,9 @@ logger = logging.getLogger(__name__)
 
 
 class AzureChatOpenAI(ChatOpenAI):
-    """Wrapper around Azure OpenAI Chat Completion API. To use this class you
+    """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.
 

libs/langchain/langchain/chat_models/human.py

@@ -67,7 +67,7 @@ def _collect_yaml_input(
 
 
 class HumanInputChatModel(BaseChatModel):
-    """ChatModel wrapper which returns user input as the response.."""
+    """ChatModel which returns user input as the response."""
 
     input_func: Callable = Field(default_factory=lambda: _collect_yaml_input)
     message_func: Callable = Field(default_factory=lambda: _display_messages)

libs/langchain/langchain/chat_models/jinachat.py

@@ -133,8 +133,8 @@ def _convert_message_to_dict(message: BaseMessage) -> dict:
 
 
 class JinaChat(BaseChatModel):
-    """JinaChat is a wrapper for Jina AI's LLM service, providing cost-effective
+    """Wrapper for Jina AI's LLM service, providing cost-effective
-    image chat capabilities in comparison to other LLM APIs.
+    image chat capabilities.
 
     To use, you should have the ``openai`` python package installed, and the
     environment variable ``JINACHAT_API_KEY`` set to your API key, which you

libs/langchain/langchain/document_loaders/epub.py

@@ -8,7 +8,8 @@ from langchain.document_loaders.unstructured import (
 
 
 class UnstructuredEPubLoader(UnstructuredFileLoader):
-    """UnstructuredEPubLoader uses unstructured to load EPUB files.
+    """Loader that uses Unstructured to load EPUB files.
+
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
     langchain Document object. If you use "elements" mode, the unstructured

libs/langchain/langchain/document_loaders/html.py

@@ -5,7 +5,8 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredHTMLLoader(UnstructuredFileLoader):
-    """UnstructuredHTMLLoader uses unstructured to load HTML files.
+    """Loader that uses Unstructured to load HTML files.
+
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
     langchain Document object. If you use "elements" mode, the unstructured

libs/langchain/langchain/document_loaders/image.py

@@ -5,7 +5,8 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredImageLoader(UnstructuredFileLoader):
-    """UnstructuredImageLoader uses unstructured to load PNG and JPG files.
+    """Loader that uses Unstructured to load PNG and JPG files.
+
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
     langchain Document object. If you use "elements" mode, the unstructured

libs/langchain/langchain/document_loaders/markdown.py

@@ -5,7 +5,8 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredMarkdownLoader(UnstructuredFileLoader):
-    """UnstructuredMarkdownLoader uses unstructured to load markdown files.
+    """Loader that uses Unstructured to load markdown files.
+
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
     langchain Document object. If you use "elements" mode, the unstructured

libs/langchain/langchain/document_loaders/tencent_cos_directory.py

@@ -7,7 +7,7 @@ from langchain.document_loaders.tencent_cos_file import TencentCOSFileLoader
 
 
 class TencentCOSDirectoryLoader(BaseLoader):
-    """Loading logic for loading documents from Tencent Cloud COS."""
+    """Loader for Tencent Cloud COS directory."""
 
     def __init__(self, conf: Any, bucket: str, prefix: str = ""):
         """Initialize with COS config, bucket and prefix.

libs/langchain/langchain/document_loaders/tencent_cos_file.py

@@ -9,7 +9,7 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class TencentCOSFileLoader(BaseLoader):
-    """Loading logic for loading documents from Tencent Cloud COS."""
+    """Loader for Tencent Cloud COS file."""
 
     def __init__(self, conf: Any, bucket: str, key: str):
         """Initialize with COS config, bucket and key name.

libs/langchain/langchain/document_loaders/unstructured.py

@@ -34,7 +34,7 @@ def validate_unstructured_version(min_unstructured_version: str) -> None:
 
 
 class UnstructuredBaseLoader(BaseLoader, ABC):
-    """Loader that uses unstructured to load files."""
+    """Loader that uses Unstructured to load files."""
 
     def __init__(
         self,
@@ -130,7 +130,9 @@ class UnstructuredBaseLoader(BaseLoader, ABC):
 
 
 class UnstructuredFileLoader(UnstructuredBaseLoader):
-    """UnstructuredFileLoader uses unstructured to load files. The file loader uses the
+    """Loader that uses Unstructured to load files.
+
+    The file loader uses the
     unstructured partition function and will automatically detect the file
     type. You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
@@ -209,7 +211,8 @@ def get_elements_from_api(
 
 
 class UnstructuredAPIFileLoader(UnstructuredFileLoader):
-    """UnstructuredAPIFileLoader uses the Unstructured API to load files.
+    """Loader that uses the Unstructured API to load files.
+
     By default, the loader makes a call to the hosted Unstructured API.
     If you are running the unstructured API locally, you can change the
     API rule by passing in the url parameter when you initialize the loader.
@@ -272,7 +275,9 @@ class UnstructuredAPIFileLoader(UnstructuredFileLoader):
 
 
 class UnstructuredFileIOLoader(UnstructuredBaseLoader):
-    """UnstructuredFileIOLoader uses unstructured to load files. The file loader
+    """Loader that uses Unstructured to load files.
+
+    The file loader
     uses the unstructured partition function and will automatically detect the file
     type. You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single
@@ -317,7 +322,8 @@ class UnstructuredFileIOLoader(UnstructuredBaseLoader):
 
 
 class UnstructuredAPIFileIOLoader(UnstructuredFileIOLoader):
-    """UnstructuredAPIFileIOLoader uses the Unstructured API to load files.
+    """Loader that uses the Unstructured API to load files.
+
     By default, the loader makes a call to the hosted Unstructured API.
     If you are running the unstructured API locally, you can change the
     API rule by passing in the url parameter when you initialize the loader.

