# Chat

{% tabs %}
{% tab title="Multimodal \[Text, Audio]" %}

```python
import base64
from aibrary import AiBrary

aibrary = AiBrary()

# Function to encode the image
def encode_file(path):
    with open(path, "rb") as file:
        return base64.b64encode(file.read()).decode("utf-8")

# Getting the base64 string
english_audio_base64 = encode_file("tests/assets/file.mp3")
return aibrary.chat.completions.create(
    model="GPT-4o-Audio-Preview-2024-12-17@openai",
    modalities=["text", "audio"],
    audio={"voice": "alloy", "format": "wav"},
    messages=[
        {"role": "system", "content": "translate to persian"},
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {"data": english_audio_base64, "format": "mp3"},
                }
            ],
        },
    ],
)
```

{% endtab %}

{% tab title="Multimodal \[Text, Image]" %}

```python
from aibrary import AiBrary
aibrary = AiBrary()

# Function to encode the image
def encode_file(path):
    with open(path, "rb") as file:
        return base64.b64encode(file.read()).decode("utf-8")

# Getting the base64 string
base64_image = encode_file("tests/assets/test-image.jpg")

return aibrary.chat.completions.create(
    model="Claude-3-5-Haiku",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is in this image?",
                },
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
                },
            ],
        }
    ],
)
```

{% endtab %}

{% tab title="Chat \[Stream]" %}

```python
aibrary = AiBrary()
aibrary.chat.completions.create(
    model="Llama-3.1-Nemotron-70B-Instruct",
    messages=[
        {"role": "user", "content": "How are you today?"},
        {"role": "assistant", "content": "I'm doing great, thank you!"},
    ],
    stream=True,
)
```

{% endtab %}

{% tab title="Chat \[Non-Stream]" %}

```python
aibrary = AiBrary()
aibrary.chat.completions.create(
    model="Llama-3.1-Nemotron-70B-Instruct",
    messages=[
        {"role": "user", "content": "How are you today?"},
        {"role": "assistant", "content": "I'm doing great, thank you!"},
    ]
)
```

{% endtab %}
{% endtabs %}

{% openapi src="/files/Dw2lhls9PkqDudu910qL" path="/v0/chat/completions" method="post" %}
[openapi.json](https://2030775142-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fp4IwQOR0zSJQKAC7b7hY%2Fuploads%2F4Z0rHZNC7ipANhpX4HEf%2Fopenapi.json?alt=media\&token=525b1926-3989-474c-baed-7a15958ec382)
{% endopenapi %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aibrary.dev/chat-and-multimodal-features/chat.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.