要解决在使用DSPy训练管道中的HuggingFaceEmbedding类时出现的"'HuggingFaceEmbedding'对象没有属性'_model'"错误，请确保在HuggingFaceEmbedding类中正确初始化_model属性。以下是显示如何在__init__方法中初始化_model的相关信息：

确保AutoModel的初始化正确放置在__init__方法中，并确保_model属性得到正确设置。这应该解决属性错误1(https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/embeddings/llama-index-embeddings-huggingface/llama_index/embeddings/huggingface/base.py)2(https://github.com/run-llama/llama_index/blob/main/llama-index-legacy/llama_index/legacy/embeddings/huggingface.py)。

• 要继续与Dosu交谈，请提及@dosu。*

@tituslhy 你好，我也在尝试使用 HuggingFaceEmbedding 与 DSPy。与烹饪书不同，我只是在 DSPy 模块中使用了向量检索器。这里是一个更简洁的示例来演示这个问题：

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
import dspy
from dspy.teleprompt import BootstrapFewShot

class Rag(dspy.Module):
    def __init__(self):
        super().__init__()
        reader = SimpleDirectoryReader(input_files=["paul_graham_essay.txt"])
        docs = reader.load_data()
        index = VectorStoreIndex.from_documents(docs)
        self.retriever = index.as_retriever()

    def forward(self, question):
        return dspy.Prediction(answer=str(self.retriever.retrieve(question)))

Settings.embed_model = HuggingFaceEmbedding(
    model_name="BAAI/bge-small-en-v1.5", trust_remote_code=True
)
Settings.llm = None

teleprompter = BootstrapFewShot()
train_examples = [
    dspy.Example(
        question="What did the author do growing up?",
        answer="The author wrote short stories and also worked on programming.",
    ).with_inputs("question"),
    dspy.Example(
        question="What did the author do during his time at YC?",
        answer="organizing a Summer Founders Program, funding startups, writing essays, working on a new version of Arc, creating Hacker News, and developing internal software for YC",
    ).with_inputs("question"),
]
teleprompter.compile(Rag(), trainset=train_examples)

只需下载数据集：

wget https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt -O paul_graham_essay.txt

即使没有 LLM,你也应该能够运行这个示例。
这在我这边的输出是：

2024-07-02T08:47:05.960695Z [error    ] Failed to run or to evaluate example Example({'question': 'What did the author do growing up?', 'answer': 'The author wrote short stories and also worked on programming.'}) (input_keys={'question'}) with None due to 'HuggingFaceEmbedding' object has no attribute '_model'. [dspy.teleprompt.bootstrap] filename=bootstrap.py lineno=211
2024-07-02T08:47:05.961326Z [error    ] Failed to run or to evaluate example Example({'question': 'What did the author do during his time at YC?', 'answer': 'organizing a Summer Founders Program, funding startups, writing essays, working on a new version of Arc, creating Hacker News, and developing internal software for YC'}) (input_keys={'question'}) with None due to 'HuggingFaceEmbedding' object has no attribute '_model'. [dspy.teleprompt.bootstrap] filename=bootstrap.py lineno=211

虽然我还没有做更多的调查，但我认为这可能与我之前打开的一个问题有关 #13956 。在一个相关的 issue 上，一个开发者提到你不能使用本地嵌入模型进行多进程。因此，我怀疑 teleprompter.compile() 中可能有一些与此相关的问题(因为 DSPy 不使用多进程)。