libs/langchain/langchain/document_transformers/doctran_text_extract.py

@@ -5,7 +5,7 @@ from langchain.utils import get_from_env
 
 
 class DoctranPropertyExtractor(BaseDocumentTransformer):
-    """Extracts properties from text documents using doctran.
+    """Extract properties from text documents using doctran.
 
     Arguments:
         properties: A list of the properties to extract.

libs/langchain/langchain/document_transformers/doctran_text_qa.py

@@ -5,7 +5,7 @@ from langchain.utils import get_from_env
 
 
 class DoctranQATransformer(BaseDocumentTransformer):
-    """Extracts QA from text documents using doctran.
+    """Extract QA from text documents using doctran.
 
     Arguments:
         openai_api_key: OpenAI API key. Can also be specified via environment variable

libs/langchain/langchain/document_transformers/doctran_text_translate.py

@@ -5,7 +5,7 @@ from langchain.utils import get_from_env
 
 
 class DoctranTextTranslator(BaseDocumentTransformer):
-    """Translates text documents using doctran.
+    """Translate text documents using doctran.
 
     Arguments:
         openai_api_key: OpenAI API key. Can also be specified via environment variable

libs/langchain/langchain/evaluation/qa/eval_chain.py

@@ -1,4 +1,4 @@
-"""LLM Chain specifically for evaluating question answering."""
+"""LLM Chains for evaluating question answering."""
 from __future__ import annotations
 
 import re
@@ -50,7 +50,7 @@ def _parse_string_eval_output(text: str) -> dict:
 
 
 class QAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
-    """LLM Chain specifically for evaluating question answering."""
+    """LLM Chain for evaluating question answering."""
 
     output_key: str = "results"  #: :meta private:
 
@@ -184,7 +184,7 @@ class QAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
 
 
 class ContextQAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
-    """LLM Chain specifically for evaluating QA w/o GT based on context"""
+    """LLM Chain for evaluating QA w/o GT based on context"""
 
     @property
     def requires_reference(self) -> bool:
@@ -308,7 +308,7 @@ class ContextQAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
 
 
 class CotQAEvalChain(ContextQAEvalChain):
-    """LLM Chain specifically for evaluating QA using chain of thought reasoning."""
+    """LLM Chain for evaluating QA using chain of thought reasoning."""
 
     @property
     def evaluation_name(self) -> str:

libs/langchain/langchain/evaluation/qa/generate_chain.py

@@ -1,4 +1,4 @@
-"""LLM Chain specifically for generating examples for question answering."""
+"""LLM Chain for generating examples for question answering."""
 from __future__ import annotations
 
 from typing import Any
@@ -9,7 +9,7 @@ from langchain.schema.language_model import BaseLanguageModel
 
 
 class QAGenerateChain(LLMChain):
-    """LLM Chain specifically for generating examples for question answering."""
+    """LLM Chain for generating examples for question answering."""
 
     @classmethod
     def from_llm(cls, llm: BaseLanguageModel, **kwargs: Any) -> QAGenerateChain:

libs/langchain/langchain/experimental/autonomous_agents/autogpt/output_parser.py

@@ -7,11 +7,15 @@ from langchain.schema import BaseOutputParser
 
 
 class AutoGPTAction(NamedTuple):
+    """Action returned by AutoGPTOutputParser."""
+
     name: str
     args: Dict
 
 
 class BaseAutoGPTOutputParser(BaseOutputParser):
+    """Base Output parser for AutoGPT."""
+
     @abstractmethod
     def parse(self, text: str) -> AutoGPTAction:
         """Return AutoGPTAction"""
@@ -36,6 +40,8 @@ def preprocess_json_input(input_str: str) -> str:
 
 
 class AutoGPTOutputParser(BaseAutoGPTOutputParser):
+    """Output parser for AutoGPT."""
+
     def parse(self, text: str) -> AutoGPTAction:
         try:
             parsed = json.loads(text, strict=False)

libs/langchain/langchain/experimental/autonomous_agents/autogpt/prompt.py

@@ -13,6 +13,8 @@ from langchain.vectorstores.base import VectorStoreRetriever
 
 
 class AutoGPTPrompt(BaseChatPromptTemplate, BaseModel):
+    """Prompt for AutoGPT."""
+
     ai_name: str
     ai_role: str
     tools: List[BaseTool]

libs/langchain/langchain/experimental/autonomous_agents/autogpt/prompt_generator.py

@@ -123,7 +123,7 @@ class PromptGenerator:
 
 
 def get_prompt(tools: List[BaseTool]) -> str:
-    """This function generates a prompt string.
+    """Generates a prompt string.
 
