langchain/libs/community/langchain_community/chains/llm_requests.py
Eugene Yurtsev f92006de3c
multiple: langchain 0.2 in master (#21191)
0.2rc 

migrations

- [x] Move memory
- [x] Move remaining retrievers
- [x] graph_qa chains
- [x] some dependency from evaluation code potentially on math utils
- [x] Move openapi chain from `langchain.chains.api.openapi` to
`langchain_community.chains.openapi`
- [x] Migrate `langchain.chains.ernie_functions` to
`langchain_community.chains.ernie_functions`
- [x] migrate `langchain/chains/llm_requests.py` to
`langchain_community.chains.llm_requests`
- [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder`
->
`langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder`
(namespace not ideal, but it needs to be moved to `langchain` to avoid
circular deps)
- [x] unit tests langchain -- add pytest.mark.community to some unit
tests that will stay in langchain
- [x] unit tests community -- move unit tests that depend on community
to community
- [x] mv integration tests that depend on community to community
- [x] mypy checks

Other todo

- [x] Make deprecation warnings not noisy (need to use warn deprecated
and check that things are implemented properly)
- [x] Update deprecation messages with timeline for code removal (likely
we actually won't be removing things until 0.4 release) -- will give
people more time to transition their code.
- [ ] Add information to deprecation warning to show users how to
migrate their code base using langchain-cli
- [ ] Remove any unnecessary requirements in langchain (e.g., is
SQLALchemy required?)

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-05-08 16:46:52 -04:00

98 lines
3.2 KiB
Python

"""Chain that hits a URL and then uses an LLM to parse results."""
from __future__ import annotations
from typing import Any, Dict, List, Optional
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain_core.callbacks import CallbackManagerForChainRun
from langchain_core.pydantic_v1 import Extra, Field, root_validator
from langchain_community.utilities.requests import TextRequestsWrapper
DEFAULT_HEADERS = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36" # noqa: E501
}
class LLMRequestsChain(Chain):
"""Chain that requests a URL and then uses an LLM to parse results.
**Security Note**: This chain can make GET requests to arbitrary URLs,
including internal URLs.
Control access to who can run this chain and what network access
this chain has.
See https://python.langchain.com/docs/security for more information.
"""
llm_chain: LLMChain # type: ignore[valid-type]
requests_wrapper: TextRequestsWrapper = Field(
default_factory=lambda: TextRequestsWrapper(headers=DEFAULT_HEADERS),
exclude=True,
)
text_length: int = 8000
requests_key: str = "requests_result" #: :meta private:
input_key: str = "url" #: :meta private:
output_key: str = "output" #: :meta private:
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Will be whatever keys the prompt expects.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Will always return text key.
:meta private:
"""
return [self.output_key]
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key and python package exists in environment."""
try:
from bs4 import BeautifulSoup # noqa: F401
except ImportError:
raise ImportError(
"Could not import bs4 python package. "
"Please install it with `pip install bs4`."
)
return values
def _call(
self,
inputs: Dict[str, Any],
run_manager: Optional[CallbackManagerForChainRun] = None,
) -> Dict[str, Any]:
from bs4 import BeautifulSoup
_run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
# Other keys are assumed to be needed for LLM prediction
other_keys = {k: v for k, v in inputs.items() if k != self.input_key}
url = inputs[self.input_key]
res = self.requests_wrapper.get(url)
# extract the text from the html
soup = BeautifulSoup(res, "html.parser")
other_keys[self.requests_key] = soup.get_text()[: self.text_length]
result = self.llm_chain.predict( # type: ignore[attr-defined]
callbacks=_run_manager.get_child(), **other_keys
)
return {self.output_key: result}
@property
def _chain_type(self) -> str:
return "llm_requests_chain"