diff --git a/README.md b/README.md
index b88c3d8..19adf9b 100644
--- a/README.md
+++ b/README.md
@@ -1814,12 +1814,13 @@ Click here to try out the online demo of [MiniCPM-o 2.6](https://minicpm-omni-we
 
 ### Local WebUI Demo <!-- omit in toc --> 
   
-You can easily build your own local WebUI demo using the following commands, experience real-time streaming voice/video call. 
+You can easily build your own local WebUI demo using the following commands.
 
-Please ensure that `transformers==4.44.2` is installed, as other versions may have compatibility issues. We are investigating this issue.
+Please ensure that `transformers==4.44.2` is installed, as other versions may have compatibility issues.
 
 If you are using an older version of PyTorch, you might encounter this issue `"weight_norm_fwd_first_dim_kernel" not implemented for 'BFloat16'`, Please add `self.minicpmo_model.tts.float()` during the model initialization.
 
+**For real-time voice/video call demo:**
 1. launch model server:
 ```shell
 pip install -r requirements_o2.6.txt
@@ -1843,6 +1844,14 @@ bash ./make_ssl_cert.sh  # output key.pem and cert.pem
 pnpm install  # install requirements
 pnpm run dev  # start server
 ```
+Open `https://localhost:8088/` in browser and enjoy the real-time voice/video call.
+
+**For chatbot demo:**
+```shell
+pip install -r requirements_o2.6.txt
+
+python web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py
+```
 
 ## Inference
 
@@ -1860,8 +1869,7 @@ pnpm run dev  # start server
 
 ### Multi-turn Conversation
 
-Please ensure that `transformers==4.44.2` is installed, as other versions may have compatibility issues.
-
+Please ensure that `transformers==4.44.2` is installed, as other versions may have compatibility issues. We are investigating this issue.
 ```shell
 pip install -r requirements_o2.6.txt
 ```
diff --git a/README_zh.md b/README_zh.md
index c8c696c..6924e22 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -1802,8 +1802,9 @@ MiniCPM-o 2.6 可以通过多种方式轻松使用：(1) [llama.cpp](https://git
 
 ### 本地 WebUI Demo <!-- omit in toc --> 
 
-您可以使用以下命令轻松构建自己的本地 WebUI Demo, 体验实时流式视频/语音通话。更详细的部署教程请参考[文档](https://modelbest.feishu.cn/wiki/RnjjwnUT7idMSdklQcacd2ktnyN)。
+您可以使用以下命令轻松构建自己的本地 WebUI Demo。更详细的部署教程请参考[文档](https://modelbest.feishu.cn/wiki/RnjjwnUT7idMSdklQcacd2ktnyN)。
 
+**实时流式视频/语音通话demo:**
 1. 启动model server:
 ```shell
 pip install -r requirements_o2.6.txt
@@ -1828,6 +1829,14 @@ bash ./make_ssl_cert.sh  # output key.pem and cert.pem
 pnpm install  # install requirements
 pnpm run dev  # start server
 ```
+浏览器打开`https://localhost:8088/`，开始体验实时流式视频/语音通话.
+
+**Chatbot图文对话demo:**
+```shell
+pip install -r requirements_o2.6.txt
+
+python web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py
+```
 
