Spaces:
Runtime error
Runtime error
File size: 5,254 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
import json
import os
from typing import Any, Dict, List, Optional
from langchain_core._api import deprecated
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
DEFAULT_MODEL = "sentence-transformers/all-mpnet-base-v2"
VALID_TASKS = ("feature-extraction",)
@deprecated(
since="0.2.2",
removal="0.3.0",
alternative_import="langchain_huggingface.HuggingFaceEndpointEmbeddings",
)
class HuggingFaceHubEmbeddings(BaseModel, Embeddings):
"""HuggingFaceHub embedding 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.
Example:
.. code-block:: python
from langchain_community.embeddings import HuggingFaceHubEmbeddings
model = "sentence-transformers/all-mpnet-base-v2"
hf = HuggingFaceHubEmbeddings(
model=model,
task="feature-extraction",
huggingfacehub_api_token="my-api-key",
)
"""
client: Any #: :meta private:
async_client: Any #: :meta private:
model: Optional[str] = None
"""Model name to use."""
repo_id: Optional[str] = None
"""Huggingfacehub repository id, for backward compatibility."""
task: Optional[str] = "feature-extraction"
"""Task to call the model with."""
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 = values["huggingfacehub_api_token"] or os.getenv(
"HUGGINGFACEHUB_API_TOKEN"
)
try:
from huggingface_hub import AsyncInferenceClient, InferenceClient
if values["model"]:
values["repo_id"] = values["model"]
elif values["repo_id"]:
values["model"] = values["repo_id"]
else:
values["model"] = DEFAULT_MODEL
values["repo_id"] = DEFAULT_MODEL
client = InferenceClient(
model=values["model"],
token=huggingfacehub_api_token,
)
async_client = AsyncInferenceClient(
model=values["model"],
token=huggingfacehub_api_token,
)
if values["task"] not in VALID_TASKS:
raise ValueError(
f"Got invalid task {values['task']}, "
f"currently only {VALID_TASKS} are supported"
)
values["client"] = client
values["async_client"] = async_client
except ImportError:
raise ImportError(
"Could not import huggingface_hub python package. "
"Please install it with `pip install huggingface_hub`."
)
return values
def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""Call out to HuggingFaceHub's embedding endpoint for embedding search docs.
Args:
texts: The list of texts to embed.
Returns:
List of embeddings, one for each text.
"""
# replace newlines, which can negatively affect performance.
texts = [text.replace("\n", " ") for text in texts]
_model_kwargs = self.model_kwargs or {}
responses = self.client.post(
json={"inputs": texts, "parameters": _model_kwargs}, task=self.task
)
return json.loads(responses.decode())
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
"""Async Call to HuggingFaceHub's embedding endpoint for embedding search docs.
Args:
texts: The list of texts to embed.
Returns:
List of embeddings, one for each text.
"""
# replace newlines, which can negatively affect performance.
texts = [text.replace("\n", " ") for text in texts]
_model_kwargs = self.model_kwargs or {}
responses = await self.async_client.post(
json={"inputs": texts, "parameters": _model_kwargs}, task=self.task
)
return json.loads(responses.decode())
def embed_query(self, text: str) -> List[float]:
"""Call out to HuggingFaceHub's embedding endpoint for embedding query text.
Args:
text: The text to embed.
Returns:
Embeddings for the text.
"""
response = self.embed_documents([text])[0]
return response
async def aembed_query(self, text: str) -> List[float]:
"""Async Call to HuggingFaceHub's embedding endpoint for embedding query text.
Args:
text: The text to embed.
Returns:
Embeddings for the text.
"""
response = (await self.aembed_documents([text]))[0]
return response
|