File size: 1,498 Bytes
3cdb7c9 222fb60 3cdb7c9 3330fc9 3cdb7c9 3330fc9 3cdb7c9 3330fc9 3cdb7c9 3330fc9 3cdb7c9 3330fc9 3cdb7c9 |
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 |
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoProcessor
from PIL import Image
import requests
import torch
# Define the FastAPI app
app = FastAPI()
# Initialize model and processor at startup
processor = AutoProcessor.from_pretrained('allenai/Molmo-7B-D-0924', trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained('allenai/Molmo-7B-D-0924', trust_remote_code=True)
# Move the model to GPU if available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
# Request body structure
class GenerateRequest(BaseModel):
image_url: str
text_input: str
# API root endpoint
@app.get("/")
def root():
return {"message": "Molmo-7B-D API is up and running!"}
# Text generation endpoint
@app.post("/generate/")
def generate_text(request: GenerateRequest):
try:
# Fetch image from URL
response = requests.get(request.image_url, stream=True)
image = Image.open(response.raw)
# Preprocess inputs
inputs = processor(images=[image], text=request.text_input, return_tensors="pt").to(device)
# Generate text
output_ids = model.generate(inputs["input_ids"], max_new_tokens=200)
generated_text = processor.tokenizer.decode(output_ids[0], skip_special_tokens=True)
return {"generated_text": generated_text}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
|