Update app.py

app.py

@@ -4,9 +4,10 @@ import numpy as np
 from groq import Groq
 import faiss
 import fitz  # PyMuPDF
+
 # Set up Groq API client
 def get_groq_client():
-return Groq(api_key=os.environ.get("groq_api"))
+    return Groq(api_key=os.environ.get("groq_api"))
 
 # Function to extract text from PDF
 def extract_pdf_content(pdf_file):
@@ -22,7 +23,7 @@ def chunk_text(text, chunk_size=500):
     return [" ".join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
 
 # Function to compute embeddings using Groq's Llama3-70B-8192 model
-def compute_embeddings(text_chunks):
+def compute_embeddings(groq_client, text_chunks):
     embeddings = []
     for chunk in text_chunks:
         response = groq_client.chat.completions.create(
@@ -45,7 +46,7 @@ def search_faiss_index(index, query_embedding, text_chunks, top_k=3):
     return [(text_chunks[idx], distances[0][i]) for i, idx in enumerate(indices[0])]
 
 # Function to generate professional content using Groq's Llama3-70B-8192 model
-def generate_professional_content_groq(topic):
+def generate_professional_content_groq(groq_client, 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"
@@ -53,7 +54,7 @@ def generate_professional_content_groq(topic):
     return response['choices'][0]['message']['content'].strip()
 
 # Function to compute query embedding using Groq's Llama3-70B-8192 model
-def compute_query_embedding(query):
+def compute_query_embedding(groq_client, query):
     response = groq_client.chat.completions.create(
         messages=[{"role": "user", "content": query}],
         model="llama3-70b-8192"
@@ -68,6 +69,9 @@ st.sidebar.header("AI-Based Tutor with Vector Search")
 uploaded_file = st.sidebar.file_uploader("Upload Study Material (PDF)", type=["pdf"])
 topic = st.sidebar.text_input("Enter a topic (e.g., Newton's Third Law)")
 
+# Initialize Groq client
+groq_client = get_groq_client()
+
 if uploaded_file:
     # Extract and process file content
     content = extract_pdf_content(uploaded_file)
@@ -75,7 +79,7 @@ if uploaded_file:
 
     # Chunk and compute embeddings
     chunks = chunk_text(content)
-    embeddings = compute_embeddings(chunks)
+    embeddings = compute_embeddings(groq_client, chunks)
 
     # Build FAISS index
     index = build_faiss_index(embeddings)
@@ -89,7 +93,7 @@ if st.button("Generate Study Material"):
         st.header(f"Study Material: {topic}")
         
         # Compute query embedding
-        query_embedding = compute_query_embedding(topic)
+        query_embedding = compute_query_embedding(groq_client, topic)
 
         # Search FAISS index
         if uploaded_file:
@@ -101,7 +105,7 @@ if st.button("Generate Study Material"):
             st.warning("No file uploaded. Generating AI-based content instead.")
         
         # Generate content using Groq's Llama3-70B-8192 model
-        ai_content = generate_professional_content_groq(topic)
+        ai_content = generate_professional_content_groq(groq_client, topic)
         st.write("**AI-Generated Content (Groq - Llama3-70B-8192):**")
         st.write(ai_content)
     else: