File size: 3,881 Bytes
8d7815c
 
 
 
 
 
 
 
 
 
 
 
67dacdd
8d7815c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb63b63
8d7815c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97d9864
8d7815c
 
844350c
8d7815c
 
61afd29
 
3ef0259
8d7815c
 
 
 
66b8012
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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
import argparse
import os
import random
import io
from PIL import Image
import numpy as np
import torch
import torch.backends.cudnn as cudnn

from minigpt4.common.config import Config
from minigpt4.common.dist_utils import get_rank
from minigpt4.common.registry import registry
from minigpt4.conversation.conversation import Chat, CONV_VISION
from fastapi import FastAPI, HTTPException, File, UploadFile,Form
from fastapi.responses import RedirectResponse
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from PIL import Image
import io
import uvicorn
# imports modules for registration
from minigpt4.datasets.builders import *
from minigpt4.models import *
from minigpt4.processors import *
from minigpt4.runners import *
from minigpt4.tasks import *


def parse_args():
    parser = argparse.ArgumentParser(description="Demo")
    parser.add_argument("--cfg-path", type=str, default='eval_configs/minigpt4_eval.yaml',
                        help="path to configuration file.")
    parser.add_argument(
        "--options",
        nargs="+",
        help="override some settings in the used config, the key-value pair "
             "in xxx=yyy format will be merged into config file (deprecate), "
             "change to --cfg-options instead.",
    )
    args = parser.parse_args()
    return args


def setup_seeds(config):
    seed = config.run_cfg.seed + get_rank()

    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)

    cudnn.benchmark = False
    cudnn.deterministic = True


# ========================================
#             Model Initialization
# ========================================

SHARED_UI_WARNING = f'''### [NOTE] It is possible that you are waiting in a lengthy queue.

You can duplicate and use it with a paid private GPU.

<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/Vision-CAIR/minigpt4?duplicate=true"><img style="margin-top:0;margin-bottom:0" src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-xl-dark.svg" alt="Duplicate Space"></a>

Alternatively, you can also use the demo on our [project page](https://minigpt-4.github.io).
'''

print('Initializing Chat')
cfg = Config(parse_args())

model_config = cfg.model_cfg
model_cls = registry.get_model_class(model_config.arch)
model = model_cls.from_config(model_config).to('cuda:0')

vis_processor_cfg = cfg.datasets_cfg.cc_align.vis_processor.train
vis_processor = registry.get_processor_class(vis_processor_cfg.name).from_config(vis_processor_cfg)
chat = Chat(model, vis_processor)
print('Initialization Finished')

# ========================================
#             Gradio Setting
# ========================================

app = FastAPI()
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],  # Replace "*" with your frontend domain
    allow_credentials=True,
    allow_methods=["GET", "POST"],
    allow_headers=["*"],
)


class Item(BaseModel):
    gr_img: UploadFile = File(..., description="Image file")
    text_input: str = None

@app.get("/")
async def root():
    return RedirectResponse(url="/docs")

@app.post("/process/")
async def process_item(
        file: UploadFile = File(...),
        prompt: str = Form(...),
):
    chat_state = CONV_VISION.copy()
    img_list = []
    chatbot=[]
    pil_image = Image.open(io.BytesIO(await file.read()))
    chat.upload_img(pil_image, chat_state, img_list)
    chat.ask(prompt, chat_state)
    chatbot = chatbot + [[prompt, None]]
    llm_message = chat.answer(conv=chat_state, img_list=img_list, max_new_tokens=300, num_beams=1, temperature=1,
                max_length=2000)[0]
    chatbot[-1][1] = llm_message
    return chatbot


if __name__ == "__main__":
    # Run the FastAPI app with Uvicorn
    uvicorn.run("main:app", host="0.0.0.0", port=7860)