Spaces:
Sleeping
Sleeping
File size: 6,007 Bytes
97c1fc3 |
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 |
from flask import Flask, request, jsonify, render_template
from dotenv import load_dotenv
from groq import Groq
import os
import uuid
from gtts import gTTS
import io
import base64
import speech_recognition as sr
import tempfile
import json
try:
import pyaudio
except ImportError:
print("Warning: PyAudio not available, speech functionality will be limited")
# Initialize Flask app
app = Flask(__name__, static_folder='static')
# Load environment variables
load_dotenv()
# Groq API Configuration
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
client = Groq(api_key=GROQ_API_KEY)
MODEL = "llama3-70b-8192"
# Initialize speech recognition
recognizer = sr.Recognizer()
# Store conversation history
conversations = {}
def load_base_prompt():
try:
with open("base_prompt.txt", "r") as file:
return file.read().strip()
except FileNotFoundError:
print("Error: base_prompt.txt file not found.")
return "You are a helpful assistant for language learning."
# Load the base prompt
base_prompt = load_base_prompt()
def chat_with_groq(user_message, conversation_id=None):
try:
# Get conversation history or create new
messages = conversations.get(conversation_id, [])
if not messages:
messages.append({"role": "system", "content": base_prompt})
# Add user message
messages.append({"role": "user", "content": user_message})
# Get completion from Groq
completion = client.chat.completions.create(
model=MODEL,
messages=messages,
temperature=0.1,
max_tokens=1024
)
# Add assistant's response to history
assistant_message = completion.choices[0].message.content.strip()
messages.append({"role": "assistant", "content": assistant_message})
# Update conversation history
if conversation_id:
conversations[conversation_id] = messages
return assistant_message
except Exception as e:
print(f"Error in chat_with_groq: {str(e)}")
return f"I apologize, but I'm having trouble responding right now. Error: {str(e)}"
def text_to_speech(text):
try:
tts = gTTS(text=text, lang='en')
audio_io = io.BytesIO()
tts.write_to_fp(audio_io)
audio_io.seek(0)
return audio_io
except Exception as e:
print(f"Error in text_to_speech: {str(e)}")
return None
def speech_to_text(audio_file):
try:
# Save the uploaded audio to a temporary file
with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as temp_audio:
audio_file.save(temp_audio.name)
# Use SpeechRecognition to convert speech to text
with sr.AudioFile(temp_audio.name) as source:
# Adjust recognition settings
recognizer.dynamic_energy_threshold = True
recognizer.energy_threshold = 4000
# Record the entire audio file
audio = recognizer.record(source)
# Perform recognition with increased timeout
text = recognizer.recognize_google(audio, language='en-US')
return text
except sr.UnknownValueError:
return "Could not understand audio"
except sr.RequestError as e:
return f"Could not request results; {str(e)}"
except Exception as e:
print(f"Error in speech_to_text: {str(e)}")
return None
finally:
# Clean up temporary file
try:
os.unlink(temp_audio.name)
except:
pass
@app.route('/')
def index():
return render_template('index.html')
@app.route('/api/chat', methods=['POST'])
def chat():
try:
data = request.get_json()
user_message = data.get('message', '')
conversation_id = data.get('conversation_id', str(uuid.uuid4()))
if not user_message:
return jsonify({'error': 'No message provided'}), 400
# Get response from Groq
response = chat_with_groq(user_message, conversation_id)
# Generate voice response
audio_io = text_to_speech(response)
result = {
'response': response,
'conversation_id': conversation_id
}
if audio_io:
audio_base64 = base64.b64encode(audio_io.getvalue()).decode('utf-8')
result['voice_response'] = audio_base64
return jsonify(result)
except Exception as e:
return jsonify({'error': str(e)}), 500
@app.route('/api/voice', methods=['POST'])
def handle_voice():
try:
if 'audio' not in request.files:
return jsonify({'error': 'No audio file provided'}), 400
audio_file = request.files['audio']
conversation_id = request.form.get('conversation_id', str(uuid.uuid4()))
# Convert speech to text
text = speech_to_text(audio_file)
if not text:
return jsonify({'error': 'Could not transcribe audio'}), 400
# Get response from Groq
response = chat_with_groq(text, conversation_id)
# Generate voice response
audio_io = text_to_speech(response)
result = {
'text': text,
'response': response,
'conversation_id': conversation_id
}
if audio_io:
audio_base64 = base64.b64encode(audio_io.getvalue()).decode('utf-8')
result['voice_response'] = audio_base64
return jsonify(result)
except Exception as e:
return jsonify({'error': str(e)}), 500
if __name__ == '__main__':
app.run(host='0.0.0.0', port=7860)
|