langchain 0.4.0.dev0__py3-none-any.whl → 1.0.0__py3-none-any.whl

langchain/agents/react/agent.py

@@ -1,145 +0,0 @@
-from __future__ import annotations
-
-from collections.abc import Sequence
-from typing import Optional, Union
-
-from langchain_core.language_models import BaseLanguageModel
-from langchain_core.prompts import BasePromptTemplate
-from langchain_core.runnables import Runnable, RunnablePassthrough
-from langchain_core.tools import BaseTool
-from langchain_core.tools.render import ToolsRenderer, render_text_description
-
-from langchain.agents import AgentOutputParser
-from langchain.agents.format_scratchpad import format_log_to_str
-from langchain.agents.output_parsers import ReActSingleInputOutputParser
-
-
-def create_react_agent(
-    llm: BaseLanguageModel,
-    tools: Sequence[BaseTool],
-    prompt: BasePromptTemplate,
-    output_parser: Optional[AgentOutputParser] = None,
-    tools_renderer: ToolsRenderer = render_text_description,
-    *,
-    stop_sequence: Union[bool, list[str]] = True,
-) -> Runnable:
-    """Create an agent that uses ReAct prompting.
-
-    Based on paper "ReAct: Synergizing Reasoning and Acting in Language Models"
-    (https://arxiv.org/abs/2210.03629)
-
-    .. warning::
-       This implementation is based on the foundational ReAct paper but is older and not well-suited for production applications.
-       For a more robust and feature-rich implementation, we recommend using the `create_react_agent` function from the LangGraph library.
-       See the [reference doc](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent)
-       for more information.
-
-    Args:
-        llm: LLM to use as the agent.
-        tools: Tools this agent has access to.
-        prompt: The prompt to use. See Prompt section below for more.
-        output_parser: AgentOutputParser for parse the LLM output.
-        tools_renderer: This controls how the tools are converted into a string and
-            then passed into the LLM. Default is `render_text_description`.
-        stop_sequence: bool or list of str.
-            If True, adds a stop token of "Observation:" to avoid hallucinates.
-            If False, does not add a stop token.
-            If a list of str, uses the provided list as the stop tokens.
-
-            Default is True. You may to set this to False if the LLM you are using
-            does not support stop sequences.
-
-    Returns:
-        A Runnable sequence representing an agent. It takes as input all the same input
-        variables as the prompt passed in does. It returns as output either an
-        AgentAction or AgentFinish.
-
-    Examples:
-
-        .. code-block:: python
-
-            from langchain import hub
-            from langchain_community.llms import OpenAI
-            from langchain.agents import AgentExecutor, create_react_agent
-
-            prompt = hub.pull("hwchase17/react")
-            model = OpenAI()
-            tools = ...
-
-            agent = create_react_agent(model, tools, prompt)
-            agent_executor = AgentExecutor(agent=agent, tools=tools)
-
-            agent_executor.invoke({"input": "hi"})
-
-            # Use with chat history
-            from langchain_core.messages import AIMessage, HumanMessage
-            agent_executor.invoke(
-                {
-                    "input": "what's my name?",
-                    # Notice that chat_history is a string
-                    # since this prompt is aimed at LLMs, not chat models
-                    "chat_history": "Human: My name is Bob\\nAI: Hello Bob!",
-                }
-            )
-
-    Prompt:
-
-        The prompt must have input keys:
-            * `tools`: contains descriptions and arguments for each tool.
-            * `tool_names`: contains all tool names.
-            * `agent_scratchpad`: contains previous agent actions and tool outputs as a string.
-
-        Here's an example:
-
-        .. code-block:: python
-
-            from langchain_core.prompts import PromptTemplate
-
-            template = '''Answer the following questions as best you can. You have access to the following tools:
-
-            {tools}
-
-            Use the following format:
-
-            Question: the input question you must answer
-            Thought: you should always think about what to do
-            Action: the action to take, should be one of [{tool_names}]
-            Action Input: the input to the action
-            Observation: the result of the action
-            ... (this Thought/Action/Action Input/Observation can repeat N times)
-            Thought: I now know the final answer
-            Final Answer: the final answer to the original input question
-
-            Begin!
-
-            Question: {input}
-            Thought:{agent_scratchpad}'''
-
-            prompt = PromptTemplate.from_template(template)
-
-    """  # noqa: E501
-    missing_vars = {"tools", "tool_names", "agent_scratchpad"}.difference(
-        prompt.input_variables + list(prompt.partial_variables),
-    )
-    if missing_vars:
-        msg = f"Prompt missing required variables: {missing_vars}"
-        raise ValueError(msg)
-
-    prompt = prompt.partial(
-        tools=tools_renderer(list(tools)),
-        tool_names=", ".join([t.name for t in tools]),
-    )
-    if stop_sequence:
-        stop = ["\nObservation"] if stop_sequence is True else stop_sequence
-        llm_with_stop = llm.bind(stop=stop)
-    else:
-        llm_with_stop = llm
-    output_parser = output_parser or ReActSingleInputOutputParser()
-    return (
-        RunnablePassthrough.assign(
-            agent_scratchpad=lambda x: format_log_to_str(x["intermediate_steps"]),
-        )
-        | prompt
-        | llm_with_stop
-        | output_parser
-    )

