Add application file

app.py

@@ -0,0 +1,52 @@
+import os
+import faiss
+import numpy as np
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+from groq import Groq
+
+api_key = os.getenv("API_KEY")
+
+client = Groq(api_key=api_key)
+
+index = faiss.read_index("/kaggle/working/medicine_index.index")
+
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+model_id = "llama-3.3-70b-versatile"
+
+
+def get_relevant_document(query, index, top_k=1):
+    query_embedding = model.encode([query]).astype(np.float32)
+    D, I = index.search(query_embedding, top_k)
+    return I[0][0], D[0][0]
+
+
+def generate_response_from_groq(query, context):
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {"role": "user", "content": query},
+            {"role": "system", "content": context}
+        ],
+        model=model_id,
+    )
+    return chat_completion.choices[0].message.content
+
+
+def chatbot(user_query):
+    doc_index, similarity_score = get_relevant_document(user_query, index)
+
+    context = f"Medicine details based on index: {doc_index} with similarity score: {similarity_score}"
+
+    response = generate_response_from_groq(user_query, context)
+    return response
+
+
+iface = gr.Interface(fn=chatbot,
+                     inputs="text",
+                     outputs="text",
+                     title="Medicine Chatbot",
+                     description="Ask me about any medicine and get relevant information.")
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+faiss-cpu
+sentence-transformers
+requests
+groq