OpenOrca

from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")

label2id = {
    "Bénéfices professionnels": 0,
    "Contrôle et contentieux": 1,
    "Dispositifs transversaux": 2,
    "Fiscalité des entreprises": 3,
    "Patrimoine et enregistrement": 4,
    "Revenus particuliers": 5,
    "Revenus patrimoniaux": 6,
    "Taxes sur la consommation": 7
}
	
id2label = {
    0: "Bénéfices professionnels",
    1: "Contrôle et contentieux",
    2: "Dispositifs transversaux",
    3: "Fiscalité des entreprises",
    4: "Patrimoine et enregistrement",
    5: "Revenus particuliers",
    6: "Revenus patrimoniaux",
    7: "Taxes sur la consommation"
}

from huggingface_hub import InferenceClient

client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")

messages = [
    {
        "role": "user",
        "content": "I saw a puppy a cat and a raccoon during my bike ride in the park. What did I saw and when?",
    },
]

response_format = {
    "type": "json",
    "value": {
        "properties": {
            "location": {"type": "string"},
            "activity": {"type": "string"},
            "animals_seen": {"type": "integer", "minimum": 1, "maximum": 5},
            "animals": {"type": "array", "items": {"type": "string"}},
        },
        "required": ["location", "activity", "animals_seen", "animals"],
    },
}

response = client.chat_completion(
    messages=messages,
    response_format=response_format,
    max_tokens=500,
)

print(response.choices[0].message.content)

response = client.chat.completions.create(
     model="gpt-3.5-turbo-0125",
     messages=[...],
     response_format={"type": "json_object"}
)