langchain/agents/react/base.py

@@ -1,189 +0,0 @@
-"""Chain that implements the ReAct paper from https://arxiv.org/pdf/2210.03629.pdf."""
-
-from __future__ import annotations
-
-from collections.abc import Sequence
-from typing import TYPE_CHECKING, Any, Optional
-
-from langchain_core._api import deprecated
-from langchain_core.documents import Document
-from langchain_core.language_models import BaseLanguageModel
-from langchain_core.prompts import BasePromptTemplate
-from langchain_core.tools import BaseTool, Tool
-from pydantic import Field
-from typing_extensions import override
-
-from langchain._api.deprecation import AGENT_DEPRECATION_WARNING
-from langchain.agents.agent import Agent, AgentExecutor, AgentOutputParser
-from langchain.agents.agent_types import AgentType
-from langchain.agents.react.output_parser import ReActOutputParser
-from langchain.agents.react.textworld_prompt import TEXTWORLD_PROMPT
-from langchain.agents.react.wiki_prompt import WIKI_PROMPT
-from langchain.agents.utils import validate_tools_single_input
-
-if TYPE_CHECKING:
-    from langchain_community.docstore.base import Docstore
-
-
-_LOOKUP_AND_SEARCH_TOOLS = {"Lookup", "Search"}
-
-
-@deprecated(
-    "0.1.0",
-    message=AGENT_DEPRECATION_WARNING,
-    removal="1.0",
-)
-class ReActDocstoreAgent(Agent):
-    """Agent for the ReAct chain."""
-
-    output_parser: AgentOutputParser = Field(default_factory=ReActOutputParser)
-
-    @classmethod
-    @override
-    def _get_default_output_parser(cls, **kwargs: Any) -> AgentOutputParser:
-        return ReActOutputParser()
-
-    @property
-    def _agent_type(self) -> str:
-        """Return Identifier of an agent type."""
-        return AgentType.REACT_DOCSTORE
-
-    @classmethod
-    @override
-    def create_prompt(cls, tools: Sequence[BaseTool]) -> BasePromptTemplate:
-        """Return default prompt."""
-        return WIKI_PROMPT
-
-    @classmethod
-    def _validate_tools(cls, tools: Sequence[BaseTool]) -> None:
-        validate_tools_single_input(cls.__name__, tools)
-        super()._validate_tools(tools)
-        if len(tools) != len(_LOOKUP_AND_SEARCH_TOOLS):
-            msg = f"Exactly two tools must be specified, but got {tools}"
-            raise ValueError(msg)
-        tool_names = {tool.name for tool in tools}
-        if tool_names != _LOOKUP_AND_SEARCH_TOOLS:
-            msg = f"Tool names should be Lookup and Search, got {tool_names}"
-            raise ValueError(msg)
-
-    @property
-    def observation_prefix(self) -> str:
-        """Prefix to append the observation with."""
-        return "Observation: "
-
-    @property
-    def _stop(self) -> list[str]:
-        return ["\nObservation:"]
-
-    @property
-    def llm_prefix(self) -> str:
-        """Prefix to append the LLM call with."""
-        return "Thought:"
-
-
-@deprecated(
-    "0.1.0",
-    message=AGENT_DEPRECATION_WARNING,
-    removal="1.0",
-)
-class DocstoreExplorer:
-    """Class to assist with exploration of a document store."""
-
-    def __init__(self, docstore: Docstore):
-        """Initialize with a docstore, and set initial document to None."""
-        self.docstore = docstore
-        self.document: Optional[Document] = None
-        self.lookup_str = ""
-        self.lookup_index = 0
-
-    def search(self, term: str) -> str:
-        """Search for a term in the docstore, and if found save."""
-        result = self.docstore.search(term)
-        if isinstance(result, Document):
-            self.document = result
-            return self._summary
-        self.document = None
-        return result
-
-    def lookup(self, term: str) -> str:
-        """Lookup a term in document (if saved)."""
-        if self.document is None:
-            msg = "Cannot lookup without a successful search first"
-            raise ValueError(msg)
-        if term.lower() != self.lookup_str:
-            self.lookup_str = term.lower()
