Why does llama-index still require an OpenAI key when using Hugging Face local embedding model?

题意：当使用Hugging Face的本地嵌入模型时，为什么llama-index仍然需要一个OpenAI的密钥（key）？

问题背景：

I am creating a very simple question and answer app based on documents using llama-index. Previously, I had it working with OpenAI. Now I want to try using no external APIs so I'm trying the Hugging Face example.

我正在使用 llama-index 创建一个基于文档的非常简单的问答应用。之前，我使用 OpenAI 来实现这个功能。现在我想尝试不使用任何外部 API，所以我正在尝试 Hugging Face 的示例。

Note that for a completely private experience, also setup a local embedding model.

请注意，为了获得完全私有的体验，也请设置一个本地嵌入模型。

Here is my code:        这是我的代码

from pathlib import Path
import gradio as gr
import sys
import logging
import os

from llama_index.llms import HuggingFaceLLM
from llama_index.prompts.prompts import SimpleInputPrompt

logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))


from llama_index import SimpleDirectoryReader, VectorStoreIndex, ServiceContext, load_index_from_storage, StorageContext

storage_path = "storage/"

docs_path="docs"

def construct_index(directory_path):
    max_input_size = 4096
    num_outputs = 512
    #max_chunk_overlap = 20
    chunk_overlap_ratio = 0.1
    chunk_size_limit = 600

    #prompt_helper = PromptHelper(max_input_size, num_outputs, chunk_overlap_ratio, chunk_size_limit=chunk_size_limit)

    system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
    - StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
    - StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
    - StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
    - StableLM will refuse to participate in anything that could harm a human.
    """

    # This will wrap the default prompts that are internal to llama-index
    query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")


    llm = HuggingFaceLLM(
        context_window=4096,
        max_new_tokens=256,
        generate_kwargs={"temperature": 0.7, "do_sample": False},
        system_prompt=system_prompt,
        query_wrapper_prompt=query_wrapper_prompt,
        tokenizer_name="StabilityAI/stablelm-tuned-alpha-3b",
        model_name="StabilityAI/stablelm-tuned-alpha-3b",
        device_map="auto",
        stopping_ids=[50278, 50279, 50277, 1, 0],
        tokenizer_kwargs={"max_length": 4096},
        # uncomment this if using CUDA to reduce memory usage
        # model_kwargs={"torch_dtype": torch.float16}
    )
    #llm=ChatOpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=num_outputs)
    #llm_predictor = LLMPredictor(llm=llm)
    service_context = ServiceContext.from_defaults(chunk_size=1024, llm=llm)

    documents = SimpleDirectoryReader(directory_path).load_data()

    index = VectorStoreIndex.from_documents(documents, service_context=service_context)
    #index = VectorStoreIndex(documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper)

    index.storage_context.persist(persist_dir=storage_path)

    return index

def chatbot(input_text):
    index = load_index_from_storage(StorageContext.from_defaults(persist_dir=storage_path))
    #index = GPTVectorStoreIndex.load_from_disk('index.json')
    #query_engine = index.as_query_engine(response_synthesizer=response_synthesizer);
    query_engine = index.as_query_engine(streaming=True)

    response = query_engine.query(input_text)

    print(response.source_nodes)

    relevant_files=[]

    for node_with_score in response.source_nodes:
        print(node_with_score)
        print(node_with_score.node)
        print(node_with_score.node.metadata)
        print(node_with_score.node.metadata['file_name'])

        file = node_with_score.node.metadata['file_name']
        print( file )

        # Resolve the full file path for the downloading
        full_file_path = Path( docs_path, file ).resolve()

        # See if it's already in the array
        if full_file_path not in relevant_files:
            relevant_files.append( full_file_path ) # Add it

    print( relevant_files )

    return response.get_response(), relevant_files

iface = gr.Interface(fn=chatbot,
                     inputs=gr.components.Textbox(lines=7, label="Enter your text"),
                     outputs=[
                        gr.components.Textbox(label="Response"), 
                        gr.components.File(label="Relevant Files")
                        ],
                     title="Custom-trained AI Chatbot",
                     allow_flagging="never")

index = construct_index(docs_path)
iface.launch(share=False)

