Update app.py

app.py

@@ -1,24 +1,30 @@
 import os
 import streamlit as st
-from PyPDF2  import PdfReader
+from PyPDF2 import PdfReader
 import numpy as np
 from groq import Groq
 import faiss
 import fitz
+from io import BytesIO
 
-# Set up Groq API client
-#groq_client = Groq(api_key="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")
+# Function to set up Groq API client
 def get_groq_client():
-    return Groq(api_key=os.environ.get("groq_api"))
-    
+    api_key = os.getenv("groq_api")
+    if not api_key:
+        raise ValueError("Groq API key not found in environment variables.")
+    return Groq(api_key=api_key)
+
+groq_client = get_groq_client()
+
 # Function to extract text from PDF
-def extract_pdf_content(pdf_file):
-    doc = fitz.open(pdf_file)
+def extract_pdf_content(uploaded_file):
+    pdf_stream = BytesIO(uploaded_file.read())  # Convert to file-like object
+    doc = fitz.open(stream=pdf_stream, filetype="pdf")
     content = ""
     for page in doc:
         content += page.get_text()
     return content
-    
+
 # Function to split content into chunks
 def chunk_text(text, chunk_size=500):
     words = text.split()
@@ -32,7 +38,10 @@ def compute_embeddings(text_chunks):
             messages=[{"role": "user", "content": chunk}],
             model="llama3-70b-8192"
         )
-        embeddings.append(np.array(response['choices'][0]['message']['content']))
+        # Convert response to NumPy array
+        embedding_str = response['choices'][0]['message']['content']
+        embedding = np.fromstring(embedding_str, sep=",")
+        embeddings.append(embedding)
     return np.array(embeddings)
 
 # Function to build FAISS index
@@ -61,7 +70,9 @@ def compute_query_embedding(query):
         messages=[{"role": "user", "content": query}],
         model="llama3-70b-8192"
     )
-    return np.array(response['choices'][0]['message']['content']).reshape(1, -1)
+    # Convert to NumPy array
+    embedding_str = response['choices'][0]['message']['content']
+    return np.fromstring(embedding_str, sep=",").reshape(1, -1)
 
 # Streamlit app
 st.title("Generative AI for Electrical Engineering Education with FAISS and Groq")
@@ -72,40 +83,46 @@ uploaded_file = st.sidebar.file_uploader("Upload Study Material (PDF)", type=["p
 topic = st.sidebar.text_input("Enter a topic (e.g., Newton's Third Law)")
 
 if uploaded_file:
-    # Extract and process file content
-    content = extract_pdf_content(uploaded_file)
-    st.sidebar.success(f"{uploaded_file.name} uploaded successfully!")
+    try:
+        # Extract and process file content
+        content = extract_pdf_content(uploaded_file)
+        st.sidebar.success(f"{uploaded_file.name} uploaded successfully!")
 
-    # Chunk and compute embeddings
-    chunks = chunk_text(content)
-    embeddings = compute_embeddings(chunks)
+        # Chunk and compute embeddings
+        chunks = chunk_text(content)
+        embeddings = compute_embeddings(chunks)
 
-    # Build FAISS index
-    index = build_faiss_index(embeddings)
+        # Build FAISS index
+        index = build_faiss_index(embeddings)
 
-    st.write("**File Processed and Indexed for Search**")
-    st.write(f"Total chunks created: {len(chunks)}")
+        st.write("**File Processed and Indexed for Search**")
+        st.write(f"Total chunks created: {len(chunks)}")
+    except Exception as e:
+        st.error(f"Error processing file: {e}")
 
 # Generate study material
 if st.button("Generate Study Material"):
     if topic:
-        st.header(f"Study Material: {topic}")
-        
-        # Compute query embedding
-        query_embedding = compute_query_embedding(topic)
-
-        # Search FAISS index
-        if uploaded_file:
-            results = search_faiss_index(index, query_embedding, chunks, top_k=3)
-            st.write("**Relevant Content from Uploaded File:**")
-            for result, distance in results:
-                st.write(f"- {result} (Similarity: {distance:.2f})")
-        else:
-            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)
-        st.write("**AI-Generated Content (Groq - Llama3-70B-8192):**")
-        st.write(ai_content)
+        try:
+            st.header(f"Study Material: {topic}")
+
+            # Compute query embedding
+            query_embedding = compute_query_embedding(topic)
+
+            # Search FAISS index
+            if uploaded_file:
+                results = search_faiss_index(index, query_embedding, chunks, top_k=3)
+                st.write("**Relevant Content from Uploaded File:**")
+                for result, distance in results:
+                    st.write(f"- {result} (Similarity: {distance:.2f})")
+            else:
+                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)
+            st.write("**AI-Generated Content (Groq - Llama3-70B-8192):**")
+            st.write(ai_content)
+        except Exception as e:
+            st.error(f"Error generating content: {e}")
     else:
         st.warning("Please enter a topic!")