chat.mdx

Make chat calls using your LLM.

Parameters

The llm.chat method can have the following parameters.

Parameter	Type	Description
input	str	The input message to send to the chat model.
is_stream	bool	The temperature parameter for the model.
**kwargs	dict	Additional parameters to pass to the chat model.

Refer to your provider-specific documentation for additional kwargs you can use.

Returns

Output	Type	Description
ChatCompletion	object	A chat completion object in the OpenAI format + metrics computed by LLMstudio.

Usage

Here's how to use .chat() to make calls to your LLM.

Start by importing LLM. ```python from llmstudio import LLM ``` Set up an LLM from your desired provider. ```python llm = LLM('openai/gpt-4o') ``` Create your message. Your message can be a simple `string` or a message in the `OpenAI format`.

   <Tabs>
        <Tab title="String format">
            ```python
            message = "Hello, how are you today?"
            ```
        </Tab>
        <Tab title="OpenAI format">
            ```python
            message = [
            {"role": "system", "content": "You are a helpfull assistant."},
            {"role": "user", "content": "Hello, how are you today?"}
            ]
            ```
        </Tab>
    </Tabs> 

</Step>
<Step>

    <Tabs>
        <Tab title="Non-stream response">
            Get your response.
            ```python
            response = llm.chat(message)
            ```

            Vizualize your response.
             ```python
            print(response)
            ```
        </Tab>
        <Tab title="Stream response">
            Get your response.
            ```python
            response = llm.chat(message, is_stream = True)
            ```

            Vizualize your response.
             ```python
            for chunk in response:
                print(chunk)
            ```
        </Tab>
    </Tabs> 

    <Check>You are done chating with your **LLMstudio LLM**!</Check>
</Step>