EmbeddingsLocalHuggingFace.py

# Copyright 2024-, RGBYang.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from transformers import AutoTokenizer, AutoModel
import torch
from langchain.embeddings.base import Embeddings

# 使用本地模型初始化Embeddings
class EmbeddingsLocalHuggingFace(Embeddings):
    def __init__(self, model_name: str):
        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
        self.model = AutoModel.from_pretrained(model_name)
        self.model.eval()  # 确保模型处于评估模式

    def embed_documents(self, texts):
        return self._embed(texts)

    def embed_query(self, text):
        return self._embed([text])[0]

    def _embed(self, texts):
        embeddings = []
        with torch.no_grad():
            for text in texts:
                inputs = self.tokenizer(text, return_tensors='pt', padding=True, truncation=True)
                outputs = self.model(**inputs)
                # 获取最后一层隐藏状态的均值作为嵌入
                embedding = outputs.last_hidden_state.mean(dim=1).squeeze().cpu().numpy()
                embeddings.append(embedding.tolist())
        return embeddings