Spaces:
Sleeping
Sleeping
File size: 2,740 Bytes
2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e 2d9bcbf 5ecc50e | 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 | import gradio as gr
import numpy as np
import json
import tensorflow as tf
from tensorflow.keras.models import load_model
# ====================
# Load models
# ====================
encoder_model = load_model("encoder_model.h5")
decoder_model = load_model("decoder_model.h5")
# ====================
# Load assets
# ====================
with open("assets/char2idx.json", "r", encoding="utf-8") as f:
char2idx = json.load(f)
with open("assets/idx2char.json", "r", encoding="utf-8") as f:
idx2char = json.load(f)
with open("assets/config.json", "r", encoding="utf-8") as f:
config = json.load(f)
num_chars = config["num_chars"]
max_len_input = config["max_len_input"]
max_len_target = config["max_len_target"]
latent_dim = config["latent_dim"]
# ====================
# Encode input text
# ====================
def encode_text(text, max_len):
x = np.zeros((1, max_len, num_chars), dtype="float32")
words = text.lower().split(" ")
for t, w in enumerate(words[:max_len]):
if w in char2idx:
x[0, t, char2idx[w]] = 1.0
return x
# ====================
# Decode sequence
# ====================
def decode_sequence(input_seq):
states_value = encoder_model.predict(input_seq)
target_seq = np.zeros((1, 1, num_chars))
target_seq[0, 0, char2idx["\t"]] = 1.0
decoded_sentence = ""
stop_condition = False
while not stop_condition:
output_tokens, h, c = decoder_model.predict([target_seq] + states_value)
sampled_token_index = np.argmax(output_tokens[0, -1, :])
sampled_char = idx2char[str(sampled_token_index)] # key là str khi lưu json
if sampled_char == "\n" or len(decoded_sentence.split(" ")) >= max_len_target - 1:
stop_condition = True
decoded_sentence += sampled_char
else:
decoded_sentence += sampled_char + " "
target_seq = np.zeros((1, 1, num_chars))
target_seq[0, 0, sampled_token_index] = 1.0
states_value = [h, c]
return decoded_sentence.strip()
# ====================
# Gradio interface
# ====================
def chatbot(user_input, history=[]):
seq = encode_text(user_input, max_len_input)
response = decode_sequence(seq)
history.append((user_input, response))
return history, history
with gr.Blocks() as demo:
gr.Markdown("# Basic Chatbot")
chatbot_ui = gr.Chatbot()
msg = gr.Textbox(placeholder="Type a message...")
clear = gr.Button("Clear")
def respond(message, chat_history):
response = chatbot(message, chat_history)[1][-1][1]
return "", chat_history
msg.submit(respond, [msg, chatbot_ui], [msg, chatbot_ui])
clear.click(lambda: None, None, chatbot_ui, queue=False)
demo.launch()
|