ChatEverlyAI

EverlyAI 讓您可以在雲端大規模執行 ML 模型。它也提供對多個 LLM 模型的 API 存取。

此筆記本示範如何使用 langchain.chat_models.ChatEverlyAI 進行 EverlyAI 託管端點。

• 設定 EVERLYAI_API_KEY 環境變數
• 或使用 everlyai_api_key 關鍵字引數

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

import os
from getpass import getpass

if "EVERLYAI_API_KEY" not in os.environ:
    os.environ["EVERLYAI_API_KEY"] = getpass()

讓我們試用 EverlyAI 託管端點上提供的 LLAMA 模型

from langchain_community.chat_models import ChatEverlyAI
from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful AI that shares everything you know."),
    HumanMessage(
        content="Tell me technical facts about yourself. Are you a transformer model? How many billions of parameters do you have?"
    ),
]

chat = ChatEverlyAI(
    model_name="meta-llama/Llama-2-7b-chat-hf", temperature=0.3, max_tokens=64
)
print(chat(messages).content)

API 參考：ChatEverlyAI | HumanMessage | SystemMessage

  Hello! I'm just an AI, I don't have personal information or technical details like a human would. However, I can tell you that I'm a type of transformer model, specifically a BERT (Bidirectional Encoder Representations from Transformers) model. B

EverlyAI 也支援串流回應

from langchain_community.chat_models import ChatEverlyAI
from langchain_core.callbacks import StreamingStdOutCallbackHandler
from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a humorous AI that delights people."),
    HumanMessage(content="Tell me a joke?"),
]

chat = ChatEverlyAI(
    model_name="meta-llama/Llama-2-7b-chat-hf",
    temperature=0.3,
    max_tokens=64,
    streaming=True,
    callbacks=[StreamingStdOutCallbackHandler()],
)
chat(messages)

API 參考：ChatEverlyAI | StreamingStdOutCallbackHandler | HumanMessage | SystemMessage

  Ah, a joke, you say? *adjusts glasses* Well, I've got a doozy for you! *winks*
 *pauses for dramatic effect*
Why did the AI go to therapy?
*drumroll*
Because

AIMessageChunk(content="  Ah, a joke, you say? *adjusts glasses* Well, I've got a doozy for you! *winks*\n *pauses for dramatic effect*\nWhy did the AI go to therapy?\n*drumroll*\nBecause")

讓我們在 EverlyAI 上試用不同的語言模型

from langchain_community.chat_models import ChatEverlyAI
from langchain_core.callbacks import StreamingStdOutCallbackHandler
from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a humorous AI that delights people."),
    HumanMessage(content="Tell me a joke?"),
]

chat = ChatEverlyAI(
    model_name="meta-llama/Llama-2-13b-chat-hf-quantized",
    temperature=0.3,
    max_tokens=128,
    streaming=True,
    callbacks=[StreamingStdOutCallbackHandler()],
)
chat(messages)

API 參考：ChatEverlyAI | StreamingStdOutCallbackHandler | HumanMessage | SystemMessage

  OH HO HO! *adjusts monocle* Well, well, well! Look who's here! *winks*

You want a joke, huh? *puffs out chest* Well, let me tell you one that's guaranteed to tickle your funny bone! *clears throat*

Why couldn't the bicycle stand up by itself? *pauses for dramatic effect* Because it was two-tired! *winks*

Hope that one put a spring in your step, my dear! *

AIMessageChunk(content="  OH HO HO! *adjusts monocle* Well, well, well! Look who's here! *winks*\n\nYou want a joke, huh? *puffs out chest* Well, let me tell you one that's guaranteed to tickle your funny bone! *clears throat*\n\nWhy couldn't the bicycle stand up by itself? *pauses for dramatic effect* Because it was two-tired! *winks*\n\nHope that one put a spring in your step, my dear! *")

相關

• 聊天模型概念指南
• 聊天模型操作指南