תחילת העבודה עם Gemma ו-LangChain

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

from google.colab import auth
auth.authenticate_user()

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

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

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'

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<'

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')

# 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

from langchain_google_vertexai import GemmaLocalKaggle

# @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

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"

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'

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

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

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<"

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'