Modal

本頁面涵蓋如何使用 Modal 生態系統來執行 LangChain 自訂 LLM。它分為兩個部分

1. Modal 安裝與網頁端點部署
2. 使用已部署的網頁端點與 LLM 封裝器類別。

安裝與設定

• 使用 pip install modal 安裝
• 執行 modal token new

定義您的 Modal 函數與 Webhook

您必須包含提示。有一個嚴格的回應結構

class Item(BaseModel):
    prompt: str

@stub.function()
@modal.web_endpoint(method="POST")
def get_text(item: Item):
    return {"prompt": run_gpt2.call(item.prompt)}

以下是使用 GPT2 模型的範例

from pydantic import BaseModel

import modal

CACHE_PATH = "/root/model_cache"

class Item(BaseModel):
    prompt: str

stub = modal.Stub(name="example-get-started-with-langchain")

def download_model():
    from transformers import GPT2Tokenizer, GPT2LMHeadModel
    tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
    model = GPT2LMHeadModel.from_pretrained('gpt2')
    tokenizer.save_pretrained(CACHE_PATH)
    model.save_pretrained(CACHE_PATH)

# Define a container image for the LLM function below, which
# downloads and stores the GPT-2 model.
image = modal.Image.debian_slim().pip_install(
    "tokenizers", "transformers", "torch", "accelerate"
).run_function(download_model)

@stub.function(
    gpu="any",
    image=image,
    retries=3,
)
def run_gpt2(text: str):
    from transformers import GPT2Tokenizer, GPT2LMHeadModel
    tokenizer = GPT2Tokenizer.from_pretrained(CACHE_PATH)
    model = GPT2LMHeadModel.from_pretrained(CACHE_PATH)
    encoded_input = tokenizer(text, return_tensors='pt').input_ids
    output = model.generate(encoded_input, max_length=50, do_sample=True)
    return tokenizer.decode(output[0], skip_special_tokens=True)

@stub.function()
@modal.web_endpoint(method="POST")
def get_text(item: Item):
    return {"prompt": run_gpt2.call(item.prompt)}

部署網頁端點

使用 modal deploy CLI 命令將網頁端點部署到 Modal 雲端。您的網頁端點將在 modal.run 網域下取得一個持久 URL。

圍繞 Modal 網頁端點的 LLM 封裝器

Modal LLM 封裝器類別將接受您已部署的網頁端點 URL。

from langchain_community.llms import Modal

endpoint_url = "https://ecorp--custom-llm-endpoint.modal.run"  # REPLACE ME with your deployed Modal web endpoint's URL

llm = Modal(endpoint_url=endpoint_url)
llm_chain = LLMChain(prompt=prompt, llm=llm)

question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"

llm_chain.run(question)

API 參考文檔：Modal