mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-29 07:19:59 +00:00
8516a03a02
This PR upgrades langchain-community to pydantic 2.
* Most of this PR was auto-generated using code mods with gritql
(https://github.com/eyurtsev/migrate-pydantic/tree/main)
* Subsequently, some code was fixed manually due to accommodate
differences between pydantic 1 and 2
Breaking Changes:
- Use TEXTEMBED_API_KEY and TEXTEMBEB_API_URL for env variables for text
embed integrations:
cbea780492
Other changes:
- Added pydantic_settings as a required dependency for community. This
may be removed if we have enough time to convert the dependency into an
optional one.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
61 lines
1.8 KiB
Python
61 lines
1.8 KiB
Python
from abc import abstractmethod
|
|
from typing import Any, Optional, Protocol, Sequence, runtime_checkable
|
|
|
|
from langchain_core.callbacks import (
|
|
AsyncCallbackManagerForToolRun,
|
|
CallbackManagerForToolRun,
|
|
)
|
|
from langchain_core.tools import BaseTool
|
|
from pydantic import Field
|
|
|
|
from langchain_community.llms.gradient_ai import TrainResult
|
|
|
|
|
|
@runtime_checkable
|
|
class TrainableLLM(Protocol):
|
|
"""Protocol for trainable language models."""
|
|
|
|
@abstractmethod
|
|
def train_unsupervised(
|
|
self,
|
|
inputs: Sequence[str],
|
|
**kwargs: Any,
|
|
) -> TrainResult: ...
|
|
|
|
@abstractmethod
|
|
async def atrain_unsupervised(
|
|
self,
|
|
inputs: Sequence[str],
|
|
**kwargs: Any,
|
|
) -> TrainResult: ...
|
|
|
|
|
|
class Memorize(BaseTool):
|
|
"""Tool that trains a language model."""
|
|
|
|
name: str = "memorize"
|
|
description: str = (
|
|
"Useful whenever you observed novel information "
|
|
"from previous conversation history, "
|
|
"i.e., another tool's action outputs or human comments. "
|
|
"The action input should include observed information in detail, "
|
|
"then the tool will fine-tune yourself to remember it."
|
|
)
|
|
llm: TrainableLLM = Field()
|
|
|
|
def _run(
|
|
self,
|
|
information_to_learn: str,
|
|
run_manager: Optional[CallbackManagerForToolRun] = None,
|
|
) -> str:
|
|
train_result = self.llm.train_unsupervised((information_to_learn,))
|
|
return f"Train complete. Loss: {train_result['loss']}"
|
|
|
|
async def _arun(
|
|
self,
|
|
information_to_learn: str,
|
|
run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
|
|
) -> str:
|
|
train_result = await self.llm.atrain_unsupervised((information_to_learn,))
|
|
return f"Train complete. Loss: {train_result['loss']}"
|