-            self.lookup_index = 0
-        else:
-            self.lookup_index += 1
-        lookups = [p for p in self._paragraphs if self.lookup_str in p.lower()]
-        if len(lookups) == 0:
-            return "No Results"
-        if self.lookup_index >= len(lookups):
-            return "No More Results"
-        result_prefix = f"(Result {self.lookup_index + 1}/{len(lookups)})"
-        return f"{result_prefix} {lookups[self.lookup_index]}"
-
-    @property
-    def _summary(self) -> str:
-        return self._paragraphs[0]
-
-    @property
-    def _paragraphs(self) -> list[str]:
-        if self.document is None:
-            msg = "Cannot get paragraphs without a document"
-            raise ValueError(msg)
-        return self.document.page_content.split("\n\n")
-
-
-@deprecated(
-    "0.1.0",
-    message=AGENT_DEPRECATION_WARNING,
-    removal="1.0",
-)
-class ReActTextWorldAgent(ReActDocstoreAgent):
-    """Agent for the ReAct TextWorld chain."""
-
-    @classmethod
-    @override
-    def create_prompt(cls, tools: Sequence[BaseTool]) -> BasePromptTemplate:
-        """Return default prompt."""
-        return TEXTWORLD_PROMPT
-
-    @classmethod
-    def _validate_tools(cls, tools: Sequence[BaseTool]) -> None:
-        validate_tools_single_input(cls.__name__, tools)
-        super()._validate_tools(tools)
-        if len(tools) != 1:
-            msg = f"Exactly one tool must be specified, but got {tools}"
-            raise ValueError(msg)
-        tool_names = {tool.name for tool in tools}
-        if tool_names != {"Play"}:
-            msg = f"Tool name should be Play, got {tool_names}"
-            raise ValueError(msg)
-
-
-@deprecated(
-    "0.1.0",
-    message=AGENT_DEPRECATION_WARNING,
-    removal="1.0",
-)
-class ReActChain(AgentExecutor):
-    """[Deprecated] Chain that implements the ReAct paper."""
-
-    def __init__(self, llm: BaseLanguageModel, docstore: Docstore, **kwargs: Any):
-        """Initialize with the LLM and a docstore."""
-        docstore_explorer = DocstoreExplorer(docstore)
-        tools = [
-            Tool(
-                name="Search",
-                func=docstore_explorer.search,
-                description="Search for a term in the docstore.",
-            ),
-            Tool(
-                name="Lookup",
-                func=docstore_explorer.lookup,
-                description="Lookup a term in the docstore.",
-            ),
-        ]
-        agent = ReActDocstoreAgent.from_llm_and_tools(llm, tools)
-        super().__init__(agent=agent, tools=tools, **kwargs)

langchain/agents/react/output_parser.py

@@ -1,35 +0,0 @@
-import re
-from typing import Union
-
-from langchain_core.agents import AgentAction, AgentFinish
-from langchain_core.exceptions import OutputParserException
-from typing_extensions import override
-
-from langchain.agents.agent import AgentOutputParser
-
-
-class ReActOutputParser(AgentOutputParser):
-    """Output parser for the ReAct agent."""
-
-    @override
-    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
-        action_prefix = "Action: "
-        if not text.strip().split("\n")[-1].startswith(action_prefix):
-            msg = f"Could not parse LLM Output: {text}"
-            raise OutputParserException(msg)
-        action_block = text.strip().split("\n")[-1]
-
-        action_str = action_block[len(action_prefix) :]
-        # Parse out the action and the directive.
-        re_matches = re.search(r"(.*?)\[(.*?)\]", action_str)
-        if re_matches is None:
-            msg = f"Could not parse action directive: {action_str}"
-            raise OutputParserException(msg)
-        action, action_input = re_matches.group(1), re_matches.group(2)
-        if action == "Finish":
-            return AgentFinish({"output": action_input}, text)
-        return AgentAction(action, action_input, text)
-
-    @property
-    def _type(self) -> str:
-        return "react"

