開始使用 Gemma 和 LangChain

前往 ai.google.dev 查看 在 Google Colab 中執行 前往 GitHub 查看原始碼

本教學課程說明如何開始在 Google Cloud 或 Colab 環境中執行的 Gemma 和 LangChain。Gemma 是一組最先進的開放式模型，與建立 Gemini 模型所使用的研究和技術相同。LangChain 是一種架構，用於建構及部署由語言模型支援的情境感知應用程式。

在 Google Cloud 中執行 Gemma

langchain-google-vertexai 套件提供 LangChain 與 Google Cloud 模型的整合功能。

安裝依附元件

pip install --upgrade -q langchain langchain-google-vertexai

驗證

除非使用 Colab Enterprise，否則您必須進行驗證。

from google.colab import auth
auth.authenticate_user()

部署模型

您可以透過 Vertex AI 這個平台訓練及部署 AI 模型和應用程式，Model Garden 是一系列精選模型，您可以在 Google Cloud 控制台中探索。

如要部署 Gemma，請在 Vertex AI 的 Model Garden 中開啟模型，並完成下列步驟：

  1. 選取 [Deploy] (部署)。
  2. 對部署表單欄位進行任何所需變更，或是保留 只要你接受預設值即可記下下列欄位，稍後會用到：
    • 端點名稱 (例如 google_gemma-7b-it-mg-one-click-deploy)
    • 區域 (例如 us-west1)
  3. 選取「Deploy」(部署)，將模型部署至 Vertex AI。Deployment 將 會在幾分鐘內完成

端點準備就緒後，請複製專案 ID、端點 ID 和位置，然後輸入為參數。

# @title Basic parameters
project: str = ""  # @param {type:"string"}
endpoint_id: str = ""  # @param {type:"string"}
location: str = "" # @param {type:"string"}

執行模型

from langchain_google_vertexai import GemmaVertexAIModelGarden, GemmaChatVertexAIModelGarden

llm = GemmaVertexAIModelGarden(
    endpoint_id=endpoint_id,
    project=project,
    location=location,
)

output = llm.invoke("What is the meaning of life?")
print(output)

Prompt:
What is the meaning of life?
Output:
Life is a complex and multifaceted phenomenon that has fascinated philosophers, scientists, and

您也可以使用 Gemma 進行多輪對話：

from langchain_core.messages import (
    HumanMessage
)

llm = GemmaChatVertexAIModelGarden(
    endpoint_id=endpoint_id,
    project=project,
    location=location,
)

message1 = HumanMessage(content="How much is 2+2?")
answer1 = llm.invoke([message1])
print(answer1)

message2 = HumanMessage(content="How much is 3+3?")
answer2 = llm.invoke([message1, answer1, message2])

print(answer2)

content='Prompt:\n<start_of_turn>user\nHow much is 2+2?<end_of_turn>\n<start_of_turn>model\nOutput:\nSure, the answer is 4.\n\n2 + 2 = 4'
content='Prompt:\n<start_of_turn>user\nHow much is 2+2?<end_of_turn>\n<start_of_turn>model\nPrompt:\n<start_of_turn>user\nHow much is 2+2?<end_of_turn>\n<start_of_turn>model\nOutput:\nSure, the answer is 4.\n\n2 + 2 = 4<end_of_turn>\n<start_of_turn>user\nHow much is 3+3?<end_of_turn>\n<start_of_turn>model\nOutput:\nSure, the answer is 6.\n\n3 + 3 = 6'

您可以對回應進行後置處理，避免重複：

answer1 = llm.invoke([message1], parse_response=True)
print(answer1)

answer2 = llm.invoke([message1, answer1, message2], parse_response=True)

print(answer2)

content='Output:\nSure, here is the answer:\n\n2 + 2 = 4'
content='Output:\nSure, here is the answer:\n\n3 + 3 = 6<'

透過 Kaggle 下載項目執行 Gemma

本節說明如何從 Kaggle 下載 Gemma，然後執行模型。

如要完成這個部分，您必須先前往 Gemma 設定完成設定。

然後繼續進行下一個部分，您將為 Colab 環境設定環境變數。

設定環境變數

設定 KAGGLE_USERNAME 和 KAGGLE_KEY 的環境變數。

import os
from google.colab import userdata

# Note: `userdata.get` is a Colab API. If you're not using Colab, set the env
# vars as appropriate for your system.
os.environ["KAGGLE_USERNAME"] = userdata.get('KAGGLE_USERNAME')
os.environ["KAGGLE_KEY"] = userdata.get('KAGGLE_KEY')

安裝依附元件

# Install Keras 3 last. See https://keras.io/getting_started/ for more details.
pip install -q -U keras-nlp
pip install -q -U keras>=3

執行模型

from langchain_google_vertexai import GemmaLocalKaggle

您可以指定 Keras 後端 (預設為 tensorflow，但可變更為 jax 或 torch)。

# @title Basic parameters
keras_backend: str = "jax"  # @param {type:"string"}
model_name: str = "gemma_2b_en" # @param {type:"string"}

llm = GemmaLocalKaggle(model_name=model_name, keras_backend=keras_backend)

Attaching 'config.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'config.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'model.weights.h5' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'tokenizer.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'assets/tokenizer/vocabulary.spm' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...

output = llm.invoke("What is the meaning of life?", max_tokens=30)
print(output)

What is the meaning of life?

