Spaces:
Running
Running
File size: 16,388 Bytes
7b74407 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 |
from main import *
from tts_api import tts_api as tts_module_api
from stt_api import stt_api as stt_module_api
from sentiment_api import sentiment_api as sentiment_module_api
from imagegen_api import imagegen_api as imagegen_module_api
from musicgen_api import musicgen_api as musicgen_module_api
from translation_api import translation_api as translation_module_api
from codegen_api import codegen_api as codegen_module_api
from text_to_video_api import text_to_video_api as text_to_video_module_api
from summarization_api import summarization_api as summarization_module_api
from image_to_3d_api import image_to_3d_api as image_to_3d_module_api
from xtts_api import xtts_api as xtts_module_api
from flask import Flask, request, jsonify, Response, send_file, stream_with_context
from flask_cors import CORS
import io
import queue
import base64
import gradio as gr
app = Flask(__name__)
CORS(app)
html_code = """<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>AI Text Generation</title>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/animate.css/4.1.1/animate.min.css"/>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css" integrity="sha512-9usAa10IRO0HhonpyAIVpjrylPvoDwiPUiKdWk5t3PyolY1cOd4DSE0Ga+ri4AuTroPR5aQvXU9xC6qOPnzFeg==" crossorigin="anonymous" referrerpolicy="no-referrer" />
<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
<style>
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: #f0f0f0;
color: #333;
margin: 0;
padding: 0;
display: flex;
flex-direction: column;
align-items: center;
min-height: 100vh;
}
.container {
width: 95%;
max-width: 900px;
padding: 20px;
background-color: #fff;
box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
border-radius: 8px;
margin-top: 20px;
margin-bottom: 20px;
display: flex;
flex-direction: column;
}
.header {
text-align: center;
margin-bottom: 20px;
}
.header h1 {
font-size: 2em;
color: #333;
}
.form-group {
margin-bottom: 15px;
}
.form-group textarea {
width: 100%;
padding: 10px;
border: 1px solid #ccc;
border-radius: 5px;
font-size: 16px;
box-sizing: border-box;
resize: vertical;
}
button {
padding: 10px 15px;
border: none;
border-radius: 5px;
background-color: #007bff;
color: white;
font-size: 18px;
cursor: pointer;
transition: background-color 0.3s ease;
}
button:hover {
background-color: #0056b3;
}
#output {
margin-top: 20px;
padding: 15px;
border: 1px solid #ddd;
border-radius: 5px;
background-color: #f9f9f9;
white-space: pre-wrap;
word-break: break-word;
overflow-y: auto;
max-height: 100vh;
}
#output strong {
font-weight: bold;
}
.animated-text {
position: fixed;
top: 20px;
left: 20px;
font-size: 1.5em;
color: rgba(0, 0, 0, 0.1);
pointer-events: none;
z-index: -1;
}
@media (max-width: 768px) {
.container {
width: 98%;
margin-top: 10px;
margin-bottom: 10px;
padding: 15px;
}
.header h1 {
font-size: 1.8em;
}
.form-group textarea, .form-group input[type="text"] {
font-size: 14px;
padding: 8px;
}
button {
font-size: 16px;
padding: 8px 12px;
}
#output {
font-size: 14px;
padding: 10px;
margin-top: 15px;
}
}
</style>
</head>
<body>
<div class="animated-text animate__animated animate__fadeIn animate__infinite infinite">AI POWERED</div>
<div class="container">
<div class="header animate__animated animate__fadeInDown">
</div>
<div class="form-group animate__animated animate__fadeInLeft">
<textarea id="text" rows="5" placeholder="Enter text"></textarea>
</div>
<button onclick="generateText()" class="animate__animated animate__fadeInUp">Generate Reasoning</button>
<div id="output" class="animate__animated">
<strong>Response:</strong><br>
<span id="generatedText"></span>
</div>
</div>
<script>
let eventSource = null;
let accumulatedText = "";
let lastResponse = "";
async function generateText() {
const inputText = document.getElementById("text").value;
document.getElementById("generatedText").innerText = "";
accumulatedText = "";
if (eventSource) {
eventSource.close();
}
const temp = 0.7;
const top_k_val = 40;
const top_p_val = 0.0;
const repetition_penalty_val = 1.2;
const requestData = {
text: inputText,
temp: temp,
top_k: top_k_val,
top_p: top_p_val,
reppenalty: repetition_penalty_val
};