langchain/agents/react/textworld_prompt.py

@@ -1,51 +0,0 @@
-from langchain_core.prompts.prompt import PromptTemplate
-
-EXAMPLES = [
-    """Setup: You are now playing a fast paced round of TextWorld! Here is your task for
-today. First of all, you could, like, try to travel east. After that, take the
-binder from the locker. With the binder, place the binder on the mantelpiece.
-Alright, thanks!
-
--= Vault =-
-You've just walked into a vault. You begin to take stock of what's here.
-
-An open safe is here. What a letdown! The safe is empty! You make out a shelf.
-But the thing hasn't got anything on it. What, you think everything in TextWorld
-should have stuff on it?
-
-You don't like doors? Why not try going east, that entranceway is unguarded.
-
-Thought: I need to travel east
-Action: Play[go east]
-Observation: -= Office =-
-You arrive in an office. An ordinary one.
-
-You can make out a locker. The locker contains a binder. You see a case. The
-case is empty, what a horrible day! You lean against the wall, inadvertently
-pressing a secret button. The wall opens up to reveal a mantelpiece. You wonder
-idly who left that here. The mantelpiece is standard. The mantelpiece appears to
-be empty. If you haven't noticed it already, there seems to be something there
-by the wall, it's a table. Unfortunately, there isn't a thing on it. Hm. Oh well
-There is an exit to the west. Don't worry, it is unguarded.
-
-Thought: I need to take the binder from the locker
-Action: Play[take binder]
-Observation: You take the binder from the locker.
-
-Thought: I need to place the binder on the mantelpiece
-Action: Play[put binder on mantelpiece]
-
-Observation: You put the binder on the mantelpiece.
-Your score has just gone up by one point.
-*** The End ***
-Thought: The End has occurred
-Action: Finish[yes]
-
-"""
-]
-SUFFIX = """\n\nSetup: {input}
-{agent_scratchpad}"""
-
-TEXTWORLD_PROMPT = PromptTemplate.from_examples(
-    EXAMPLES, SUFFIX, ["input", "agent_scratchpad"]
-)