 

Regardless, the code errors out saying:        无论如何，代码出现了错误提示：

ValueError: No API key found for OpenAI.
Please set either the OPENAI_API_KEY environment variable or openai.api_key prior to initialization.
API keys can be found or created at https://platform.openai.com/account/api-keys

Am I not understanding how to set up a local model?

我是不是没有理解如何设置本地模型？

问题解决：

Turns out I had to set the embed_model to "local" on the ServiceContext.

原来我需要将ServiceContext中的embed_model设置为"local"。

ServiceContext.from_defaults(chunk_size=1024, llm=llm, embed_model="local")

Also, when I was loading the vector index from disk I wasn't setting the llm predictor again which cause a secondary issue. So I decided to make the vector index a global variable. Here is my final code that works.

另外，当我从磁盘加载向量索引时，我没有重新设置llm predictor，这导致了另一个问题。所以我决定将向量索引设置为一个全局变量。以下是我最终能够工作的代码。

from pathlib import Path
import gradio as gr
import sys
import logging
import os

from llama_index.llms import HuggingFaceLLM
from llama_index.prompts.prompts import SimpleInputPrompt

logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))


from llama_index import SimpleDirectoryReader, VectorStoreIndex, ServiceContext, load_index_from_storage, StorageContext

storage_path = "storage"

docs_path="docs"

print(storage_path)

max_input_size = 4096
num_outputs = 512
#max_chunk_overlap = 20
chunk_overlap_ratio = 0.1
chunk_size_limit = 600


system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
- StableLM will refuse to participate in anything that could harm a human.
"""

# This will wrap the default prompts that are internal to llama-index
query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")


llm = HuggingFaceLLM(
    context_window=4096,
    max_new_tokens=256,
    generate_kwargs={"temperature": 0.7, "do_sample": False},
    system_prompt=system_prompt,
    query_wrapper_prompt=query_wrapper_prompt,
    tokenizer_name="StabilityAI/stablelm-tuned-alpha-3b",
    model_name="StabilityAI/stablelm-tuned-alpha-3b",
    device_map="auto",
    stopping_ids=[50278, 50279, 50277, 1, 0],
    tokenizer_kwargs={"max_length": 4096},
    # uncomment this if using CUDA to reduce memory usage
    # model_kwargs={"torch_dtype": torch.float16}
)

service_context = ServiceContext.from_defaults(chunk_size=1024, llm=llm, embed_model="local")

documents = SimpleDirectoryReader(docs_path).load_data()

index = VectorStoreIndex.from_documents(documents, service_context=service_context)


def chatbot(input_text):
    query_engine = index.as_query_engine()

    response = query_engine.query(input_text)

    print(response.source_nodes)

    relevant_files=[]

    for node_with_score in response.source_nodes:
        print(node_with_score)
        print(node_with_score.node)
        print(node_with_score.node.metadata)
        print(node_with_score.node.metadata['file_name'])

        file = node_with_score.node.metadata['file_name']
        print( file )

        # Resolve the full file path for the downloading
        full_file_path = Path( docs_path, file ).resolve()

        # See if it's already in the array
        if full_file_path not in relevant_files:
            relevant_files.append( full_file_path ) # Add it

    print( relevant_files )

    return response.response, relevant_files

iface = gr.Interface(fn=chatbot,
                     inputs=gr.components.Textbox(lines=7, label="Enter your text"),
                     outputs=[
                        gr.components.Textbox(label="Response"), 
                        gr.components.File(label="Relevant Files")
                        ],
                     title="Custom-trained AI Chatbot",
                     allow_flagging="never")

iface.launch(share=False)