跳到主要内容
Open In ColabOpen on GitHub

RunPod LLM

开始使用 RunPod LLM。

概述

本指南介绍如何使用 LangChain 的 RunPod LLM 类与托管在 RunPod Serverless 上的文本生成模型进行交互。

设置

  1. 安装软件包
    pip install -qU langchain-runpod
  2. 部署 LLM 端点:按照 RunPod 提供商指南中的设置步骤,在 RunPod Serverless 上部署一个兼容的文本生成端点并获取其端点 ID。
  3. 设置环境变量:确保已设置 RUNPOD_API_KEYRUNPOD_ENDPOINT_ID
import getpass
import os

# Make sure environment variables are set (or pass them directly to RunPod)
if "RUNPOD_API_KEY" not in os.environ:
os.environ["RUNPOD_API_KEY"] = getpass.getpass("Enter your RunPod API Key: ")
if "RUNPOD_ENDPOINT_ID" not in os.environ:
os.environ["RUNPOD_ENDPOINT_ID"] = input("Enter your RunPod Endpoint ID: ")

实例化

初始化 RunPod 类。您可以通过 model_kwargs 传递模型特定参数并配置轮询行为。

from langchain_runpod import RunPod

llm = RunPod(
# runpod_endpoint_id can be passed here if not set in env
model_kwargs={
"max_new_tokens": 256,
"temperature": 0.6,
"top_k": 50,
# Add other parameters supported by your endpoint handler
},
# Optional: Adjust polling
# poll_interval=0.3,
# max_polling_attempts=100
)

调用

使用标准的 LangChain .invoke().ainvoke() 方法调用模型。还支持通过 .stream().astream() 进行流式传输(通过轮询 RunPod 的 /stream 端点模拟实现)。

prompt = "Write a tagline for an ice cream shop on the moon."

# Invoke (Sync)
try:
response = llm.invoke(prompt)
print("--- Sync Invoke Response ---")
print(response)
except Exception as e:
print(
f"Error invoking LLM: {e}. Ensure endpoint ID/API key are correct and endpoint is active/compatible."
)
# Stream (Sync, simulated via polling /stream)
print("\n--- Sync Stream Response ---")
try:
for chunk in llm.stream(prompt):
print(chunk, end="", flush=True)
print() # Newline
except Exception as e:
print(
f"\nError streaming LLM: {e}. Ensure endpoint handler supports streaming output format."
)

异步用法

# AInvoke (Async)
try:
async_response = await llm.ainvoke(prompt)
print("--- Async Invoke Response ---")
print(async_response)
except Exception as e:
print(f"Error invoking LLM asynchronously: {e}.")
# AStream (Async)
print("\n--- Async Stream Response ---")
try:
async for chunk in llm.astream(prompt):
print(chunk, end="", flush=True)
print() # Newline
except Exception as e:
print(
f"\nError streaming LLM asynchronously: {e}. Ensure endpoint handler supports streaming output format."
)

链式调用

该 LLM 可与 LangChain 表达式语言 (LCEL) 链无缝集成。

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import PromptTemplate

# Assumes 'llm' variable is instantiated from the 'Instantiation' cell
prompt_template = PromptTemplate.from_template("Tell me a joke about {topic}")
parser = StrOutputParser()

chain = prompt_template | llm | parser

try:
chain_response = chain.invoke({"topic": "bears"})
print("--- Chain Response ---")
print(chain_response)
except Exception as e:
print(f"Error running chain: {e}")

# Async chain
try:
async_chain_response = await chain.ainvoke({"topic": "robots"})
print("--- Async Chain Response ---")
print(async_chain_response)
except Exception as e:
print(f"Error running async chain: {e}")

端点考量

  • 输入:端点处理器应期望提示字符串位于 {"input": {"prompt": "...", ...}} 内。
  • 输出:处理器应在最终状态响应的 "output" 键中返回生成的文本(例如,{"output": "Generated text..."}{"output": {"text": "..."}})。
  • 流式传输:对于通过 /stream 端点模拟的流式传输,处理器必须在状态响应中用一个包含分块字典的列表填充 "stream" 键,例如 [{"output": "token1"}, {"output": "token2"}]

API 参考

有关 RunPod LLM 类、参数和方法的详细文档,请参阅源代码或生成的 API 参考(如果可用)。

源代码链接:https://github.com/runpod/langchain-runpod/blob/main/langchain_runpod/llms.py