Huggingface 端点集成

from langchain_huggingface import HuggingFaceEndpoint

pip install -qU huggingface_hub

# 获取令牌：https://huggingface.co/docs/api-inference/quicktour#get-your-api-token

from getpass import getpass

HUGGINGFACEHUB_API_TOKEN = getpass()

import os

os.environ["HUGGINGFACEHUB_API_TOKEN"] = HUGGINGFACEHUB_API_TOKEN

from langchain_huggingface import HuggingFaceEndpoint

from langchain_classic.chains import LLMChain
from langchain_core.prompts import PromptTemplate

question = "Who won the FIFA World Cup in the year 1994? "

template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate.from_template(template)

repo_id = "deepseek-ai/DeepSeek-R1-0528"

llm = HuggingFaceEndpoint(
    repo_id=repo_id,
    max_length=128,
    temperature=0.5,
    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
    provider="auto",  # 在此处设置您的提供商 hf.co/settings/inference-providers
    # provider="hyperbolic",
    # provider="nebius",
    # provider="together",
)
llm_chain = prompt | llm
print(llm_chain.invoke({"question": question}))

# 在下方设置您的推理端点 URL
your_endpoint_url = "https://fayjubiy2xqn36z0.us-east-1.aws.endpoints.huggingface.cloud"

llm = HuggingFaceEndpoint(
    endpoint_url=f"{your_endpoint_url}",
    max_new_tokens=512,
    top_k=10,
    top_p=0.95,
    typical_p=0.95,
    temperature=0.01,
    repetition_penalty=1.03,
)
llm("What did foo say about bar?")

from langchain_core.callbacks import StreamingStdOutCallbackHandler
from langchain_huggingface import HuggingFaceEndpoint

llm = HuggingFaceEndpoint(
    endpoint_url=f"{your_endpoint_url}",
    max_new_tokens=512,
    top_k=10,
    top_p=0.95,
    typical_p=0.95,
    temperature=0.01,
    repetition_penalty=1.03,
    streaming=True,
)
llm("What did foo say about bar?", callbacks=[StreamingStdOutCallbackHandler()])