File size: 2,859 Bytes
1aeba5b 1d30190 3c0e4d5 1aeba5b 544b0ab 8a109b5 | 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 | import gradio as gr
from PIL import Image
import os
from chatbot_updated import (
chatbot_updated,
detect_artifact,
text_to_speech,
cleanup_audio_file
)
# =========================
# CORE FUNCTION
# =========================
def process(input_text, image, audio):
"""
Handles text + image + audio input
"""
# =========================
# 1. PRIORITY: AUDIO
# =========================
question = input_text
if audio is not None:
# gradio gives file path for audio
audio_bytes = open(audio, "rb").read()
question = audio_bytes
# =========================
# 2. IMAGE HANDLING
# =========================
img = None
detected_name = None
if image is not None:
img = Image.open(image).convert("RGB")
detected_name, annotated = detect_artifact(img)
else:
annotated = None
# =========================
# 3. CHATBOT CALL
# =========================
answer = chatbot_updated(question, image=img)
answer = str(answer).strip()
# =========================
# 4. TEXT TO SPEECH
# =========================
audio_file = text_to_speech(answer)
audio_out = None
if audio_file and os.path.exists(audio_file):
audio_out = audio_file
# =========================
# RETURN UI OUTPUTS
# =========================
return (
answer, # text output
annotated, # image output
audio_out # audio output
)
# =========================
# GRADIO UI
# =========================
with gr.Blocks(title="🏺 Egyptian Artifact Chatbot") as app:
gr.Markdown("# 🏺 Egyptian Artifact Chatbot (Gradio Version)")
gr.Markdown("Ask using text, voice, or image")
with gr.Row():
with gr.Column():
input_text = gr.Textbox(label="💬 Ask a question")
audio_input = gr.Audio(
sources=["microphone"],
type="filepath",
label="🎤 Voice Input",
)
image_input = gr.Image(
type="filepath",
label="📷 Upload Image"
)
btn = gr.Button("🚀 Get Answer")
with gr.Column():
output_text = gr.Textbox(label="🤖 Answer")
output_image = gr.Image(label="🖼 Detected Artifact")
output_audio = gr.Audio(label="🔊 Speech Output")
# =========================
# BUTTON CLICK
# =========================
btn.click(
fn=process,
inputs=[input_text, image_input, audio_input],
outputs=[output_text, output_image, output_audio]
)
# =========================
# RUN APP
# =========================
if __name__ == "__main__":
app.launch(
server_name="0.0.0.0",
server_port=7860
) |