 
 ## 推理
diff --git a/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py b/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py
new file mode 100644
index 0000000..b6d5026
--- /dev/null
+++ b/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py
@@ -0,0 +1,552 @@
+#!/usr/bin/env python
+# encoding: utf-8
+import torch
+import argparse
+from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+from PIL import Image
+from decord import VideoReader, cpu
+import io
+import os
+import copy
+import requests
+import base64
+import json
+import traceback
+import re
+import modelscope_studio as mgr
+
+
+# README, How to run demo on different devices
+
+# For Nvidia GPUs.
+# python chatbot_web_demo_o2.6.py
+
+
+# Argparser
+parser = argparse.ArgumentParser(description='demo')
+parser.add_argument('--model', type=str , default="openbmb/MiniCPM-o-2_6", help="huggingface model name or local path")
+parser.add_argument('--multi-gpus', action='store_true', default=False, help='use multi-gpus')
+args = parser.parse_args()
+device = "cuda"
+model_name = 'MiniCPM-o 2.6'
+
+# Load model
+model_path = args.model
+if args.multi_gpus:
+    from accelerate import load_checkpoint_and_dispatch, init_empty_weights, infer_auto_device_map
+    with init_empty_weights():
+        model = AutoModel.from_pretrained(model_path, trust_remote_code=True, attn_implementation='sdpa', torch_dtype=torch.bfloat16,
+            init_audio=False, init_tts=False)
+    device_map = infer_auto_device_map(model, max_memory={0: "10GB", 1: "10GB"},
+        no_split_module_classes=['SiglipVisionTransformer', 'Qwen2DecoderLayer'])
+    device_id = device_map["llm.model.embed_tokens"]
+    device_map["llm.lm_head"] = device_id # firtt and last layer should be in same device
+    device_map["vpm"] = device_id
+    device_map["resampler"] = device_id
+    device_id2 = device_map["llm.model.layers.26"]
+    device_map["llm.model.layers.8"] = device_id2
+    device_map["llm.model.layers.9"] = device_id2
+    device_map["llm.model.layers.10"] = device_id2
+    device_map["llm.model.layers.11"] = device_id2
+    device_map["llm.model.layers.12"] = device_id2
+    device_map["llm.model.layers.13"] = device_id2
+    device_map["llm.model.layers.14"] = device_id2
+    device_map["llm.model.layers.15"] = device_id2
+    device_map["llm.model.layers.16"] = device_id2
+    #print(device_map)
+
+    model = load_checkpoint_and_dispatch(model, model_path, dtype=torch.bfloat16, device_map=device_map)
+else:
+    model = AutoModel.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, init_audio=False, init_tts=False)
+    model = model.to(device=device)
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model.eval()
+
+
+
+
+ERROR_MSG = "Error, please retry"
+MAX_NUM_FRAMES = 64
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.webp'}
+VIDEO_EXTENSIONS = {'.mp4', '.mkv', '.mov', '.avi', '.flv', '.wmv', '.webm', '.m4v'}
+
+def get_file_extension(filename):
+    return os.path.splitext(filename)[1].lower()
+
+def is_image(filename):
+    return get_file_extension(filename) in IMAGE_EXTENSIONS
+
+def is_video(filename):
+    return get_file_extension(filename) in VIDEO_EXTENSIONS
+
+
+form_radio = {
+    'choices': ['Beam Search', 'Sampling'],
+    #'value': 'Beam Search',
+    'value': 'Sampling',
+    'interactive': True,
+    'label': 'Decode Type'
+}
+
+
+def create_component(params, comp='Slider'):
+    if comp == 'Slider':
+        return gr.Slider(
+            minimum=params['minimum'],
+            maximum=params['maximum'],
+            value=params['value'],
+            step=params['step'],
+            interactive=params['interactive'],
+            label=params['label']
+        )
+    elif comp == 'Radio':
+        return gr.Radio(
+            choices=params['choices'],
+            value=params['value'],
+            interactive=params['interactive'],
+            label=params['label']
+        )
+    elif comp == 'Button':
+        return gr.Button(
+            value=params['value'],
+            interactive=True
+        )
+
+
+def create_multimodal_input(upload_image_disabled=False, upload_video_disabled=False):
+    return mgr.MultimodalInput(
+        upload_image_button_props={'label': 'Upload Image', 'disabled': upload_image_disabled, 'file_count': 'multiple'},
+        upload_video_button_props={'label': 'Upload Video', 'disabled': upload_video_disabled, 'file_count': 'single'},
+        submit_button_props={'label': 'Submit'}
+    )
+
+
+def chat(img, msgs, ctx, params=None, vision_hidden_states=None):
+    try:
+        print('msgs:', msgs)
+        answer = model.chat(
+            image=None,
+            msgs=msgs,
+            tokenizer=tokenizer,
+            **params
+        )
+        res = re.sub(r'(<box>.*</box>)', '', answer)
+        res = res.replace('<ref>', '')
+        res = res.replace('</ref>', '')
+        res = res.replace('<box>', '')
+        answer = res.replace('</box>', '')
+        print('answer:', answer)
+        return 0, answer, None, None
+    except Exception as e:
+        print(e)
+        traceback.print_exc()
+        return -1, ERROR_MSG, None, None
+
+
+def encode_image(image):
+    if not isinstance(image, Image.Image):
+        if hasattr(image, 'path'):
+            image = Image.open(image.path).convert("RGB")
+        else:
+            image = Image.open(image.file.path).convert("RGB")
+    # resize to max_size
+    max_size = 448*16 
+    if max(image.size) > max_size:
+        w,h = image.size
+        if w > h:
+            new_w = max_size
+            new_h = int(h * max_size / w)
+        else:
+            new_h = max_size
+            new_w = int(w * max_size / h)
+        image = image.resize((new_w, new_h), resample=Image.BICUBIC)
+    return image
+    ## save by BytesIO and convert to base64
+    #buffered = io.BytesIO()
+    #image.save(buffered, format="png")
+    #im_b64 = base64.b64encode(buffered.getvalue()).decode()
+    #return {"type": "image", "pairs": im_b64}
+
+
+def encode_video(video):
+    def uniform_sample(l, n):
+        gap = len(l) / n
+        idxs = [int(i * gap + gap / 2) for i in range(n)]
+        return [l[i] for i in idxs]
+
+    if hasattr(video, 'path'):
+        vr = VideoReader(video.path, ctx=cpu(0))
+    else:
+        vr = VideoReader(video.file.path, ctx=cpu(0))
+    sample_fps = round(vr.get_avg_fps() / 1)  # FPS
+    frame_idx = [i for i in range(0, len(vr), sample_fps)]
+    if len(frame_idx)>MAX_NUM_FRAMES:
+        frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
+    video = vr.get_batch(frame_idx).asnumpy()
+    video = [Image.fromarray(v.astype('uint8')) for v in video]
+    video = [encode_image(v) for v in video]
+    print('video frames:', len(video))
+    return video
+
+
+def check_mm_type(mm_file):
+    if hasattr(mm_file, 'path'):
+        path = mm_file.path
+    else:
+        path = mm_file.file.path
+    if is_image(path):
+        return "image"
+    if is_video(path):
+        return "video"
+    return None
+
+
+def encode_mm_file(mm_file):
+    if check_mm_type(mm_file) == 'image':
+        return [encode_image(mm_file)]
+    if check_mm_type(mm_file) == 'video':
+        return encode_video(mm_file)
+    return None
+
+def make_text(text):
+    #return {"type": "text", "pairs": text} # # For remote call
+    return text
+
+def encode_message(_question):
+    files = _question.files
+    question = _question.text
+    pattern = r"\[mm_media\]\d+\[/mm_media\]"
+    matches = re.split(pattern, question)
+    message = []
+    if len(matches) != len(files) + 1:
+        gr.Warning("Number of Images not match the placeholder in text, please refresh the page to restart!")
+    assert len(matches) == len(files) + 1
+
+    text = matches[0].strip()
+    if text:
+        message.append(make_text(text))
+    for i in range(len(files)):
+        message += encode_mm_file(files[i])
+        text = matches[i + 1].strip()
+        if text:
+            message.append(make_text(text))
+    return message
+
+
+def check_has_videos(_question):
+    images_cnt = 0
+    videos_cnt = 0
+    for file in _question.files:
+        if check_mm_type(file) == "image":
+            images_cnt += 1 
+        else:
+            videos_cnt += 1
+    return images_cnt, videos_cnt 
+
+
+def count_video_frames(_context):
+    num_frames = 0
+    for message in _context:
+        for item in message["content"]:
+            #if item["type"] == "image": # For remote call
+            if isinstance(item, Image.Image):
+                num_frames += 1