const params = new URLSearchParams(requestData).toString();
eventSource = new EventSource('/api/v1/generate_stream?' + params);
eventSource.onmessage = function(event) {
if (event.data === "<END_STREAM>") {
eventSource.close();
const currentResponse = accumulatedText.replace("<|endoftext|>", "").replace(/\s+(?=[.,，。])/g, '').trim();
if (currentResponse === lastResponse.trim()) {
accumulatedText = "**Response is repetitive. Please try again or rephrase your query.**";
} else {
lastResponse = currentResponse;
}
document.getElementById("generatedText").innerHTML = marked.parse(accumulatedText);
return;
}
accumulatedText += event.data;
let partialText = accumulatedText.replace("<|endoftext|>", "").replace(/\s+(?=[.,，。])/g, '').trim();
document.getElementById("generatedText").innerHTML = marked.parse(partialText);
};
eventSource.onerror = function(error) {
console.error("SSE error", error);
eventSource.close();
};
const outputDiv = document.getElementById("output");
outputDiv.classList.add("show");
}
function base64ToBlob(base64Data, contentType) {
contentType = contentType || '';
const sliceSize = 1024;
const byteCharacters = atob(base64Data);
const bytesLength = byteCharacters.length;
const slicesCount = Math.ceil(bytesLength / sliceSize);
const byteArrays = new Array(slicesCount);
for (let sliceIndex = sliceIndex < slicesCount; ++sliceIndex) {
const begin = sliceIndex * sliceSize;
const end = Math.min(begin + sliceSize, bytesLength);
const bytes = new Array(end - begin);
for (let offset = begin, i = 0; offset < end; ++i, ++offset) {
bytes[i] = byteCharacters[offset].charCodeAt(0);
}
byteArrays[sliceIndex] = new Uint8Array(bytes);
}
return new Blob(byteArrays, { type: contentType });
}
</script>
</body>
</html>
"""
feedback_queue = queue.Queue()
@app.route("/")
def index():
return html_code
@app.route("/api/v1/generate_stream", methods=["GET"])
def generate_stream():
text = request.args.get("text", "")
temp = float(request.args.get("temp", 0.7))
top_k = int(request.args.get("top_k", 40))
top_p = float(request.args.get("top_p", 0.0))
reppenalty = float(request.args.get("reppenalty", 1.2))
response_queue = queue.Queue()
reasoning_queue.put({
'text_input': text,
'temperature': temp,
'top_k': top_k,
'top_p': top_p,
'repetition_penalty': reppenalty,
'response_queue': response_queue
})
@stream_with_context
def event_stream():
while True:
output = response_queue.get()
if "error" in output:
yield "data: <ERROR>\n\n"
break
text_chunk = output.get("text")
if text_chunk:
for word in text_chunk.split(' '):
clean_word = word.strip()
if clean_word:
yield "data: " + clean_word + "\n\n"
yield "data: <END_STREAM>\n\n"
break
return Response(event_stream(), mimetype="text/event-stream")
@app.route("/api/v1/generate", methods=["POST"])
def generate():
data = request.get_json()
text = data.get("text", "")
temp = float(data.get("temp", 0.7))
top_k = int(data.get("top_k", 40))
top_p = float(data.get("top_p", 0.0))
reppenalty = float(data.get("reppenalty", 1.2))
response_queue = queue.Queue()
reasoning_queue.put({
'text_input': text,
'temperature': temp,
'top_k': top_k,
'top_p': top_p,
'repetition_penalty': reppenalty,
'response_queue': response_queue
})
output = response_queue.get()
if "error" in output:
return jsonify({"error": output["error"]}), 500
result_text = output.get("text", "").strip()
return jsonify({"response": result_text})
@app.route("/api/v1/feedback", methods=["POST"])
def feedback():
data = request.get_json()
feedback_text = data.get("feedback_text")
correct_category = data.get("correct_category")
if feedback_text and correct_category:
feedback_queue.put((feedback_text, correct_category))
return jsonify({"status": "feedback received"})
return jsonify({"status": "feedback failed"}), 400
@app.route("/api/v1/tts", methods=["POST"])
def tts_api():
return tts_module_api()
@app.route("/api/v1/stt", methods=["POST"])
def stt_api():
return stt_module_api()
@app.route("/api/v1/sentiment", methods=["POST"])
def sentiment_api():
return sentiment_module_api()
@app.route("/api/v1/imagegen", methods=["POST"])
def imagegen_api():
return imagegen_module_api()
@app.route("/api/v1/musicgen", methods=["POST"])
def musicgen_api():
return musicgen_module_api()
@app.route("/api/v1/translation", methods=["POST"])
def translation_api():
return translation_module_api()
@app.route("/api/v1/codegen", methods=["POST"])
def codegen_api():
return codegen_module_api()
@app.route("/api/v1/text_to_video", methods=["POST"])
def text_to_video_api():
return text_to_video_module_api()
@app.route("/api/v1/summarization", methods=["POST"])
def summarization_api():
return summarization_module_api()
@app.route("/api/v1/image_to_3d", methods=["POST"])
def image_to_3d_api():
return image_to_3d_module_api()
@app.route("/api/v1/xtts_clone", methods=["POST"])
def xtts_clone_api():
return xtts_module_api()
@app.route("/api/v1/sadtalker", methods=["POST"])
def sadtalker():
from sadtalker_api import router as sadtalker_router
return sadtalker_router.create_video()
if __name__ == "__main__":
with gr.Blocks() as demo:
gr.Markdown("## AI Powerhouse")
with gr.Tab("Text Generation"):
text_input = gr.Textbox(lines=5, placeholder="Enter text")
text_output = gr.Markdown()
text_button = gr.Button("Generate Text")
text_button.click(generate, inputs=text_input, outputs=text_output)
with gr.Tab("Image Generation"):
image_text_input = gr.Textbox(lines=3, placeholder="Enter prompt for image")
image_output = gr.Image()
image_button = gr.Button("Generate Image")
image_button.click(imagegen_api, inputs=image_text_input, outputs=image_output)
with gr.Tab("Music Generation"):
music_text_input = gr.Textbox(lines=3, placeholder="Enter prompt for music")
music_output = gr.Audio()
music_button = gr.Button("Generate Music")
music_button.click(musicgen_api, inputs=music_text_input, outputs=music_output)
with gr.Tab("Code Generation"):
code_text_input = gr.Textbox(lines=3, placeholder="Enter prompt for code")
code_output = gr.File()
code_button = gr.Button("Generate Code")
code_button.click(codegen_api, inputs=code_text_input, outputs=code_output)
with gr.Tab("Text to Video"):
video_text_input = gr.Textbox(lines=3, placeholder="Enter prompt for video")
video_output = gr.Video()
video_button = gr.Button("Generate Video")
video_button.click(text_to_video_api, inputs=video_text_input, outputs=video_output)
with gr.Tab("Summarization"):
summary_text_input = gr.Textbox(lines=5, placeholder="Enter text to summarize")
summary_output = gr.Textbox()
summary_button = gr.Button("Summarize")
summary_button.click(summarization_api, inputs=summary_text_input, outputs=summary_output)
with gr.Tab("Translation"):
translate_text_input = gr.Textbox(lines=3, placeholder="Enter text to translate")
translate_lang_dropdown = gr.Dropdown(['es', 'en', 'fr', 'de'], value='es', label="Target Language")
translation_output = gr.Textbox()
translate_button = gr.Button("Translate")
translate_button.click(translation_api, inputs=[translate_text_input, translate_lang_dropdown], outputs=translation_output)
with gr.Tab("Sentiment Analysis"):
sentiment_text_input = gr.Textbox(lines=3, placeholder="Enter text for sentiment analysis")
sentiment_output = gr.Textbox()
sentiment_button = gr.Button("Analyze Sentiment")
sentiment_button.click(sentiment_api, inputs=sentiment_text_input, outputs=sentiment_output)
with gr.Tab("Text to Speech"):
tts_text_input = gr.Textbox(lines=3, placeholder="Enter text for speech")
tts_output = gr.Audio()
tts_button = gr.Button("Generate Speech")
tts_button.click(tts_api, inputs=tts_text_input, outputs=tts_output)
with gr.Tab("Voice Cloning (XTTS)"):
xtts_text_input = gr.Textbox(lines=3, placeholder="Enter text for voice cloning")
xtts_audio_input = gr.Audio(source="upload", type="filepath", label="Reference Audio for Voice Cloning")
xtts_output = gr.Audio()
xtts_button = gr.Button("Clone Voice")
xtts_button.click(xtts_module_api, inputs=[xtts_text_input, xtts_audio_input], outputs=xtts_output)
with gr.Tab("Speech to Text"):
stt_audio_input = gr.Audio(source="microphone", type="filepath")
stt_output = gr.Textbox()
stt_button = gr.Button("Transcribe Speech")
stt_button.click(stt_api, inputs=stt_audio_input, outputs=stt_output)
with gr.Tab("Image to 3D"):
image_3d_input = gr.Image(source="upload", type="filepath")
model_3d_output = gr.File()
image_3d_button = gr.Button("Generate 3D Model")
image_3d_button.click(image_to_3d_api, inputs=image_3d_input, outputs=model_3d_output)
app = gr.routes.App(demo)
app.run(host="0.0.0.0", port=7860)
|