Update app.py

app.py

@@ -1,24 +1,12 @@
+import os
 import streamlit as st
 from PyPDF2 import PdfReader
-from transformers import pipeline, AutoTokenizer, AutoModel
-from sklearn.feature_extraction.text import TfidfVectorizer
-import faiss
 import numpy as np
+from groq import Groq
+import faiss
 
-# Load the Hugging Face model for text generation
-@st.cache_resource
-def load_text_generator():
-    return pipeline("text2text-generation", model="google/flan-t5-base")
-
-# Load the Hugging Face model for embeddings
-@st.cache_resource
-def load_embedding_model():
-    tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
-    model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
-    return tokenizer, model
-
-text_generator = load_text_generator()
-embedding_tokenizer, embedding_model = load_embedding_model()
+# Set up Groq API client
+groq_client = Groq(api_key="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")
 
 # Function to extract text from PDF
 def extract_pdf_content(pdf_file):
@@ -33,13 +21,15 @@ def chunk_text(text, chunk_size=500):
     words = text.split()
     return [" ".join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
 
-# Function to compute embeddings
+# Function to compute embeddings using Groq's Llama3-70B-8192 model
 def compute_embeddings(text_chunks):
     embeddings = []
     for chunk in text_chunks:
-        inputs = embedding_tokenizer(chunk, return_tensors="pt", truncation=True, padding=True)
-        outputs = embedding_model(**inputs)
-        embeddings.append(outputs.pooler_output.detach().numpy()[0])
+        response = groq_client.chat.completions.create(
+            messages=[{"role": "user", "content": chunk}],
+            model="llama3-70b-8192"
+        )
+        embeddings.append(np.array(response['choices'][0]['message']['content']))
     return np.array(embeddings)
 
 # Function to build FAISS index
@@ -54,20 +44,24 @@ def search_faiss_index(index, query_embedding, text_chunks, top_k=3):
     distances, indices = index.search(query_embedding, top_k)
     return [(text_chunks[idx], distances[0][i]) for i, idx in enumerate(indices[0])]
 
-# Function to generate structured content
-def generate_professional_content(topic):
-    prompt = f"Explain '{topic}' in bullet points, highlighting key concepts, examples, and applications."
-    response = text_generator(prompt, max_length=300, num_return_sequences=1)
-    return response[0]['generated_text']
+# Function to generate professional content using Groq's Llama3-70B-8192 model
+def generate_professional_content_groq(topic):
+    response = groq_client.chat.completions.create(
+        messages=[{"role": "user", "content": f"Explain '{topic}' in bullet points, highlighting key concepts, examples, and applications for electrical engineering students."}],
+        model="llama3-70b-8192"
+    )
+    return response['choices'][0]['message']['content'].strip()
 
-# Function to compute query embedding
+# Function to compute query embedding using Groq's Llama3-70B-8192 model
 def compute_query_embedding(query):
-    inputs = embedding_tokenizer(query, return_tensors="pt", truncation=True, padding=True)
-    outputs = embedding_model(**inputs)
-    return outputs.pooler_output.detach().numpy()
+    response = groq_client.chat.completions.create(
+        messages=[{"role": "user", "content": query}],
+        model="llama3-70b-8192"
+    )
+    return np.array(response['choices'][0]['message']['content']).reshape(1, -1)
 
 # Streamlit app
-st.title("Generative AI for Electrical Engineering Education with FAISS")
+st.title("Generative AI for Electrical Engineering Education with FAISS and Groq")
 st.sidebar.header("AI-Based Tutor with Vector Search")
 
 # File upload section
@@ -106,10 +100,9 @@ if st.button("Generate Study Material"):
         else:
             st.warning("No file uploaded. Generating AI-based content instead.")
         
-        # Generate AI content
-        ai_content = generate_professional_content(topic)
-        st.write("**AI-Generated Content:**")
+        # Generate content using Groq's Llama3-70B-8192 model
+        ai_content = generate_professional_content_groq(topic)
+        st.write("**AI-Generated Content (Groq - Llama3-70B-8192):**")
         st.write(ai_content)
     else:
         st.warning("Please enter a topic!")
-