add app

app.py

@@ -0,0 +1,166 @@
+import os
+import datetime
+import json
+import base64
+from PIL import Image
+import gradio as gr
+import hashlib
+import requests
+from utils import build_logger
+import io
+
+LOGDIR = "log"
+logger = build_logger("otter", LOGDIR)
+
+no_change_btn = gr.Button.update()
+enable_btn = gr.Button.update(interactive=True)
+disable_btn = gr.Button.update(interactive=False)
+
+
+def decode_image(encoded_image: str) -> Image:
+    decoded_bytes = base64.b64decode(encoded_image.encode("utf-8"))
+    buffer = io.BytesIO(decoded_bytes)
+    image = Image.open(buffer)
+    return image
+
+
+def encode_image(image: Image.Image, format: str = "PNG") -> str:
+    with io.BytesIO() as buffer:
+        image.save(buffer, format=format)
+        encoded_image = base64.b64encode(buffer.getvalue()).decode("utf-8")
+    return encoded_image
+
+
+def get_conv_log_filename():
+    t = datetime.datetime.now()
+    name = os.path.join(LOGDIR, f"{t.year}-{t.month:02d}-{t.day:02d}-conv.json")
+    return name
+
+
+def get_conv_image_dir():
+    name = os.path.join(LOGDIR, "images")
+    os.makedirs(name, exist_ok=True)
+    return name
+
+
+def get_image_name(image, image_dir=None):
+    buffer = io.BytesIO()
+    image.save(buffer, format="PNG")
+    image_bytes = buffer.getvalue()
+    md5 = hashlib.md5(image_bytes).hexdigest()
+
+    if image_dir is not None:
+        image_name = os.path.join(image_dir, md5 + ".png")
+    else:
+        image_name = md5 + ".png"
+
+    return image_name
+
+
+def resize_image(image, max_size):
+    width, height = image.size
+    aspect_ratio = float(width) / float(height)
+
+    if width > height:
+        new_width = max_size
+        new_height = int(new_width / aspect_ratio)
+    else:
+        new_height = max_size
+        new_width = int(new_height * aspect_ratio)
+
+    resized_image = image.resize((new_width, new_height))
+    return resized_image
+
+def http_bot(image_input, text_input, request: gr.Request):
+    logger.info(f"http_bot. ip: {request.client.host}")
+    print(f"Prompt request: {text_input}")
+
+    base64_image_str = encode_image(image_input)    
+
+    payload = {
+        "content": [
+            {
+                "prompt": text_input,
+                "image": base64_image_str,
+            }
+        ],
+        "token": "sk-OtterHD",
+    }
+
+    print(
+        "request: ",
+        {
+            "prompt": text_input,
+            "image": base64_image_str[:10],
+        },
+    )
+
+    url = "http://10.128.0.40:8890/app/otter"
+    headers = {"Content-Type": "application/json"}
+
+    response = requests.post(url, headers=headers, data=json.dumps(payload))
+    results = response.json()
+    print("response: ", {"result": results["result"]})
+    return results["result"]
+
+title = """
+# OTTER-HD: A High-Resolution Multi-modality Model
+[[Otter Codebase]](https://github.com/Luodian/Otter) [[Paper]]() [[Checkpoints & Benchmarks]](https://huggingface.co/Otter-AI) 
+         
+"""
+
+css = """
+  #mkd {
+    height: 1000px; 
+    overflow: auto; 
+    border: 1px solid #ccc; 
+  }
+"""
+
+if __name__ == "__main__":
+    with gr.Blocks(css=css) as demo:
+        gr.Markdown(title)
+        dialog_state = gr.State()
+        input_state = gr.State()
+        with gr.Tab("Ask a Question"):
+            with gr.Row(equal_height=True):
+                with gr.Column(scale=2):
+                    image_input = gr.Image(label="Upload a High-Res Image", type="pil").style(height=600)
+                with gr.Column(scale=1):
+                    vqa_output = gr.Textbox(label="Output").style(height=600)
+            text_input = gr.Textbox(label="Ask a Question")
+
+            vqa_btn = gr.Button("Send It")
+
+            gr.Examples(
+                [
+                    [
+                        "./assets/IMG_00095.png",
+                        "How many camels are inside this image?",
+                    ],
+                    [
+                        "./assets/IMG_00095.png",
+                        "How many people are inside this image?",
+                    ],
+                    [
+                        "./assets/IMG_00012.png",
+                        "How many apples are there?",
+                    ],
+                    # ["./assets/./IMG_00012.png", "How many apples are there? Count them row by row."],
+                    [
+                        "./assets/IMG_00080.png",
+                        "What is this and where is it from?",
+                    ],
+                    [
+                        "./assets/IMG_00094.png",
+                        "What's important on this website?",
+                    ],
+                ],
+                inputs=[image_input, text_input],
+                outputs=[vqa_output],
+                fn=http_bot,
+                label="Click on any Examples below👇",
+            )
+        vqa_btn.click(fn=http_bot, inputs=[image_input, text_input], outputs=vqa_output)
+
+    demo.launch()

