Update app.py

app.py

@@ -3,7 +3,6 @@ from transformers import T5ForConditionalGeneration, T5Tokenizer
 from sentence_transformers import SentenceTransformer
 import faiss
 import torch
-import numpy as np
 import wikipediaapi
 
 # Initialize Wikipedia API with a custom user-agent
@@ -26,26 +25,20 @@ def fetch_wikipedia_articles(titles):
 # Initialize SentenceTransformer for embeddings
 embedder = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 
-# List of Wikipedia articles to retrieve
+# Fetch and create the corpus
 titles = [
-    "Crypto",
+   "Crypto",
     "Finance",
     "Technology",
     "Healthcare",
     "Education"
 ]
-
-# Fetch and create the corpus
-# st.write("Fetching Wikipedia articles...")
-st.write("")
+st.write("Fetching Wikipedia articles...")
 corpus = fetch_wikipedia_articles(titles)
 
 # Generate embeddings for the corpus
-# st.write("Generating embeddings...")
-st.write("")
+st.write("Generating embeddings...")
 embeddings = embedder.encode(corpus, convert_to_tensor=True)
-
-# Convert embeddings to NumPy array
 embeddings_np = embeddings.cpu().numpy()
 
 # Initialize FAISS index and add embeddings
@@ -60,31 +53,28 @@ tokenizer = T5Tokenizer.from_pretrained(model_name)
 # Streamlit interface
 st.title("Humanized AI Text Generator")
 
-# Text input from the user (no character limit, with adjustable height)
-user_input = st.text_area("Enter your query here", height=200)
+# Input from the user
+user_input = st.text_area("Enter your query here (e.g., about a country, concept, etc.)", height=200)
 
-# Button to generate text
 if st.button("Generate Humanized Text"):
-    if user_input.strip():  # Ensure non-empty input
-        # Convert user input to embedding for retrieval
+    if user_input.strip():
+        # Retrieve context from FAISS based on user input embedding
         query_embedding = embedder.encode([user_input], convert_to_tensor=True)
-
-        # Retrieve top 5 related documents from FAISS index
         _, top_k_indices = faiss_index.search(query_embedding.cpu().numpy(), k=5)
-
-        # Retrieve documents based on top_k_indices
+        
+        # Retrieve documents based on FAISS top_k_indices
         def retrieve_documents(top_k_indices):
             return " ".join([corpus[i] for i in top_k_indices[0]])
 
         context = retrieve_documents(top_k_indices)
-
-        # Concatenate query and context
+        
+        # Concatenate user input and context for model input
         input_text = f"{user_input} {context}"
+        
+        # Tokenize input
+        inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)
 
-        # Tokenize input and generate output
-        inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)  # Adjusted max_length for input
-
-        # Generate output without truncation in the generate method
+        # Generate output
         outputs = model.generate(inputs.input_ids, max_length=2000, num_return_sequences=1)
 
         # Decode the generated text
@@ -93,4 +83,4 @@ if st.button("Generate Humanized Text"):
         # Display the generated text
         st.write(generated_text)
     else:
-        st.write("Please enter a query.")
+        st.write("Please enter a valid query.")