Clarifai LLM¶

使用 Clarifai 调用不同 LLM 模型的示例 Notebook¶

如果您在 colab 上打开此 Notebook，您可能需要安装 LlamaIndex 🦙。

In [ ]

%pip install llama-index-llms-clarifai

%pip install llama-index-llms-clarifai

In [ ]

!pip install llama-index

!pip install llama-index

安装 clarifai

In [ ]

!pip install clarifai

!pip install clarifai

将 clarifai PAT 设置为环境变量。

In [ ]

import os

os.environ["CLARIFAI_PAT"] = "<YOUR CLARIFAI PAT>"

import os os.environ["CLARIFAI_PAT"] = ""

导入 clarifai 包

In [ ]

from llama_index.llms.clarifai import Clarifai

from llama_index.llms.clarifai import Clarifai

从我们的模型页面根据您的偏好探索各种模型

In [ ]

# Example parameters
params = dict(
    user_id="clarifai",
    app_id="ml",
    model_name="llama2-7b-alternative-4k",
    model_url=(
        "https://clarifai.com/clarifai/ml/models/llama2-7b-alternative-4k"
    ),
)

# 示例参数 params = dict( user_id="clarifai", app_id="ml", model_name="llama2-7b-alternative-4k", model_url=( "https://clarifai.com/clarifai/ml/models/llama2-7b-alternative-4k" ), )

初始化 LLM

In [ ]

# Method:1 using model_url parameter
llm_model = Clarifai(model_url=params["model_url"])

# 方法 1：使用 model_url 参数 llm_model = Clarifai(model_url=params["model_url"])

In [ ]

# Method:2 using model_name, app_id & user_id parameters
llm_model = Clarifai(
    model_name=params["model_name"],
    app_id=params["app_id"],
    user_id=params["user_id"],
)

# 方法 2：使用 model_name, app_id & user_id 参数 llm_model = Clarifai( model_name=params["model_name"], app_id=params["app_id"], user_id=params["user_id"], )

调用 complete 函数

In [ ]

llm_reponse = llm_model.complete(
    prompt="write a 10 line rhyming poem about science"
)

llm_reponse = llm_model.complete( prompt="write a 10 line rhyming poem about science" )

In [ ]

print(llm_reponse)

print(llm_reponse)

.
Science is fun, it's true!
From atoms to galaxies, it's all new!
With experiments and tests, we learn so fast,
And discoveries come from the past.
It helps us understand the world around,
And makes our lives more profound.
So let's embrace this wondrous art,
And see where it takes us in the start!

调用 chat 函数

In [ ]

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="user", content="write about climate change in 50 lines")
]
Response = llm_model.chat(messages)

from llama_index.core.llms import ChatMessage messages = [ ChatMessage(role="user", content="write about climate change in 50 lines") ] Response = llm_model.chat(messages)

In [ ]

print(Response)

print(Response)

user:  or less.
Climate change is a serious threat to our planet and its inhabitants. Rising temperatures are causing extreme weather events, such as hurricanes, droughts, and wildfires. Sea levels are rising, threatening coastal communities and ecosystems. The melting of polar ice caps is disrupting global navigation and commerce. Climate change is also exacerbating air pollution, which can lead to respiratory problems and other health issues. It's essential that we take action now to reduce greenhouse gas emissions and transition to renewable energy sources to mitigate the worst effects of climate change.

使用推理参数¶

或者，您可以使用推理参数调用模型。

In [ ]

# Here is an inference parameter example for GPT model.
inference_params = dict(temperature=str(0.3), max_tokens=20)

# 以下是 GPT 模型的推理参数示例。 inference_params = dict(temperature=str(0.3), max_tokens=20)

In [ ]

llm_reponse = llm_model.complete(
    prompt="What is nuclear fission and fusion?",
    inference_params=params,
)

llm_reponse = llm_model.complete( prompt="What is nuclear fission and fusion?", inference_params=params, )

In [ ]

messages = [ChatMessage(role="user", content="Explain about the big bang")]
Response = llm_model.chat(messages, inference_params=params)

messages = [ChatMessage(role="user", content="Explain about the big bang")] Response = llm_model.chat(messages, inference_params=params)