from svector import SVECTOR

client = SVECTOR()

# Analyze image from URL
response = client.vision.analyze_from_url(
    image_url="https://example.com/image.jpg",
    prompt="What do you see in this image?",
    detail="high"
)
print(response.analysis)

# Using responses.create format
response = client.responses.create(
    model="spec-3-turbo",
    input=[{
        "role": "user",
        "content": [
            {"type": "input_text", "text": "what's in this image?"},
            {
                "type": "input_image",
                "image_url": "https://example.com/image.jpg",
            },
        ],
    }],
)
print(response.output_text)

import base64

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

# Getting the Base64 string
base64_image = encode_image("path_to_your_image.jpg")

response = client.responses.create(
    model="spec-3-turbo",
    input=[
        {
            "role": "user",
            "content": [
                { "type": "input_text", "text": "what's in this image?" },
                {
                    "type": "input_image",
                    "image_url": f"data:image/jpeg;base64,{base64_image}",
                },
            ],
        }
    ],
)
print(response.output_text)

# Function to create a file with the Files API
def create_file(file_path):
    with open(file_path, "rb") as file_content:
        result = client.files.create(
            file=file_content,
            purpose="vision",
        )
        return result["file_id"]

# Getting the file ID
file_id = create_file("path_to_your_image.jpg")

response = client.responses.create(
    model="spec-3-turbo",
    input=[{
        "role": "user",
        "content": [
            {"type": "input_text", "text": "what's in this image?"},
            {
                "type": "input_image",
                "file_id": file_id,
            },
        ],
    }],
)
print(response.output_text)

response = client.vision.extract_text(
    image_url="https://example.com/document.jpg"
)
print(f"Extracted text: {response.analysis}")

response = client.vision.detect_objects(
    image_url="https://example.com/scene.jpg",
    object_types=["cars", "people", "buildings"]
)
print(f"Detected objects: {response.analysis}")

images = [
    {"url": "https://example.com/image1.jpg"},
    {"url": "https://example.com/image2.jpg"}
]

response = client.vision.compare_images(
    images=images,
    prompt="Compare these images and describe differences"
)
print(response.analysis)

result = client.vision.analyze_with_confidence(
    image_url="https://example.com/image.jpg",
    prompt="Analyze this image"
)
print(f"Analysis: {result['analysis']}")
print(f"Confidence: {result['confidence']}%")

images = [
    {"image_url": "https://example.com/1.jpg", "prompt": "Describe this"},
    {"image_url": "https://example.com/2.jpg", "prompt": "What's here?"}
]

results = client.vision.batch_analyze(images, delay=1.0)
for i, result in enumerate(results):
    print(f"Image {i+1}: {result['analysis']}")

response = client.conversations.create(
    model="spec-3-turbo",
    instructions="You are a helpful AI assistant.",
    input="Explain quantum computing in simple terms."
)
print(response.output)

stream = client.conversations.create_stream(
    model="spec-3-turbo",
    instructions="You are a creative writer.",
    input="Write a short poem about technology."
)

for event in stream:
    if not event.done:
        print(event.content, end="", flush=True)

response = client.chat.create(
    model="spec-3-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is machine learning?"}
    ]
)
print(response["choices"][0]["message"]["content"])

with open("document.pdf", "rb") as f:
    file_response = client.files.create(
        file=f,
        purpose="default"
    )
print(f"File ID: {file_response['file_id']}")

from svector import APIError, AuthenticationError, RateLimitError

try:
    response = client.vision.analyze_from_url(
        image_url="https://example.com/image.jpg"
    )
except AuthenticationError:
    print("Invalid API key")
except RateLimitError:
    print("Rate limit exceeded")
except APIError as e:
    print(f"API error: {e}")

from svector import encode_image, create_data_url

# Encode image to base64
base64_data = encode_image("path/to/image.jpg")

# Create data URL
data_url = create_data_url(base64_data, "image/jpeg")