+    return num_frames
+
+
+def respond(_question, _chat_bot, _app_cfg, params_form):
+    _context = _app_cfg['ctx'].copy()
+    _context.append({'role': 'user', 'content': encode_message(_question)})
+
+    images_cnt = _app_cfg['images_cnt']
+    videos_cnt = _app_cfg['videos_cnt']
+    files_cnts = check_has_videos(_question)
+    if files_cnts[1] + videos_cnt > 1 or (files_cnts[1] + videos_cnt == 1 and files_cnts[0] + images_cnt > 0):
+        gr.Warning("Only supports single video file input right now!")
+        return _question, _chat_bot, _app_cfg
+
+    if params_form == 'Beam Search':
+        params = {
+            'sampling': False,
+            'num_beams': 3,
+            'repetition_penalty': 1.2,
+            "max_new_tokens": 2048
+        }
+    else:
+        params = {
+            'sampling': True,
+            'top_p': 0.8,
+            'top_k': 100,
+            'temperature': 0.7,
+            'repetition_penalty': 1.05,
+            "max_new_tokens": 2048
+        }
+    
+    if files_cnts[1] + videos_cnt > 0:
+        params["max_inp_length"] = 4352 # 4096+256
+        params["use_image_id"] = False
+        params["max_slice_nums"] = 1 if count_video_frames(_context) > 16 else 2
+
+    code, _answer, _, sts = chat("", _context, None, params)
+
+    images_cnt += files_cnts[0]
+    videos_cnt += files_cnts[1]
+    _context.append({"role": "assistant", "content": [make_text(_answer)]}) 
+    _chat_bot.append((_question, _answer))
+    if code == 0:
+        _app_cfg['ctx']=_context
+        _app_cfg['sts']=sts
+    _app_cfg['images_cnt'] = images_cnt
+    _app_cfg['videos_cnt'] = videos_cnt
+
+    upload_image_disabled = videos_cnt > 0
+    upload_video_disabled = videos_cnt > 0 or images_cnt > 0
+    return create_multimodal_input(upload_image_disabled, upload_video_disabled), _chat_bot, _app_cfg
+
+
+def fewshot_add_demonstration(_image, _user_message, _assistant_message, _chat_bot, _app_cfg):
+    ctx = _app_cfg["ctx"]
+    message_item = []
+    if _image is not None:
+        image = Image.open(_image).convert("RGB")
+        ctx.append({"role": "user", "content": [encode_image(image), make_text(_user_message)]})
+        message_item.append({"text": "[mm_media]1[/mm_media]" + _user_message, "files": [_image]})
+    else:
+        if _user_message:
+            ctx.append({"role": "user", "content": [make_text(_user_message)]})
+            message_item.append({"text": _user_message, "files": []})
+        else:
+            message_item.append(None)
+    if _assistant_message:
+        ctx.append({"role": "assistant", "content": [make_text(_assistant_message)]})
+        message_item.append({"text": _assistant_message, "files": []})
+    else:
+        message_item.append(None)
+
+    _chat_bot.append(message_item)
+    return None, "", "", _chat_bot, _app_cfg
+
+
+def fewshot_respond(_image, _user_message, _chat_bot, _app_cfg, params_form):
+    user_message_contents = []
+    _context = _app_cfg["ctx"].copy()
+    if _image:
+        image = Image.open(_image).convert("RGB")
+        user_message_contents += [encode_image(image)]
+    if _user_message:
+        user_message_contents += [make_text(_user_message)]
+    if user_message_contents:
+        _context.append({"role": "user", "content": user_message_contents})
+
+    if params_form == 'Beam Search':
+        params = {
+            'sampling': False,
+            'num_beams': 3,
+            'repetition_penalty': 1.2,
+            "max_new_tokens": 2048
+        }
+    else:
+        params = {
+            'sampling': True,
+            'top_p': 0.8,
+            'top_k': 100,
+            'temperature': 0.7,
+            'repetition_penalty': 1.05,
+            "max_new_tokens": 2048
+        }
+    
+    code, _answer, _, sts = chat("", _context, None, params)
+
+    _context.append({"role": "assistant", "content": [make_text(_answer)]})
+
+    if _image:
+        _chat_bot.append([
+            {"text": "[mm_media]1[/mm_media]" + _user_message, "files": [_image]},
+            {"text": _answer, "files": []}        
+        ])
+    else:
+        _chat_bot.append([
+            {"text": _user_message, "files": [_image]},
+            {"text": _answer, "files": []}        
+        ])
+    if code == 0:
