Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 import streamlit as st
 import PyPDF2
 import requests
+import numpy as np
 import faiss
 from groq import Groq
 
@@ -35,20 +36,20 @@ def chunk_text(text, max_length=500):
         chunks.append(chunk.strip())
     return chunks
 
-# Function to compute simple embeddings
+# Function to compute embeddings using NumPy
 def compute_embeddings(chunks):
     embeddings = []
     for chunk in chunks:
-        vector = [ord(char) for char in chunk[:300]]  # Truncate to 300 characters
-        padded_vector = vector + [0] * (300 - len(vector))  # Zero-pad to fixed size
+        vector = np.array([ord(char) for char in chunk[:300]], dtype=np.float32)  # Truncate to 300 characters
+        padded_vector = np.pad(vector, (0, 300 - len(vector)), mode="constant")
         embeddings.append(padded_vector)
-    return embeddings
+    return np.vstack(embeddings)
 
 # Function to create FAISS index
 def create_faiss_index(embeddings):
-    dimension = len(embeddings[0])
+    dimension = embeddings.shape[1]
     index = faiss.IndexFlatL2(dimension)
-    index.add(faiss.FloatVectorArray(embeddings))
+    index.add(embeddings)
     return index
 
 # Function to query Groq API
@@ -78,8 +79,8 @@ def main():
     question = st.text_input("Ask a question based on the document:")
     if question:
         st.write("Searching for relevant chunks...")
-        question_embedding = compute_embeddings([question])[0]
-        _, indices = index.search(faiss.FloatVectorArray([question_embedding]), k=1)
+        question_embedding = compute_embeddings([question])[0].reshape(1, -1)
+        distances, indices = index.search(question_embedding, k=1)
         relevant_chunk = chunks[indices[0][0]]
 
         st.write("Generating answer using Groq API...")
@@ -90,3 +91,4 @@ def main():
 if __name__ == "__main__":
     main()
 
+