mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
c0d67420e5
<!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. These live is docs/extras directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17, @rlancemartin. -->
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
"""Experimental implementation of RELLM wrapped LLM."""
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING, Any, List, Optional, cast
|
|
|
|
from langchain.callbacks.manager import CallbackManagerForLLMRun
|
|
from langchain.llms.huggingface_pipeline import HuggingFacePipeline
|
|
from langchain.llms.utils import enforce_stop_tokens
|
|
|
|
from langchain_experimental.pydantic_v1 import Field, root_validator
|
|
|
|
if TYPE_CHECKING:
|
|
import rellm
|
|
from regex import Pattern as RegexPattern
|
|
else:
|
|
try:
|
|
from regex import Pattern as RegexPattern
|
|
except ImportError:
|
|
pass
|
|
|
|
|
|
def import_rellm() -> rellm:
|
|
"""Lazily import rellm."""
|
|
try:
|
|
import rellm
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import rellm python package. "
|
|
"Please install it with `pip install rellm`."
|
|
)
|
|
return rellm
|
|
|
|
|
|
class RELLM(HuggingFacePipeline):
|
|
"""RELLM wrapped LLM using HuggingFace Pipeline API."""
|
|
|
|
regex: RegexPattern = Field(..., description="The structured format to complete.")
|
|
max_new_tokens: int = Field(
|
|
default=200, description="Maximum number of new tokens to generate."
|
|
)
|
|
|
|
@root_validator
|
|
def check_rellm_installation(cls, values: dict) -> dict:
|
|
import_rellm()
|
|
return values
|
|
|
|
def _call(
|
|
self,
|
|
prompt: str,
|
|
stop: Optional[List[str]] = None,
|
|
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
|
**kwargs: Any,
|
|
) -> str:
|
|
rellm = import_rellm()
|
|
from transformers import Text2TextGenerationPipeline
|
|
|
|
pipeline = cast(Text2TextGenerationPipeline, self.pipeline)
|
|
|
|
text = rellm.complete_re(
|
|
prompt,
|
|
self.regex,
|
|
tokenizer=pipeline.tokenizer,
|
|
model=pipeline.model,
|
|
max_new_tokens=self.max_new_tokens,
|
|
)
|
|
if stop is not None:
|
|
# This is a bit hacky, but I can't figure out a better way to enforce
|
|
# stop tokens when making calls to huggingface_hub.
|
|
text = enforce_stop_tokens(text, stop)
|
|
return text
|