+        _app_cfg['ctx']=_context
+        _app_cfg['sts']=sts
+    return None, '', '', _chat_bot, _app_cfg
+
+
+def regenerate_button_clicked(_question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg, params_form):
+    if len(_chat_bot) <= 1 or not _chat_bot[-1][1]:
+        gr.Warning('No question for regeneration.')
+        return '', _image, _user_message, _assistant_message, _chat_bot, _app_cfg
+    if _app_cfg["chat_type"] == "Chat":
+        images_cnt = _app_cfg['images_cnt']
+        videos_cnt = _app_cfg['videos_cnt']
+        _question = _chat_bot[-1][0]
+        _chat_bot = _chat_bot[:-1]
+        _app_cfg['ctx'] = _app_cfg['ctx'][:-2]
+        files_cnts = check_has_videos(_question)
+        images_cnt -= files_cnts[0]
+        videos_cnt -= files_cnts[1]
+        _app_cfg['images_cnt'] = images_cnt
+        _app_cfg['videos_cnt'] = videos_cnt
+        upload_image_disabled = videos_cnt > 0
+        upload_video_disabled = videos_cnt > 0 or images_cnt > 0
+        _question, _chat_bot, _app_cfg = respond(_question, _chat_bot, _app_cfg, params_form)
+        return _question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg
+    else: 
+        last_message = _chat_bot[-1][0]
+        last_image = None
+        last_user_message = ''
+        if last_message.text:
+            last_user_message = last_message.text
+        if last_message.files:
+            last_image = last_message.files[0].file.path
+        _chat_bot = _chat_bot[:-1]
+        _app_cfg['ctx'] = _app_cfg['ctx'][:-2]
+        _image, _user_message, _assistant_message, _chat_bot, _app_cfg = fewshot_respond(last_image, last_user_message, _chat_bot, _app_cfg, params_form)
+        return _question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg
+
+
+def flushed():
+    return gr.update(interactive=True)
+
+
+def clear(txt_message, chat_bot, app_session):
+    txt_message.files.clear()
+    txt_message.text = ''
+    chat_bot = copy.deepcopy(init_conversation)
+    app_session['sts'] = None
+    app_session['ctx'] = []
+    app_session['images_cnt'] = 0
+    app_session['videos_cnt'] = 0
+    return create_multimodal_input(), chat_bot, app_session, None, '', ''
+    
+
+def select_chat_type(_tab, _app_cfg):
+    _app_cfg["chat_type"] = _tab
+    return _app_cfg
+
+
+init_conversation = [
+    [
+        None,
+        {
+            # The first message of bot closes the typewriter.
+            "text": "You can talk to me now",
+            "flushing": False
+        }
+    ],
+]
+
+
+css = """
+video { height: auto !important; }
+.example label { font-size: 16px;}
+"""
+
+introduction = """
+
+## Features:
+1. Chat with single image
+2. Chat with multiple images
+3. Chat with video
+4. In-context few-shot learning
+
+Click `How to use` tab to see examples.
+"""
+
+
+with gr.Blocks(css=css) as demo:
+    with gr.Tab(model_name):
+        with gr.Row():
+            with gr.Column(scale=1, min_width=300):
+                gr.Markdown(value=introduction)
+                params_form = create_component(form_radio, comp='Radio')
+                regenerate = create_component({'value': 'Regenerate'}, comp='Button')
+                clear_button = create_component({'value': 'Clear History'}, comp='Button')
+
+            with gr.Column(scale=3, min_width=500):
+                app_session = gr.State({'sts':None,'ctx':[], 'images_cnt': 0, 'videos_cnt': 0, 'chat_type': 'Chat'})
+                chat_bot = mgr.Chatbot(label=f"Chat with {model_name}", value=copy.deepcopy(init_conversation), height=600, flushing=False, bubble_full_width=False)
+                
+                with gr.Tab("Chat") as chat_tab:
+                    txt_message = create_multimodal_input()
+                    chat_tab_label = gr.Textbox(value="Chat", interactive=False, visible=False)
+
+                    txt_message.submit(
+                        respond,
+                        [txt_message, chat_bot, app_session, params_form], 
+                        [txt_message, chat_bot, app_session]
+                    )
+
+                with gr.Tab("Few Shot") as fewshot_tab:
+                    fewshot_tab_label = gr.Textbox(value="Few Shot", interactive=False, visible=False)
+                    with gr.Row():
+                        with gr.Column(scale=1):
