LLM
Azure
Interact with your Azure models using LLM.
Parameters
An Azure LLM interface can have the following parameters:
Parameter | Type | Description |
---|---|---|
temperature | float | The temperature parameter for the model. |
max_tokens | int | The maximum number of tokens to generate. |
top_p | float | The top-p parameter for the model. |
frequency_penalty | float | The frequency penalty parameter for the model. |
presence_penalty | float | The presence penalty parameter for the model. |
Usage
Here is how you setup an interface to interact with your Azure models.
1
Create a config.yaml
file in the same directory as your code.
- π src
- π PythonCode.py
- π PyNotebook.ipynb
- π config.yaml
2
Define your Azure OpenAI provider and models inside the config.yaml
file.
providers:
azure:
id: azure
name: Azure
chat: true
embed: true
models:
YOUR_MODEL: <- Replace with your model name
mode: chat
max_tokens: ...
input_token_cost: ...
output_token_cost: ...
If you are not sure, you can leave
max_tokens
, input_tokens
and the other parameters as 03
Create your llm instance.
llm = LLM('azure/YOUR_MODEL',
api_key = YOUR_API_KEY,
api_endpoint = YOUR_ENDPOINT,
api_version = YOUR_API_VERSION)
4
Optional: You can add your parameters as follows:
llm = LLM('azure/model',
temperature= ...,
max_tokens= ...,
top_p= ...,
frequency_penalty= ...,
presence_penalty= ...)
You are done setting up your Azure LLM!