Source code for langchain_community.embeddings.gpt4all

from typing import Any, Dict, List, Optional

from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, root_validator


[docs]class GPT4AllEmbeddings(BaseModel, Embeddings): """GPT4All嵌入模型。 要使用,您应该安装gpt4all python包 示例: .. code-block:: python from langchain_community.embeddings import GPT4AllEmbeddings model_name = "all-MiniLM-L6-v2.gguf2.f16.gguf" gpt4all_kwargs = {'allow_download': 'True'} embeddings = GPT4AllEmbeddings( model_name=model_name, gpt4all_kwargs=gpt4all_kwargs ) """ model_name: str n_threads: Optional[int] = None device: Optional[str] = "cpu" gpt4all_kwargs: Optional[dict] = {} client: Any #: :meta private: @root_validator() def validate_environment(cls, values: Dict) -> Dict: """验证是否安装了GPT4All库。""" try: from gpt4all import Embed4All values["client"] = Embed4All( model_name=values["model_name"], n_threads=values.get("n_threads"), device=values.get("device"), **values.get("gpt4all_kwargs"), ) except ImportError: raise ImportError( "Could not import gpt4all library. " "Please install the gpt4all library to " "use this embedding model: pip install gpt4all" ) return values
[docs] def embed_documents(self, texts: List[str]) -> List[List[float]]: """使用GPT4All嵌入文档列表。 参数: texts:要嵌入的文本列表。 返回: 每个文本的嵌入列表。 """ embeddings = [self.client.embed(text) for text in texts] return [list(map(float, e)) for e in embeddings]
[docs] def embed_query(self, text: str) -> List[float]: """使用GPT4All嵌入一个查询。 参数: text: 要嵌入的文本。 返回: 文本的嵌入结果。 """ return self.embed_documents([text])[0]