Update app.py

app.py

@@ -2,7 +2,8 @@ import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from groqflow.groqmodel import GroqModel  # Ensure this is the correct import for Groq model
+from groqflow.groqapi import GroqAPI  # Adjust this based on your Groq library
 
 # Configure page
 st.set_page_config(page_title="Data Augmentation App", layout="wide")
@@ -25,20 +26,18 @@ st.title("Data Augmentation and Analysis App")
 st.sidebar.title("Upload Your File")
 st.sidebar.markdown("Supported formats: CSV, Excel")
 
-# Get the Hugging Face API key from secrets
-hf_api_key = st.secrets.get("HUGGINGFACE_KEY")
-if not hf_api_key:
-    st.error("Hugging Face API key not found in secrets.")
+# Get the Groq API key from secrets
+groq_api_key = st.secrets.get("HUGGINGFACE_API")  # Ensure this is stored in secrets.json
+if not groq_api_key:
+    st.error("Groq API key not found in secrets.")
 else:
-    # Initialize the model and tokenizer using the API key
     try:
-        model_name = "llama-3.1-8b-instant"  # Replace with the correct model name if needed
-        model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_api_key)
-        tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_api_key)
-        llm_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
-        st.success(f"Model {model_name} initialized successfully!")
+        # Initialize the Groq API or Groq model client
+        groq_api = GroqAPI(api_key=groq_api_key)
+        groq_model = GroqModel(model="llama-3.1-8b-instant", groq_api=groq_api)  # Load the specific model
+        st.success("Groq model initialized successfully!")
     except Exception as e:
-        st.error(f"Error initializing model: {e}")
+        st.error(f"Error initializing Groq model: {e}")
 
 def load_file(uploaded_file):
     """Load the uploaded file."""
@@ -67,16 +66,16 @@ def generate_graph(data, query):
         st.error(f"Error generating graph: {e}")
 
 def handle_query(data, query):
-    """Handle user query using the LLM."""
+    """Handle user query using the Groq model."""
     try:
-        if not llm_pipeline:
-            st.error("LLM pipeline is not initialized. Check for errors in setup.")
+        if not groq_model:
+            st.error("Groq model is not initialized. Check for errors in setup.")
             return
         prompt = f"Given the dataset: {data.to_dict(orient='records')}, answer the following: {query}"
-        response = llm_pipeline(prompt, max_length=200, num_return_sequences=1)
-        st.write("Response:", response[0]['generated_text'])
+        response = groq_model.generate_text(prompt)  # Use the Groq model's method for inference
+        st.write("Response:", response)
     except Exception as e:
-        st.error(f"Error in LLM processing: {e}")
+        st.error(f"Error in Groq processing: {e}")
 
 # Main App
 uploaded_file = st.sidebar.file_uploader("Upload your file here", type=["csv", "xlsx"])