Update app.py

app.py

@@ -1,58 +1,59 @@
 import gradio as gr
-import faiss_cpu as faiss
 import numpy as np
 from sentence_transformers import SentenceTransformer
+from sklearn.neighbors import NearestNeighbors
 
-# Load the model once
+# Load model
 model = SentenceTransformer('all-MiniLM-L6-v2')
 
-# Global storage for documents and index
+# Global storage
 global_docs = []
-global_index = None
+nn_model = None
+doc_embeddings = None
 
-# Load documents from uploaded file
+# Load documents
 def load_documents(file_obj):
     docs = [line.strip() for line in file_obj if line.strip()]
     return docs
 
-# Build FAISS index
+# Build index using Nearest Neighbors
 def build_index(docs):
-    embeddings = model.encode(docs).astype(np.float32)
-    index = faiss.IndexFlatL2(embeddings.shape[1])
-    index.add(embeddings)
-    return index, embeddings
+    embeddings = model.encode(docs)
+    nn = NearestNeighbors(n_neighbors=3, metric='euclidean')
+    nn.fit(embeddings)
+    return nn, embeddings
 
-# Semantic search
+# Search
 def semantic_search(query, top_k=3):
-    if not global_index or not global_docs:
-        return "Please upload a file first."
-    query_embedding = model.encode([query]).astype(np.float32)
-    distances, indices = global_index.search(query_embedding, top_k)
+    if not nn_model or not global_docs:
+        return "Please upload and index a file first."
+    query_vec = model.encode([query])
+    distances, indices = nn_model.kneighbors(query_vec, n_neighbors=top_k)
     results = [
-        f"Rank {rank + 1}:\nDocument: {global_docs[i]}\nL2 Distance: {distances[0][rank]:.4f}\n"
-        for rank, i in enumerate(indices[0])
+        f"Rank {i+1}:\nDocument: {global_docs[idx]}\nDistance: {distances[0][i]:.4f}\n"
+        for i, idx in enumerate(indices[0])
     ]
     return "\n".join(results)
 
-# Handle file upload
+# Upload and index
 def upload_and_index(file):
-    global global_docs, global_index
+    global global_docs, nn_model, doc_embeddings
     contents = file.read().decode("utf-8").splitlines()
     global_docs = [line.strip() for line in contents if line.strip()]
-    global_index, _ = build_index(global_docs)
-    return "Document indexed successfully!"
+    nn_model, doc_embeddings = build_index(global_docs)
+    return "Documents indexed successfully!"
 
-# Gradio Interface
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("## 🔍 Semantic Search in Academic Papers")
-    
-    file_input = gr.File(label="Upload Academic Paper (.txt)", file_types=['.txt'])
+    gr.Markdown("## 🔍 Semantic Search in Academic Papers (No FAISS)")
+
+    file_input = gr.File(label="Upload .txt file", file_types=[".txt"])
     upload_button = gr.Button("Upload & Index")
     upload_output = gr.Textbox(label="Status")
 
-    query_input = gr.Textbox(label="Enter Search Query")
+    query_input = gr.Textbox(label="Enter your query")
     search_button = gr.Button("Search")
-    search_output = gr.Textbox(label="Top 3 Results")
+    search_output = gr.Textbox(label="Results")
 
     upload_button.click(upload_and_index, inputs=file_input, outputs=upload_output)
     search_button.click(semantic_search, inputs=query_input, outputs=search_output)