Spaces:
Runtime error
Runtime error
File size: 5,470 Bytes
129cd69 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
from typing import Any, Dict, List, Mapping, Optional
import requests
from langchain_core.pydantic_v1 import Extra, root_validator
from langchain.callbacks.manager import CallbackManagerForLLMRun
from langchain.llms.base import LLM
from langchain.llms.utils import enforce_stop_tokens
from langchain.utils import get_from_dict_or_env
VALID_TASKS = ("text2text-generation", "text-generation", "summarization")
class HuggingFaceEndpoint(LLM):
"""HuggingFace Endpoint models.
To use, you should have the ``huggingface_hub`` python package installed, and the
environment variable ``HUGGINGFACEHUB_API_TOKEN`` set with your API token, or pass
it as a named parameter to the constructor.
Only supports `text-generation` and `text2text-generation` for now.
Example:
.. code-block:: python
from langchain.llms import HuggingFaceEndpoint
endpoint_url = (
"https://abcdefghijklmnop.us-east-1.aws.endpoints.huggingface.cloud"
)
hf = HuggingFaceEndpoint(
endpoint_url=endpoint_url,
huggingfacehub_api_token="my-api-key"
)
"""
endpoint_url: str = ""
"""Endpoint URL to use."""
task: Optional[str] = None
"""Task to call the model with.
Should be a task that returns `generated_text` or `summary_text`."""
model_kwargs: Optional[dict] = None
"""Keyword arguments to pass to the model."""
huggingfacehub_api_token: Optional[str] = None
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key and python package exists in environment."""
huggingfacehub_api_token = get_from_dict_or_env(
values, "huggingfacehub_api_token", "HUGGINGFACEHUB_API_TOKEN"
)
try:
from huggingface_hub.hf_api import HfApi
try:
HfApi(
endpoint="https://huggingface.co", # Can be a Private Hub endpoint.
token=huggingfacehub_api_token,
).whoami()
except Exception as e:
raise ValueError(
"Could not authenticate with huggingface_hub. "
"Please check your API token."
) from e
except ImportError:
raise ImportError(
"Could not import huggingface_hub python package. "
"Please install it with `pip install huggingface_hub`."
)
values["huggingfacehub_api_token"] = huggingfacehub_api_token
return values
@property
def _identifying_params(self) -> Mapping[str, Any]:
"""Get the identifying parameters."""
_model_kwargs = self.model_kwargs or {}
return {
**{"endpoint_url": self.endpoint_url, "task": self.task},
**{"model_kwargs": _model_kwargs},
}
@property
def _llm_type(self) -> str:
"""Return type of llm."""
return "huggingface_endpoint"
def _call(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> str:
"""Call out to HuggingFace Hub's inference endpoint.
Args:
prompt: The prompt to pass into the model.
stop: Optional list of stop words to use when generating.
Returns:
The string generated by the model.
Example:
.. code-block:: python
response = hf("Tell me a joke.")
"""
_model_kwargs = self.model_kwargs or {}
# payload samples
params = {**_model_kwargs, **kwargs}
parameter_payload = {"inputs": prompt, "parameters": params}
# HTTP headers for authorization
headers = {
"Authorization": f"Bearer {self.huggingfacehub_api_token}",
"Content-Type": "application/json",
}
# send request
try:
response = requests.post(
self.endpoint_url, headers=headers, json=parameter_payload
)
except requests.exceptions.RequestException as e: # This is the correct syntax
raise ValueError(f"Error raised by inference endpoint: {e}")
generated_text = response.json()
if "error" in generated_text:
raise ValueError(
f"Error raised by inference API: {generated_text['error']}"
)
if self.task == "text-generation":
text = generated_text[0]["generated_text"]
# Remove prompt if included in generated text.
if text.startswith(prompt):
text = text[len(prompt) :]
elif self.task == "text2text-generation":
text = generated_text[0]["generated_text"]
elif self.task == "summarization":
text = generated_text[0]["summary_text"]
else:
raise ValueError(
f"Got invalid task {self.task}, "
f"currently only {VALID_TASKS} are supported"
)
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
|