Create app.py

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+
+# Load the model once
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Global storage for documents and index
+global_docs = []
+global_index = None
+
+# Load documents from uploaded file
+def load_documents(file_obj):
+    docs = [line.strip() for line in file_obj if line.strip()]
+    return docs
+
+# Build FAISS index
+def build_index(docs):
+    embeddings = model.encode(docs).astype(np.float32)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+    return index, embeddings
+
+# Semantic 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)
+    results = [
+        f"Rank {rank + 1}:\nDocument: {global_docs[i]}\nL2 Distance: {distances[0][rank]:.4f}\n"
+        for rank, i in enumerate(indices[0])
+    ]
+    return "\n".join(results)
+
+# Handle file upload
+def upload_and_index(file):
+    global global_docs, global_index
+    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!"
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("## 🔍 Semantic Search in Academic Papers")
+    
+    file_input = gr.File(label="Upload Academic Paper (.txt)", file_types=['.txt'])
+    upload_button = gr.Button("Upload & Index")
+    upload_output = gr.Textbox(label="Status")
+
+    query_input = gr.Textbox(label="Enter Search Query")
+    search_button = gr.Button("Search")
+    search_output = gr.Textbox(label="Top 3 Results")
+
+    upload_button.click(upload_and_index, inputs=file_input, outputs=upload_output)
+    search_button.click(semantic_search, inputs=query_input, outputs=search_output)
+
+demo.launch()