Frist Commit

agents.py

@@ -0,0 +1,32 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.agents import (
+    AgentType,
+    load_tools,
+    initialize_agent
+)
+from langchain.memory import ConversationBufferMemory
+from langchain.callbacks import StdOutCallbackHandler
+
+class SmartChatAgent:
+
+    def __init__(self) -> None:
+
+        self.memory = ConversationBufferMemory(
+            memory_key="chat_history",
+            return_messages=True
+        )
+
+        self.llm = ChatOpenAI()
+        self.tools = load_tools(['google-search'])
+
+        self.agent = initialize_agent(
+            self.tools,
+            self.llm,
+            agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,
+            memory=self.memory,
+            verbose=True,
+        )
+
+    def run(self, text):
+        handler = StdOutCallbackHandler()
+        return self.agent.run(text, callbacks=[handler])

app.py

@@ -0,0 +1,46 @@
+import os
+
+import openai
+from dotenv import load_dotenv
+load_dotenv()
+openai.api_key=os.environ["OPENAI_API_KEY"]
+
+import gradio as gr
+from langchain.llms import OpenAI
+from interface import AudioInterface
+interface = AudioInterface()
+
+
+def process(filepath):
+    audio = open(filepath,"rb")
+    transcript = openai.Audio.transcribe("whisper-1",audio)
+    llm = OpenAI(temperature=1)
+    print(llm(transcript["text"]))
+    interface.speak(llm(transcript["text"]))
+    return  llm(transcript["text"])
+
+demo = gr.Interface(
+    fn=process,
+    inputs=gr.Audio(source="microphone",type="filepath"),
+    outputs="text")
+demo.launch()
+
+
+"""
+
+from dotenv import load_dotenv
+load_dotenv()
+
+from interface import AudioInterface
+from agents import SmartChatAgent
+
+interface = AudioInterface()
+agent = SmartChatAgent()
+
+while True:
+    text = interface.listen()
+    response = agent.run(text)
+    interface.speak(response)
+
+
+"""

interface.py

@@ -0,0 +1,27 @@
+import os
+import speech_recognition as sr
+from elevenlabs import generate, play, set_api_key
+set_api_key(os.environ['ELEVEN_API_KEY'])
+
+class AudioInterface:
+
+    def listen(self) -> str:
+        recognizer = sr.Recognizer()
+        with sr.Microphone() as source:
+            print("Say something!")
+            audio = recognizer.listen(source)
+
+        text = recognizer.recognize_whisper_api(
+            audio,
+            api_key=os.environ['OPENAI_API_KEY'],
+        )
+
+        return text
+
+    def speak(self, text):
+        audio = generate(
+            text=text,
+            voice='Bella',
+            model='eleven_monolingual_v1'
+        )
+        play(audio)

requirements.txt

@@ -0,0 +1,5 @@
+openai~=0.28.1
+gradio~=3.46.0
+python-dotenv~=1.0.0
+langchain~=0.0.306
+elevenlabs~=0.2.26