Spaces:
Sleeping
Sleeping
File size: 6,564 Bytes
65f2058 d43c6a1 86c183f d43c6a1 61da4c8 d43c6a1 86aa17d d43c6a1 86c183f d43c6a1 86c183f d43c6a1 86c183f c3ebe08 86c183f ccfe396 86c183f ccfe396 65f2058 ccfe396 65f2058 ccfe396 65f2058 ccfe396 65f2058 ccfe396 c3ebe08 ccfe396 65f2058 9b24172 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 |
import gradio as gr
from PIL import Image
from inference.main import MultiModalPhi2
messages = []
multimodal_phi2 = MultiModalPhi2(
modelname_or_path="Navyabhat/Llava-Phi2",
temperature=0.2,
max_new_tokens=1024,
device="cpu",
)
def add_content(chatbot, input_data, input_type) -> gr.Chatbot:
textflag, imageflag, audioflag = False, False, False
if input_type == "text":
chatbot.append((text, None))
textflag = True
if input_type == "image":
chatbot.append(((image,), None))
imageflag = True
if input_type == "audio":
chatbot.append(((audio_mic,), None))
audioflag = True
# else:
# if audio_upload is not None:
# chatbot.append(((audio_upload,), None))
# audioflag = True
if not any([textflag, imageflag, audioflag]):
# Raise an error if neither text nor file is provided
raise gr.Error("Enter a valid text, image or audio")
return chatbot
def clear_data():
return {prompt: None, image: None, audio_upload: None, audio_mic: None, chatbot: []}
def run(history, text, image, audio_upload, audio_mic):
if text in [None, ""]:
text = None
if audio_upload is not None:
audio = audio_upload
elif audio_mic is not None:
audio = audio_mic
else:
audio = None
print("text", text)
print("image", image)
print("audio", audio)
if image is not None:
image = Image.open(image)
outputs = multimodal_phi2(text, audio, image)
# outputs = ""
history.append((None, outputs.title()))
return history, None, None, None, None
with gr.Blocks() as demo:
chatbot = gr.Chatbot(
[],
elem_id="chatbot",
bubble_full_width=False,
avatar_images=(None, (os.path.join(os.path.dirname(__file__), "avatar.png"))),
)
with gr.Row():
txt = gr.Textbox(
scale=4,
show_label=False,
placeholder="Enter text and press enter",
container=False,
)
img_audio = gr.UploadButton("📁", file_types=["image", "audio"], label="Upload Image or Audio")
txt_msg = txt.submit(add_content, [chatbot, txt], [chatbot, txt, "text"], queue=False).then(
bot, chatbot, chatbot, api_name="bot_response"
)
img_audio_msg = img_audio.upload(add_input, [chatbot, img_audio], [chatbot, "image"], queue=False).then(
bot, chatbot, chatbot
)
# chatbot.like(print_like_dislike, None, None)
submit.click(
add_content,
inputs=[chatbot, prompt, image, audio_upload, audio_mic],
outputs=[chatbot],
).success(
run,
inputs=[chatbot, prompt, image, audio_upload, audio_mic],
outputs=[chatbot, prompt, image, audio_upload, audio_mic],
)
clear.click(
clear_data,
outputs=[prompt, image, audio_upload, audio_mic, chatbot],
)
demo.launch()
import gradio as gr
from PIL import Image
from inference.main import MultiModalPhi2
import os
messages = []
multimodal_phi2 = MultiModalPhi2(
modelname_or_path="Navyabhat/Llava-Phi2",
temperature=0.2,
max_new_tokens=1024,
device="cpu",
)
def add_content(chatbot, text, image, audio_upload, audio_mic) -> gr.Chatbot:
textflag, imageflag, audioflag = False, False, False
if text not in ["", None]:
chatbot.append((text, None))
textflag = True
if image is not None:
chatbot.append(((image,), None))
imageflag = True
if audio_mic is not None:
chatbot.append(((audio_mic,), None))
audioflag = True
else:
if audio_upload is not None:
chatbot.append(((audio_upload,), None))
audioflag = True
if not any([textflag, imageflag, audioflag]):
# Raise an error if neither text nor file is provided
raise gr.Error("Enter a valid text, image or audio")
return chatbot
def clear_data():
return {"text": None, "image": None, "audio_upload": None, "audio_mic": None, "chatbot": []}
def run(history, text, image, audio_upload, audio_mic):
if text in [None, ""]:
text = None
if audio_upload is not None:
audio = audio_upload
elif audio_mic is not None:
audio = audio_mic
else:
audio = None
print("text", text)
print("image", image)
print("audio", audio)
if image is not None:
image = Image.open(image)
outputs = multimodal_phi2(text, audio, image)
history.append((None, outputs.title()))
return history, None, None, None, None
# def print_like_dislike(x: gr.LikeData):
# print(x.index, x.value, x.liked)
def add_text(history, text):
history = history + [(text, None)]
return history, gr.Textbox(value="", interactive=False)
def add_file(history, file):
history = history + [((file.name,), None)]
return history
def bot(history):
response = "**That's cool!**"
history[-1][1] = ""
for character in response:
history[-1][1] += character
time.sleep(0.05)
yield history
with gr.Blocks() as demo:
chatbot = gr.Chatbot(
[],
elem_id="chatbot",
bubble_full_width=False,
avatar_images=(None, (os.path.join(os.path.dirname(__file__), "avatar.png"))),
)
with gr.Row():
txt = gr.Textbox(
scale=4,
show_label=False,
placeholder="Enter text and press enter",
container=False,
)
img_audio = gr.UploadButton("📁", file_types=["image", "audio"], label="Upload Image or Audio")
with gr.Row():
# Adding a Button
submit = gr.Button()
clear = gr.Button(value="Clear")
txt_msg = txt.submit(add_input, [chatbot, txt], [chatbot, txt, "text"], queue=False).then(
bot, chatbot, chatbot, api_name="bot_response"
)
img_audio_msg = img_audio.upload(add_input, [chatbot, img_audio], [chatbot, "image"], queue=False).then(
bot, chatbot, chatbot
)
# submit.click(
# add_content,
# inputs=[chatbot, txt, image, audio_upload, audio_mic],
# outputs=[chatbot],
# ).success(
# run,
# inputs=[chatbot, txt, image, audio_upload, audio_mic],
# outputs=[chatbot, txt, image, audio_upload, audio_mic],
# )
clear.click(
clear_data,
outputs=[prompt, image, audio_upload, audio_mic, chatbot],
)
# chatbot.like(print_like_dislike, None, None)
# demo.queue()
demo.launch()
|