langchain/agents/react/wiki_prompt.py

@@ -1,70 +0,0 @@
-from langchain_core.prompts.prompt import PromptTemplate
-
-EXAMPLES = [
-    """Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
-Thought: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
-Action: Search[Colorado orogeny]
-Observation: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.
-Thought: It does not mention the eastern sector. So I need to look up eastern sector.
-Action: Lookup[eastern sector]
-Observation: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.
-Thought: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.
-Action: Search[High Plains]
-Observation: High Plains refers to one of two distinct land regions
-Thought: I need to instead search High Plains (United States).
-Action: Search[High Plains (United States)]
-Observation: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
-Thought: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
-Action: Finish[1,800 to 7,000 ft]""",  # noqa: E501
-    """Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
-Thought: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
-Action: Search[Milhouse]
-Observation: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
-Thought: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
-Action: Lookup[named after]
-Observation: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
-Thought: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
-Action: Finish[Richard Nixon]""",  # noqa: E501
-    """Question: Which documentary is about Finnish rock groups, Adam Clayton Powell or The Saimaa Gesture?
-Thought: I need to search Adam Clayton Powell and The Saimaa Gesture, and find which documentary is about Finnish rock groups.
-Action: Search[Adam Clayton Powell]
-Observation: Could not find [Adam Clayton Powell]. Similar: ['Adam Clayton Powell III', 'Seventh Avenue (Manhattan)', 'Adam Clayton Powell Jr. State Office Building', 'Isabel Washington Powell', 'Adam Powell', 'Adam Clayton Powell (film)', 'Giancarlo Esposito'].
-Thought: To find the documentary, I can search Adam Clayton Powell (film).
-Action: Search[Adam Clayton Powell (film)]
-Observation: Adam Clayton Powell is a 1989 American documentary film directed by Richard Kilberg. The film is about the rise and fall of influential African-American politician Adam Clayton Powell Jr.[3][4] It was later aired as part of the PBS series The American Experience.
-Thought: Adam Clayton Powell (film) is a documentary about an African-American politician, not Finnish rock groups. So the documentary about Finnish rock groups must instead be The Saimaa Gesture.
-Action: Finish[The Saimaa Gesture]""",  # noqa: E501
-    """Question: What profession does Nicholas Ray and Elia Kazan have in common?
-Thought: I need to search Nicholas Ray and Elia Kazan, find their professions, then find the profession they have in common.
-Action: Search[Nicholas Ray]
-Observation: Nicholas Ray (born Raymond Nicholas Kienzle Jr., August 7, 1911 - June 16, 1979) was an American film director, screenwriter, and actor best known for the 1955 film Rebel Without a Cause.
-Thought: Professions of Nicholas Ray are director, screenwriter, and actor. I need to search Elia Kazan next and find his professions.
-Action: Search[Elia Kazan]
-Observation: Elia Kazan was an American film and theatre director, producer, screenwriter and actor.
-Thought: Professions of Elia Kazan are director, producer, screenwriter, and actor. So profession Nicholas Ray and Elia Kazan have in common is director, screenwriter, and actor.
-Action: Finish[director, screenwriter, actor]""",  # noqa: E501
-    """Question: Which magazine was started first Arthur's Magazine or First for Women?
-Thought: I need to search Arthur's Magazine and First for Women, and find which was started first.
-Action: Search[Arthur's Magazine]
-Observation: Arthur's Magazine (1844-1846) was an American literary periodical published in Philadelphia in the 19th century.
-Thought: Arthur's Magazine was started in 1844. I need to search First for Women next.
-Action: Search[First for Women]
-Observation: First for Women is a woman's magazine published by Bauer Media Group in the USA.[1] The magazine was started in 1989.
-Thought: First for Women was started in 1989. 1844 (Arthur's Magazine) < 1989 (First for Women), so Arthur's Magazine was started first.
-Action: Finish[Arthur's Magazine]""",  # noqa: E501
-    """Question: Were Pavel Urysohn and Leonid Levin known for the same type of work?
-Thought: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same.
-Action: Search[Pavel Urysohn]
-Observation: Pavel Samuilovich Urysohn (February 3, 1898 - August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory.
-Thought: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work.
-Action: Search[Leonid Levin]
-Observation: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist.
-Thought: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work.
-Action: Finish[yes]""",  # noqa: E501
-]
-SUFFIX = """\nQuestion: {input}
-{agent_scratchpad}"""
-
-WIKI_PROMPT = PromptTemplate.from_examples(
-    EXAMPLES, SUFFIX, ["input", "agent_scratchpad"]
-)

langchain/agents/schema.py

@@ -1,37 +0,0 @@
-from typing import Any
-
-from langchain_core.agents import AgentAction
-from langchain_core.prompts.chat import ChatPromptTemplate
-from typing_extensions import override
-
-
-class AgentScratchPadChatPromptTemplate(ChatPromptTemplate):
-    """Chat prompt template for the agent scratchpad."""
-
-    @classmethod
-    @override
-    def is_lc_serializable(cls) -> bool:
-        return False
-
-    def _construct_agent_scratchpad(
-        self,
-        intermediate_steps: list[tuple[AgentAction, str]],
-    ) -> str:
-        if len(intermediate_steps) == 0:
-            return ""
-        thoughts = ""
-        for action, observation in intermediate_steps:
-            thoughts += action.log
-            thoughts += f"\nObservation: {observation}\nThought: "
-        return (
-            f"This was your previous work "
-            f"(but I haven't seen any of it! I only see what "
-            f"you return as final answer):\n{thoughts}"
-        )
-
-    def _merge_partial_and_user_variables(self, **kwargs: Any) -> dict[str, Any]:
-        intermediate_steps = kwargs.pop("intermediate_steps")
-        kwargs["agent_scratchpad"] = self._construct_agent_scratchpad(
-            intermediate_steps,
-        )
-        return kwargs

langchain/agents/self_ask_with_search/__init__.py

@@ -1,4 +0,0 @@
-"""Chain that does self ask with search.
-
-Heavily borrowed from https://github.com/ofirpress/self-ask
-"""