OpenLM

OpenLM 是一個零依賴性、相容於 OpenAI 的 LLM 供應商，可以直接透過 HTTP 呼叫不同的推論端點。

它實作了 OpenAI Completion 類別，使其可以用作 OpenAI API 的直接替代品。此變更集利用 BaseOpenAI 以盡可能減少新增程式碼。

此範例說明如何使用 LangChain 與 OpenAI 和 HuggingFace 互動。您需要來自兩者的 API 金鑰。

設定

安裝依賴套件並設定 API 金鑰。

# Uncomment to install openlm and openai if you haven't already

%pip install --upgrade --quiet  openlm
%pip install --upgrade --quiet  langchain-openai

import os
from getpass import getpass

# Check if OPENAI_API_KEY environment variable is set
if "OPENAI_API_KEY" not in os.environ:
    print("Enter your OpenAI API key:")
    os.environ["OPENAI_API_KEY"] = getpass()

# Check if HF_API_TOKEN environment variable is set
if "HF_API_TOKEN" not in os.environ:
    print("Enter your HuggingFace Hub API key:")
    os.environ["HF_API_TOKEN"] = getpass()

搭配 OpenLM 使用 LangChain

在這裡，我們將在 LLMChain 中呼叫兩個模型，分別是來自 OpenAI 的 text-davinci-003 和 HuggingFace 上的 gpt2。

from langchain.chains import LLMChain
from langchain_community.llms import OpenLM
from langchain_core.prompts import PromptTemplate

API 參考：LLMChain | OpenLM | PromptTemplate

question = "What is the capital of France?"
template = """Question: {question}

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

prompt = PromptTemplate.from_template(template)

for model in ["text-davinci-003", "huggingface.co/gpt2"]:
    llm = OpenLM(model=model)
    llm_chain = LLMChain(prompt=prompt, llm=llm)
    result = llm_chain.run(question)
    print(
        """Model: {}
Result: {}""".format(model, result)
    )

Model: text-davinci-003
Result:  France is a country in Europe. The capital of France is Paris.
Model: huggingface.co/gpt2
Result: Question: What is the capital of France?

Answer: Let's think step by step. I am not going to lie, this is a complicated issue, and I don't see any solutions to all this, but it is still far more

相關內容

• LLM 概念指南
• LLM 操作指南