Spaces:
Runtime error
Runtime error
File size: 4,044 Bytes
ed4d993 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import logging
from typing import Any, Dict, List, Mapping, Optional, cast
import requests
from langchain_core.callbacks import CallbackManagerForLLMRun
from langchain_core.language_models.llms import LLM
from langchain_core.pydantic_v1 import Extra, Field, SecretStr, root_validator
from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
from langchain_community.llms.utils import enforce_stop_tokens
logger = logging.getLogger(__name__)
class CerebriumAI(LLM):
"""CerebriumAI large language models.
To use, you should have the ``cerebrium`` python package installed.
You should also have the environment variable ``CEREBRIUMAI_API_KEY``
set with your API key or pass it as a named argument in the constructor.
Any parameters that are valid to be passed to the call can be passed
in, even if not explicitly saved on this class.
Example:
.. code-block:: python
from langchain_community.llms import CerebriumAI
cerebrium = CerebriumAI(endpoint_url="", cerebriumai_api_key="my-api-key")
"""
endpoint_url: str = ""
"""model endpoint to use"""
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not
explicitly specified."""
cerebriumai_api_key: Optional[SecretStr] = None
class Config:
"""Configuration for this pydantic config."""
extra = Extra.forbid
@root_validator(pre=True)
def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
"""Build extra kwargs from additional params that were passed in."""
all_required_field_names = {field.alias for field in cls.__fields__.values()}
extra = values.get("model_kwargs", {})
for field_name in list(values):
if field_name not in all_required_field_names:
if field_name in extra:
raise ValueError(f"Found {field_name} supplied twice.")
logger.warning(
f"""{field_name} was transferred to model_kwargs.
Please confirm that {field_name} is what you intended."""
)
extra[field_name] = values.pop(field_name)
values["model_kwargs"] = extra
return values
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key and python package exists in environment."""
cerebriumai_api_key = convert_to_secret_str(
get_from_dict_or_env(values, "cerebriumai_api_key", "CEREBRIUMAI_API_KEY")
)
values["cerebriumai_api_key"] = cerebriumai_api_key
return values
@property
def _identifying_params(self) -> Mapping[str, Any]:
"""Get the identifying parameters."""
return {
**{"endpoint_url": self.endpoint_url},
**{"model_kwargs": self.model_kwargs},
}
@property
def _llm_type(self) -> str:
"""Return type of llm."""
return "cerebriumai"
def _call(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> str:
headers: Dict = {
"Authorization": cast(
SecretStr, self.cerebriumai_api_key
).get_secret_value(),
"Content-Type": "application/json",
}
params = self.model_kwargs or {}
payload = {"prompt": prompt, **params, **kwargs}
response = requests.post(self.endpoint_url, json=payload, headers=headers)
if response.status_code == 200:
data = response.json()
text = data["result"]
if stop is not None:
# I believe this is required since the stop tokens
# are not enforced by the model parameters
text = enforce_stop_tokens(text, stop)
return text
else:
response.raise_for_status()
return ""
|