File size: 1,712 Bytes
3722851
70be430
 
3722851
62f1e4c
 
 
3722851
f82bbf4
5332848
 
 
e414d7e
3e3cb44
3722851
 
 
 
 
70be430
 
3722851
62f1e4c
 
 
 
 
 
 
3722851
62f1e4c
 
 
 
 
 
3722851
62f1e4c
 
 
3722851
62f1e4c
 
 
 
 
 
 
3722851
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50

from fastapi import FastAPI, File, UploadFile
from fastapi.responses import JSONResponse
from transformers import AutoProcessor, AutoModelForCausalLM
import torch
from PIL import Image
import io
import os

os.environ["HF_HOME"] = "/app/.cache"
os.environ["HF_DATASETS_CACHE"] = "/app/.cache"
os.environ["TRANSFORMERS_CACHE"] = "/app/.cache"
app = FastAPI()

MODEL_NAME = os.getenv("MODEL_NAME", "lmms-lab/LLaVA-OneVision-1.5-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME, torch_dtype="auto", device_map="auto", trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(MODEL_NAME, trust_remote_code=True)

@app.post("/analyze-image")
async def analyze_image(file: UploadFile = File(...), prompt: str = "Describe this image."):
    image_bytes = await file.read()
    image = Image.open(io.BytesIO(image_bytes))
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": image},
                {"type": "text", "text": prompt},
            ],
        }
    ]
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=[image],
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to(model.device)
    generated_ids = model.generate(**inputs, max_new_tokens=1024)
    generated_ids_trimmed = [
        out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
    ]
    output_text = processor.batch_decode(
        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
    )
    return JSONResponse(content={"result": output_text[0]})