Update app.py

app.py

@@ -1,30 +1,31 @@
-import streamlit 
-import langchain
-from langchain.llms import GenerativeModel
+import gradio
+from transformers import pipeline
 
-# Replace with your Gemini API key
-API_KEY = ""
+# Initialize the Hugging Face model
+model = pipeline(model='google/flan-t5-large')
 
-# Configure the model
-llm = GenerativeModel("google-llm/text-davinci-003", api_key=API_KEY)
 
-def generate_response(user_input):
-  """
-  Sends user input to Gemini and returns its response.
+# Define the chatbot function
+def chatbot(input_text):
 
-  Args:
-      user_input: The user's message.
+    prompt = f"Give the answer of the given input in context from the bhagwat geeta. give suggestions to user which are based upon the meanings of shlok in bhagwat geeta, input = {input_text}"
+    # Generate a response from the Hugging Face model
+    response = model(prompt, max_length=250, do_sample=True)[0]['generated_text'].strip()
+  
+    # Return the bot response
+    return response
 
-  Returns:
-      The generated response from Gemini.
-  """
-  prompt ={user_input}
-  response = llm.generate_content(prompt=prompt)
-  return response.content[0]["text"]
+# Define the Gradio interface
+gradio_interface = gradio.Interface(
+    fn=chatbot,
+    inputs='text',
+    outputs='text',
+    title='Chatbot',
+    description='A weird chatbot conversations experience.',
+    examples=[
+        ['Hi, how are you?']
+    ]
+)
 
-while True:
-  user_input = input("enter your text")
-  if user_input.lower() == "quit":
-    break
-  response = generate_response(user_input)
-  st.write( {response})
+# Launch the Gradio interface
+gradio_interface.launch()