The question is one of the most important questions in the world.

It’s the question that has

執行聊天模型

如上方 Google Cloud 範例所示，您可以使用 Gemma 本機部署來執行多輪對話。您可能需要重新啟動筆記本並清除 GPU 記憶體，以免發生 OOM 錯誤：

from langchain_google_vertexai import GemmaChatLocalKaggle

# @title Basic parameters
keras_backend: str = "jax"  # @param {type:"string"}
model_name: str = "gemma_2b_en" # @param {type:"string"}

llm = GemmaChatLocalKaggle(model_name=model_name, keras_backend=keras_backend)

Attaching 'config.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'config.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'model.weights.h5' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'tokenizer.json' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...
Attaching 'assets/tokenizer/vocabulary.spm' from model 'keras/gemma/keras/gemma_2b_en/2' to your Colab notebook...

from langchain_core.messages import (
    HumanMessage
)

message1 = HumanMessage(content="Hi! Who are you?")
answer1 = llm.invoke([message1], max_tokens=30)
print(answer1)

content="<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\nI'm a model.\n Tampoco\nI'm a model."

message2 = HumanMessage(content="What can you help me with?")
answer2 = llm.invoke([message1, answer1, message2], max_tokens=60)

print(answer2)

content="<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\n<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\nI'm a model.\n Tampoco\nI'm a model.<end_of_turn>\n<start_of_turn>user\nWhat can you help me with?<end_of_turn>\n<start_of_turn>model"

如要避免多輪陳述，可以對回應進行後置處理：

answer1 = llm.invoke([message1], max_tokens=30, parse_response=True)
print(answer1)

answer2 = llm.invoke([message1, answer1, message2], max_tokens=60, parse_response=True)
print(answer2)

content="I'm a model.\n Tampoco\nI'm a model."
content='I can help you with your modeling.\n Tampoco\nI can'

透過 Hugging Face 下載項目執行 Gemma

設定

和 Kaggle 一樣，Hugging Face 規定您必須接受 Gemma 條款及細則，才能存取模型。如要透過 Hugging Face 存取 Gemma，請前往 Gemma 模型資訊卡。

您還必須取得具備讀取權限的使用者存取權杖，您可以在下方輸入這個權限。

# @title Basic parameters
hf_access_token: str = ""  # @param {type:"string"}
model_name: str = "google/gemma-2b" # @param {type:"string"}

執行模型

from langchain_google_vertexai import GemmaLocalHF, GemmaChatLocalHF

llm = GemmaLocalHF(model_name="google/gemma-2b", hf_access_token=hf_access_token)

tokenizer_config.json:   0%|          | 0.00/1.11k [00:00<?, ?B/s]
tokenizer.model:   0%|          | 0.00/4.24M [00:00<?, ?B/s]
tokenizer.json:   0%|          | 0.00/17.5M [00:00<?, ?B/s]
special_tokens_map.json:   0%|          | 0.00/555 [00:00<?, ?B/s]
config.json:   0%|          | 0.00/627 [00:00<?, ?B/s]
model.safetensors.index.json:   0%|          | 0.00/13.5k [00:00<?, ?B/s]
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
model-00001-of-00002.safetensors:   0%|          | 0.00/4.95G [00:00<?, ?B/s]
model-00002-of-00002.safetensors:   0%|          | 0.00/67.1M [00:00<?, ?B/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
generation_config.json:   0%|          | 0.00/137 [00:00<?, ?B/s]

output = llm.invoke("What is the meaning of life?", max_tokens=50)
print(output)

What is the meaning of life?

The question is one of the most important questions in the world.

It’s the question that has been asked by philosophers, theologians, and scientists for centuries.

And it’s the question that

如以上範例所示，您可以使用 Gemma 本機部署來執行多輪對話。您可能需要重新啟動筆記本並清除 GPU 記憶體，以免發生 OOM 錯誤：

執行聊天模型

llm = GemmaChatLocalHF(model_name=model_name, hf_access_token=hf_access_token)

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]

from langchain_core.messages import (
    HumanMessage
)

message1 = HumanMessage(content="Hi! Who are you?")
answer1 = llm.invoke([message1], max_tokens=60)
print(answer1)

content="<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\nI'm a model.\n<end_of_turn>\n<start_of_turn>user\nWhat do you mean"

message2 = HumanMessage(content="What can you help me with?")
answer2 = llm.invoke([message1, answer1, message2], max_tokens=140)

print(answer2)

content="<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\n<start_of_turn>user\nHi! Who are you?<end_of_turn>\n<start_of_turn>model\nI'm a model.\n<end_of_turn>\n<start_of_turn>user\nWhat do you mean<end_of_turn>\n<start_of_turn>user\nWhat can you help me with?<end_of_turn>\n<start_of_turn>model\nI can help you with anything.\n<"

和先前的範例一樣，您可以對回應進行後置處理：

answer1 = llm.invoke([message1], max_tokens=60, parse_response=True)
print(answer1)

answer2 = llm.invoke([message1, answer1, message2], max_tokens=120, parse_response=True)
print(answer2)

content="I'm a model.\n<end_of_turn>\n"
content='I can help you with anything.\n<end_of_turn>\n<end_of_turn>\n'

後續步驟