utils.py

@@ -0,0 +1,82 @@
+import logging
+import logging.handlers
+import os
+import sys
+
+handler = None
+
+
+def build_logger(logger_name, logger_dir):
+    global handler
+
+    formatter = logging.Formatter(
+        fmt="%(asctime)s | %(levelname)s | %(name)s | %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+
+    # Set the format of root handlers
+    if not logging.getLogger().handlers:
+        logging.basicConfig(level=logging.INFO)
+    logging.getLogger().handlers[0].setFormatter(formatter)
+
+    # Redirect stdout and stderr to loggers
+    stdout_logger = logging.getLogger("stdout")
+    stdout_logger.setLevel(logging.INFO)
+    sl = StreamToLogger(stdout_logger, logging.INFO)
+    sys.stdout = sl
+
+    stderr_logger = logging.getLogger("stderr")
+    stderr_logger.setLevel(logging.ERROR)
+    sl = StreamToLogger(stderr_logger, logging.ERROR)
+    sys.stderr = sl
+
+    # Get logger
+    logger = logging.getLogger(logger_name)
+    logger.setLevel(logging.INFO)
+
+    # Add a file handler for all loggers
+    if handler is None:
+        os.makedirs(logger_dir, exist_ok=True)
+        filename = os.path.join(logger_dir, logger_name + ".log")
+        handler = logging.handlers.TimedRotatingFileHandler(filename, when="D", utc=True)
+        handler.setFormatter(formatter)
+
+        for name, item in logging.root.manager.loggerDict.items():
+            if isinstance(item, logging.Logger):
+                item.addHandler(handler)
+
+    return logger
+
+
+class StreamToLogger(object):
+    """
+    Fake file-like stream object that redirects writes to a logger instance.
+    """
+
+    def __init__(self, logger, log_level=logging.INFO):
+        self.terminal = sys.stdout
+        self.logger = logger
+        self.log_level = log_level
+        self.linebuf = ""
+
+    def __getattr__(self, attr):
+        return getattr(self.terminal, attr)
+
+    def write(self, buf):
+        temp_linebuf = self.linebuf + buf
+        self.linebuf = ""
+        for line in temp_linebuf.splitlines(True):
+            # From the io.TextIOWrapper docs:
+            #   On output, if newline is None, any '\n' characters written
+            #   are translated to the system default line separator.
+            # By default sys.stdout.write() expects '\n' newlines and then
+            # translates them so this is still cross platform.
+            if line[-1] == "\n":
+                self.logger.log(self.log_level, line.rstrip())
+            else:
+                self.linebuf += line
+
+    def flush(self):
+        if self.linebuf != "":
+            self.logger.log(self.log_level, self.linebuf.rstrip())
+        self.linebuf = ""