Create app.py

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+import torch
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+
+# Load the model and tokenizer
+model_name = "nasa-impact/nasa-smd-ibm-st-v2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+def encode_text(text):
+    inputs = tokenizer(text, return_tensors='pt', padding=True, truncation=True)
+    outputs = model(**inputs)
+    return outputs.last_hidden_state.mean(dim=1).detach().numpy()
+
+def find_best_response(user_input, response_pool):
+    user_embedding = encode_text(user_input)
+    response_embeddings = np.array([encode_text(resp) for resp in response_pool])
+    similarities = cosine_similarity(user_embedding, response_embeddings).flatten()
+    best_response_index = np.argmax(similarities)
+    return response_pool[best_response_index]
+
+# Define some example responses for the chatbot to choose from
+response_pool = [
+    "Hello! How can I help you today?",
+    "I'm here to assist you with any questions you have.",
+    "What would you like to know more about?",
+    "Can you please provide more details?",
+    "I'm not sure about that. Could you clarify?"
+]
+
+def chatbot(user_input):
+    best_response = find_best_response(user_input, response_pool)
+    return best_response
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=chatbot,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your message here..."),
+    outputs="text",
+    title="Bi-encoder Chatbot",
+    description="A simple chatbot using a bi-encoder model to find the best response."
+)
+
+# Launch the interface
+iface.launch()