Deepinfra

!pip install -qU portkey-ai openai

from openai import OpenAI

from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

from google.colab import userdata

client = OpenAI(

    api_key= userdata.get('DEEPINFRA_API_KEY'), ## replace it your Mistral API key

    base_url=PORTKEY_GATEWAY_URL,

    default_headers=createHeaders(

        provider="deepinfra",

        api_key= userdata.get('PORTKEY_API_KEY'), ## replace it your Portkey API key

    )

)

chat_complete = client.chat.completions.create(

    model="meta-llama/Meta-Llama-3-70B-Instruct",

    messages=[{"role": "user",

               "content": "Who are you?"}],

)

print(chat_complete.choices[0].message.content)

Nice to meet you! I'm LLaMA, a large language model trained by a team of researcher at Meta AI. My primary function is to generate human-like responses to a wide range of questions and topics, from science and history to entertainment and culture.

I'm not a human, but rather an artificial intelligence designed to simulate conversation and answer questions to the best of my knowledge. I've been trained on a massive dataset of text from the internet and can respond in multiple languages.

I can help with things like:

* Answering questions on a variety of topics

* Generating text on a given topic or subject

* Translating text from one language to another

* Summarizing long pieces of text into shorter, more digestible versions

* Offering suggestions or ideas for creative projects

* Even just having a conversation and chatting about your day or interests!

So, what's on your mind? Want to chat about something specific or just see where the conversation takes us?