Feat - Introducing FileInputURL SDK Type for LLM Applications

[aybruhm]

Description

This PR marks the initial implementation stage of integrating file input functionality, such as images and PDFs, into our LLM applications.

To utilize the SDK input, follow these steps:

import agenta as ag
from agenta import TextParam, FloatParam, FileInputURL

..................
# more code here
..................

ag.init(app_name="linkedin_generator", base_name="app")

..................
# more code here
..................

@ag.entrypoint
def generate(
    attachment_url: FileInputURL,
) -> dict:
    # handle attachment_url

Related Issue

Closes first issue in #944

[mmabrouk]

Thanks for the PR @aybruhm !
Can you please create an example application that uses an image based on openai

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4-vision-preview",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What’s in this image?"},
                {
                    "type": "image_url",
                    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                },
            ],
        }
    ],
    max_tokens=300,
)

print(response.choices[0])

(see https://platform.openai.com/docs/api-reference/chat/create for documentation)