Upload 2 files

app.py

@@ -0,0 +1,43 @@
+
+import gradio as gr
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from sklearn.neighbors import NearestNeighbors
+
+model = SentenceTransformer('all-MiniLM-L6-v2')
+global_docs = []
+nn_model = None
+doc_embeddings = None
+
+def semantic_search(query, top_k=3):
+    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 {i+1}:\nDocument: {global_docs[idx]}\nDistance: {distances[0][i]:.4f}\n"
+        for i, idx in enumerate(indices[0])
+    ]
+    return "\n".join(results)
+
+def upload_and_index(file):
+    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()]
+    doc_embeddings = model.encode(global_docs)
+    nn_model = NearestNeighbors(n_neighbors=3, metric='euclidean')
+    nn_model.fit(doc_embeddings)
+    return "Documents indexed successfully!"
+
+with gr.Blocks() as demo:
+    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 your query")
+    search_button = gr.Button("Search")
+    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)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+sentence-transformers
+scikit-learn
+numpy