Spaces:
Running
Running
File size: 4,514 Bytes
cdf597f dc400fa cdf597f dc400fa cdf597f 777de86 |
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 |
import os
from groq import Groq
import gradio as gr
# Access the API key from Colab Secrets
groq_api_key = os.environ.get("GROQ_API_KEY")
if not groq_api_key:
raise ValueError("GROQ_API_KEY not found in Colab Secrets. Please add it.")
client = Groq(api_key=groq_api_key)
# IMPORTANT: Check Groq's model deprecation page (https://console.groq.com/docs/deprecations)
# for the latest available and recommended models.
# As of July 2025, I'll use a likely available one.
# You might need to update this model_name if it changes on Groq's side.
# Recommended current models: "llama-3.1-8b-instant" or "llama-3.3-70b-versatile"
DEFAULT_GROQ_MODEL = "llama-3.1-8b-instant"
def get_groq_response(messages: list, model_name: str = DEFAULT_GROQ_MODEL, temperature: float = 0.7):
"""
Generates a response from Groq given a list of messages.
Args:
messages (list): A list of message dictionaries (e.g., [{"role": "user", "content": "Hello"}]).
model_name (str): The Groq model to use.
temperature (float): Controls the randomness of the output.
Returns:
str: The generated response content.
"""
try:
chat_completion = client.chat.completions.create(
messages=messages,
model=model_name,
temperature=temperature,
max_tokens=1024, # Adjust as needed
stream=False,
)
return chat_completion.choices[0].message.content
except Exception as e:
print(f"Error calling Groq API: {e}")
return "An error occurred while generating a response. Please check your API key and Groq console."
# --- Simple Conversational Agent Class ---
class SimpleGroqAgent:
def __init__(self, model_name: str = DEFAULT_GROQ_MODEL, temperature: float = 0.7):
self.model_name = model_name
self.temperature = temperature
# Initialize with a system message to define the agent's persona
self.conversation_history = [{"role": "system", "content": "You are a helpful and concise AI assistant powered by Groq. You respond quickly."}]
def chat(self, user_input: str) -> str:
"""
Processes user input and returns an AI response, updating conversation history.
"""
# Add user's message to history
self.conversation_history.append({"role": "user", "content": user_input})
# Get response from Groq using the current history
response_content = get_groq_response(self.conversation_history, self.model_name, self.temperature)
# Add assistant's response to history
self.conversation_history.append({"role": "assistant", "content": response_content})
return response_content
def reset_conversation(self):
"""Resets the conversation history."""
self.conversation_history = [{"role": "system", "content": "You are a helpful and concise AI assistant powered by Groq. You respond quickly."}]
# --- Gradio Interface Setup ---
# Instantiate your agent
groq_agent = SimpleGroqAgent()
def chat_interface_function(message, history):
"""
Function to be used by Gradio's ChatInterface.
'history' is a list of [user_message, bot_message] pairs.
Gradio's Chatbot component manages the visual history,
but our SimpleGroqAgent manages the history sent to the LLM.
"""
# The SimpleGroqAgent already manages its own internal history.
# We just need to pass the current message to it.
response = groq_agent.chat(message)
return response
# Create the Gradio ChatInterface
# In Colab, share=True will generate a public URL.
demo = gr.ChatInterface(
fn=chat_interface_function,
chatbot=gr.Chatbot(height=300),
textbox=gr.Textbox(placeholder="Ask me anything, powered by Groq!", container=False, scale=7),
title="⚡️ Groq-Powered AI Assistant in Colab ⚡️",
description=f"Ask a question and get a lightning-fast response from Groq's {DEFAULT_GROQ_MODEL} LLM!",
theme="soft",
examples=[
"Tell me a short, funny story.",
"Explain the concept of neural networks in simple terms.",
"What are the main components of a computer?",
"Write a creative short paragraph about a futuristic city."
],
)
# Launch the Gradio app
# This will provide a public URL you can click to access the UI.
# It will also run the UI directly in the Colab output.
print(f"Launching Gradio demo with model: {DEFAULT_GROQ_MODEL}")
demo.launch(share=True) |