Home / File/ toolkit.py — langchain Source File

toolkit.py — langchain Source File

Architecture documentation for toolkit.py, a python file in the langchain codebase. 6 imports, 0 dependents.

Entity Profile

Dependency Diagram

graph LR
  5267c032_dda3_79c4_9c44_828c1765ed44["toolkit.py"]
  e929cf21_6ab8_6ff3_3765_0d35a099a053["langchain_core.language_models"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> e929cf21_6ab8_6ff3_3765_0d35a099a053
  121262a1_0bd6_d637_bce3_307ab6b3ecd4["langchain_core.tools"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> 121262a1_0bd6_d637_bce3_307ab6b3ecd4
  95e05501_5650_2f3c_99db_c054e96d4e43["langchain_core.tools.base"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> 95e05501_5650_2f3c_99db_c054e96d4e43
  f75e66a0_314a_f961_16d7_464ee959064b["langchain_core.vectorstores"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> f75e66a0_314a_f961_16d7_464ee959064b
  dd5e7909_a646_84f1_497b_cae69735550e["pydantic"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> dd5e7909_a646_84f1_497b_cae69735550e
  a4aca3cb_d354_1b6d_bde6_2a56d12c755c["langchain_community.tools.vectorstore.tool"]
  5267c032_dda3_79c4_9c44_828c1765ed44 --> a4aca3cb_d354_1b6d_bde6_2a56d12c755c
  style 5267c032_dda3_79c4_9c44_828c1765ed44 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

"""Toolkit for interacting with a vector store."""

from langchain_core.language_models import BaseLanguageModel
from langchain_core.tools import BaseTool
from langchain_core.tools.base import BaseToolkit
from langchain_core.vectorstores import VectorStore
from pydantic import BaseModel, ConfigDict, Field


class VectorStoreInfo(BaseModel):
    """Information about a `VectorStore`."""

    vectorstore: VectorStore = Field(exclude=True)
    name: str
    description: str

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
    )


class VectorStoreToolkit(BaseToolkit):
    """Toolkit for interacting with a `VectorStore`."""

    vectorstore_info: VectorStoreInfo = Field(exclude=True)
    llm: BaseLanguageModel

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
    )

    def get_tools(self) -> list[BaseTool]:
        """Get the tools in the toolkit."""
        try:
            from langchain_community.tools.vectorstore.tool import (
                VectorStoreQATool,
                VectorStoreQAWithSourcesTool,
            )
        except ImportError as e:
            msg = "You need to install langchain-community to use this toolkit."
            raise ImportError(msg) from e
        description = VectorStoreQATool.get_description(
            self.vectorstore_info.name,
            self.vectorstore_info.description,
        )
        qa_tool = VectorStoreQATool(
            name=self.vectorstore_info.name,
            description=description,
            vectorstore=self.vectorstore_info.vectorstore,
            llm=self.llm,
        )
        description = VectorStoreQAWithSourcesTool.get_description(
            self.vectorstore_info.name,
            self.vectorstore_info.description,
        )
        qa_with_sources_tool = VectorStoreQAWithSourcesTool(
            name=f"{self.vectorstore_info.name}_with_sources",
            description=description,
            vectorstore=self.vectorstore_info.vectorstore,
            llm=self.llm,
        )
        return [qa_tool, qa_with_sources_tool]


class VectorStoreRouterToolkit(BaseToolkit):
    """Toolkit for routing between Vector Stores."""

    vectorstores: list[VectorStoreInfo] = Field(exclude=True)
    llm: BaseLanguageModel

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
    )

    def get_tools(self) -> list[BaseTool]:
        """Get the tools in the toolkit."""
        tools: list[BaseTool] = []
        try:
            from langchain_community.tools.vectorstore.tool import (
                VectorStoreQATool,
            )
        except ImportError as e:
            msg = "You need to install langchain-community to use this toolkit."
            raise ImportError(msg) from e
        for vectorstore_info in self.vectorstores:
            description = VectorStoreQATool.get_description(
                vectorstore_info.name,
                vectorstore_info.description,
            )
            qa_tool = VectorStoreQATool(
                name=vectorstore_info.name,
                description=description,
                vectorstore=vectorstore_info.vectorstore,
                llm=self.llm,
            )
            tools.append(qa_tool)
        return tools

Subdomains

Dependencies

  • langchain_community.tools.vectorstore.tool
  • langchain_core.language_models
  • langchain_core.tools
  • langchain_core.tools.base
  • langchain_core.vectorstores
  • pydantic

Frequently Asked Questions

What does toolkit.py do?
toolkit.py is a source file in the langchain codebase, written in python. It belongs to the AgentOrchestration domain, AgentExcecutor subdomain.
What does toolkit.py depend on?
toolkit.py imports 6 module(s): langchain_community.tools.vectorstore.tool, langchain_core.language_models, langchain_core.tools, langchain_core.tools.base, langchain_core.vectorstores, pydantic.
Where is toolkit.py in the architecture?
toolkit.py is located at libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/toolkit.py (domain: AgentOrchestration, subdomain: AgentExcecutor, directory: libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore).

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free