Spaces:
Sleeping
Sleeping
File size: 3,696 Bytes
a7b5657 |
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 |
from __future__ import annotations
import logging
from typing import Any, Dict, List, Optional
from langchain.embeddings.base import Embeddings
from langchain.pydantic_v1 import BaseModel, root_validator
from langchain.utils import get_from_dict_or_env
logger = logging.getLogger(__name__)
class ZhipuAIEmbeddings(BaseModel, Embeddings):
"""`Zhipuai Embeddings` embedding models."""
zhipuai_api_key: Optional[str] = None
"""Zhipuai application apikey"""
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""
Validate whether zhipuai_api_key in the environment variables or
configuration file are available or not.
Args:
values: a dictionary containing configuration information, must include the
fields of zhipuai_api_key
Returns:
a dictionary containing configuration information. If zhipuai_api_key
are not provided in the environment variables or configuration
file, the original values will be returned; otherwise, values containing
zhipuai_api_key will be returned.
Raises:
ValueError: zhipuai package not found, please install it with `pip install
zhipuai`
"""
values["zhipuai_api_key"] = get_from_dict_or_env(
values,
"zhipuai_api_key",
"ZHIPUAI_API_KEY",
)
try:
from zhipuai import ZhipuAI
values["client"] = ZhipuAI(api_key=values["zhipuai_api_key"])
except ImportError:
raise ValueError(
"Zhipuai package not found, please install it with "
"`pip install zhipuai`"
)
return values
def _embed(self, texts: str) -> List[float]:
# send request
try:
print("cal embed:", texts)
resp = self.client.embeddings.create(
model="embedding-2",
input=texts
)
#print("resp:", resp)
except Exception as e:
raise ValueError(f"Error raised by inference endpoint: {e}")
if not resp.data :
raise ValueError(
"Error raised by inference API HTTP code: %s, %s"
% (resp["code"], resp["msg"])
)
embeddings = resp.data[0].embedding
return embeddings
def embed_query(self, text: str) -> List[float]:
"""
Embedding a text.
Args:
Text (str): A text to be embedded.
Return:
List [float]: An embedding list of input text, which is a list of floating-point values.
"""
resp = self.embed_documents([text])
return resp[0]
def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""
Embeds a list of text documents.
Args:
texts (List[str]): A list of text documents to embed.
Returns:
List[List[float]]: A list of embeddings for each document in the input list.
Each embedding is represented as a list of float values.
"""
return [self._embed(text) for text in texts]
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
"""Asynchronous Embed search docs."""
raise NotImplementedError(
"Please use `embed_documents`. Official does not support asynchronous requests")
async def aembed_query(self, text: str) -> List[float]:
"""Asynchronous Embed query text."""
raise NotImplementedError(
"Please use `aembed_query`. Official does not support asynchronous requests") |