remove CVEs (#8092)

This PR aims to move all code with CVEs into `langchain.experimental`.
Note that we are NOT yet removing from the core `langchain` package - we
will give people a week to migrate here.

See MIGRATE.md for how to migrate

Zero changes to functionality

Vulnerabilities this addresses:

PALChain:
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5752409
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759265

SQLDatabaseChain
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759268

`load_prompt` (Python files only)
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5725807

libs/experimental/langchain_experimental/plan_and_execute/executors/agent_executor.py

@@ -1,54 +0,0 @@
-from typing import List
-
-from langchain.agents.agent import AgentExecutor
-from langchain.agents.structured_chat.base import StructuredChatAgent
-from langchain.experimental.plan_and_execute.executors.base import ChainExecutor
-from langchain.schema.language_model import BaseLanguageModel
-from langchain.tools import BaseTool
-
-HUMAN_MESSAGE_TEMPLATE = """Previous steps: {previous_steps}
-
-Current objective: {current_step}
-
-{agent_scratchpad}"""
-
-TASK_PREFIX = """{objective}
-
-"""
-
-
-def load_agent_executor(
-    llm: BaseLanguageModel,
-    tools: List[BaseTool],
-    verbose: bool = False,
-    include_task_in_prompt: bool = False,
-) -> ChainExecutor:
-    """
-    Load an agent executor.
-
-    Args:
-        llm: BaseLanguageModel
-        tools: List[BaseTool]
-        verbose: bool. Defaults to False.
-        include_task_in_prompt: bool. Defaults to False.
-
-    Returns:
-        ChainExecutor
-    """
-    input_variables = ["previous_steps", "current_step", "agent_scratchpad"]
-    template = HUMAN_MESSAGE_TEMPLATE
-
-    if include_task_in_prompt:
-        input_variables.append("objective")
-        template = TASK_PREFIX + template
-
-    agent = StructuredChatAgent.from_llm_and_tools(
-        llm,
-        tools,
-        human_message_template=template,
-        input_variables=input_variables,
-    )
-    agent_executor = AgentExecutor.from_agent_and_tools(
-        agent=agent, tools=tools, verbose=verbose
-    )
-    return ChainExecutor(chain=agent_executor)

libs/experimental/langchain_experimental/plan_and_execute/executors/base.py

@@ -1,39 +0,0 @@
-from abc import abstractmethod
-from typing import Any
-
-from langchain.callbacks.manager import Callbacks
-from langchain.chains.base import Chain
-from langchain.experimental.plan_and_execute.schema import StepResponse
-from pydantic import BaseModel
-
-
-class BaseExecutor(BaseModel):
-    @abstractmethod
-    def step(
-        self, inputs: dict, callbacks: Callbacks = None, **kwargs: Any
-    ) -> StepResponse:
-        """Take step."""
-
-    @abstractmethod
-    async def astep(
-        self, inputs: dict, callbacks: Callbacks = None, **kwargs: Any
-    ) -> StepResponse:
-        """Take step."""
-
-
-class ChainExecutor(BaseExecutor):
-    chain: Chain
-
-    def step(
-        self, inputs: dict, callbacks: Callbacks = None, **kwargs: Any
-    ) -> StepResponse:
-        """Take step."""
-        response = self.chain.run(**inputs, callbacks=callbacks)
-        return StepResponse(response=response)
-
-    async def astep(
-        self, inputs: dict, callbacks: Callbacks = None, **kwargs: Any
-    ) -> StepResponse:
-        """Take step."""
-        response = await self.chain.arun(**inputs, callbacks=callbacks)
-        return StepResponse(response=response)