     It includes various constraints, commands, resources, and performance evaluations.
 

libs/langchain/langchain/experimental/cpal/constants.py

@@ -2,6 +2,8 @@ from enum import Enum
 
 
 class Constant(Enum):
+    """Enum for constants used in the CPAL."""
+
     narrative_input = "narrative_input"
     chain_answer = "chain_answer"  # natural language answer
     chain_data = "chain_data"  # pydantic instance

libs/langchain/langchain/graphs/arangodb_graph.py

@@ -136,7 +136,7 @@ def get_arangodb_client(
     username: Optional[str] = None,
     password: Optional[str] = None,
 ) -> Any:
-    """Convenience method that gets Arango DB from credentials.
+    """Get the Arango DB client from credentials.
 
     Args:
         url: Arango DB url. Can be passed in as named arg or set as environment

libs/langchain/langchain/prompts/base.py

@@ -110,7 +110,7 @@ class StringPromptValue(PromptValue):
 
 
 class StringPromptTemplate(BasePromptTemplate, ABC):
-    """String prompt should expose the format method, returning a prompt."""
+    """String prompt that exposes the format method, returning a prompt."""
 
     def format_prompt(self, **kwargs: Any) -> PromptValue:
         """Create Chat Messages."""

libs/langchain/langchain/retrievers/google_cloud_enterprise_search.py

@@ -18,7 +18,8 @@ if TYPE_CHECKING:
 
 
 class GoogleCloudEnterpriseSearchRetriever(BaseRetriever):
-    """Wrapper around Google Cloud Enterprise Search Service API.
+    """Retriever for the Google Cloud Enterprise Search Service API.
+
     For the detailed explanation of the Enterprise Search concepts
     and configuration parameters refer to the product documentation.
 

libs/langchain/langchain/retrievers/self_query/deeplake.py

@@ -26,6 +26,7 @@ OPERATOR_TO_TQL = {
 
 
 def can_cast_to_float(string: str) -> bool:
+    """Check if a string can be cast to a float."""
     try:
         float(string)
         return True

libs/langchain/langchain/retrievers/web_research.py

@@ -67,6 +67,8 @@ class QuestionListOutputParser(PydanticOutputParser):
 
 
 class WebResearchRetriever(BaseRetriever):
+    """Retriever for web research based on the Google Search API."""
+
     # Inputs
     vectorstore: VectorStore = Field(
         ..., description="Vector store for storing web pages"

libs/langchain/langchain/tools/amadeus/base.py

@@ -13,4 +13,6 @@ if TYPE_CHECKING:
 
 
 class AmadeusBaseTool(BaseTool):
+    """Base Tool for Amadeus."""
+
     client: Client = Field(default_factory=authenticate)

libs/langchain/langchain/tools/amadeus/closest_airport.py

@@ -12,6 +12,8 @@ from langchain.tools.amadeus.base import AmadeusBaseTool
 
 
 class ClosestAirportSchema(BaseModel):
+    """Schema for the AmadeusClosestAirport tool."""
+
     location: str = Field(
         description=(
             " The location for which you would like to find the nearest airport "
@@ -29,6 +31,8 @@ class ClosestAirportSchema(BaseModel):
 
 
 class AmadeusClosestAirport(AmadeusBaseTool):
+    """Tool for finding the closest airport to a particular location."""
+
     name: str = "closest_airport"
     description: str = (
         "Use this tool to find the closest airport to a particular location."

libs/langchain/langchain/tools/amadeus/flight_search.py

@@ -14,6 +14,8 @@ logger = logging.getLogger(__name__)
 
 
 class FlightSearchSchema(BaseModel):
+    """Schema for the AmadeusFlightSearch tool."""
+
     originLocationCode: str = Field(
         description=(
             " The three letter International Air Transport "
@@ -53,6 +55,8 @@ class FlightSearchSchema(BaseModel):
 
 
 class AmadeusFlightSearch(AmadeusBaseTool):
+    """Tool for searching for a single flight between two airports."""
+
     name: str = "single_flight_search"
     description: str = (
         " Use this tool to search for a single flight between the origin and "

libs/langchain/langchain/tools/github/tool.py

@@ -20,6 +20,8 @@ from langchain.utilities.github import GitHubAPIWrapper
 
 
 class GitHubAction(BaseTool):
+    """Tool for interacting with the GitHub API."""
+
     api_wrapper: GitHubAPIWrapper = Field(default_factory=GitHubAPIWrapper)
     mode: str
     name = ""

libs/langchain/langchain/utils/strings.py

@@ -36,4 +36,5 @@ def stringify_dict(data: dict) -> str:
 
 
 def comma_list(items: List[Any]) -> str:
+    """Convert a list to a comma-separated string."""
     return ", ".join(str(item) for item in items)