+                            image_input = gr.Image(type="filepath", sources=["upload"])
+                        with gr.Column(scale=3):
+                            user_message = gr.Textbox(label="User")
+                            assistant_message = gr.Textbox(label="Assistant")
+                            with gr.Row():
+                                add_demonstration_button = gr.Button("Add Example")
+                                generate_button = gr.Button(value="Generate", variant="primary")
+                    add_demonstration_button.click(
+                        fewshot_add_demonstration,
+                        [image_input, user_message, assistant_message, chat_bot, app_session],
+                        [image_input, user_message, assistant_message, chat_bot, app_session]
+                    )
+                    generate_button.click(
+                        fewshot_respond,
+                        [image_input, user_message, chat_bot, app_session, params_form],
+                        [image_input, user_message, assistant_message, chat_bot, app_session]
+                    )
+
+                chat_tab.select(
+                    select_chat_type,
+                    [chat_tab_label, app_session],
+                    [app_session]
+                )
+                chat_tab.select( # do clear
+                    clear,
+                    [txt_message, chat_bot, app_session],
+                    [txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
+                )
+                fewshot_tab.select(
+                    select_chat_type,
+                    [fewshot_tab_label, app_session],
+                    [app_session]
+                )
+                fewshot_tab.select( # do clear
+                    clear,
+                    [txt_message, chat_bot, app_session],
+                    [txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
+                )
+                chat_bot.flushed(
+                    flushed,
+                    outputs=[txt_message]
+                )
+                regenerate.click(
+                    regenerate_button_clicked,
+                    [txt_message, image_input, user_message, assistant_message, chat_bot, app_session, params_form],
+                    [txt_message, image_input, user_message, assistant_message, chat_bot, app_session]
+                )
+                clear_button.click(
+                    clear,
+                    [txt_message, chat_bot, app_session],
+                    [txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
+                )
+
+    with gr.Tab("How to use"):
+        with gr.Column():
+            with gr.Row():
+                image_example = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/m_bear2.gif", label='1. Chat with single or multiple images', interactive=False, width=400, elem_classes="example")
+                example2 = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/video2.gif", label='2. Chat with video', interactive=False, width=400, elem_classes="example")
+                example3 = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/fshot.gif", label='3. Few shot', interactive=False, width=400, elem_classes="example")
+
+
+# launch
+demo.launch(share=False, debug=True, show_api=False, server_port=8000, server_name="0.0.0.0")
+
diff --git a/web_demos/minicpm-o_2.6/web_server/src/views/home/index.vue b/web_demos/minicpm-o_2.6/web_server/src/views/home/index.vue
index 8695045..5efc39d 100644
--- a/web_demos/minicpm-o_2.6/web_server/src/views/home/index.vue
+++ b/web_demos/minicpm-o_2.6/web_server/src/views/home/index.vue
@@ -39,8 +39,9 @@
             <VoiceCall v-else-if="!isWebSocket && activeTab === 'voice'" v-model="isCalling" />
             <VideoCallWs v-else-if="isWebSocket && activeTab === 'video'" v-model="isCalling" />
             <VideoCall v-else-if="!isWebSocket && activeTab === 'video'" v-model="isCalling" />
+            <!-- TODO: https is required to support chatbot in iframe -->
             <iframe
-                src="https://minicpm-omni-webdemo-iframe.modelbest.cn"
+                src="http://127.0.0.1:8000/"
                 frameborder="0"
                 width="100%"
                 height="100%"