Upload app.py with huggingface_hub

app.py

@@ -1,68 +1,34 @@
-# Install dependencies (Hugging Face will run this in requirements.txt ideally)
-# !pip install langchain langchain-community langchain-google-genai gradio huggingface_hub python-dotenv
-
 import os
 import gradio as gr
-from dotenv import load_dotenv
-
-# Updated imports for latest LangChain (Aug 2025)
-from langchain.chains import LLMChain
-from langchain_core.prompts import PromptTemplate
+from langchain.chat_models import ChatOpenAI
+from langchain import LLMChain, PromptTemplate
 from langchain.memory import ConversationBufferMemory
-from langchain_google_genai import ChatGoogleGenerativeAI
-
-# Load API keys from environment
-load_dotenv()
-os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")
 
-# Try creating a Gemini Flash 2.5 model
-try:
-    llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash", temperature=0)
-    response = llm.invoke("Hello Gemini, can you hear me?")
-    print("✅ API is working!")
-    print("Response:", response.content)
-except Exception as e:
-    print("❌ API Error:", str(e))
-
-# Prompt Template
-template = """As an adventurous and globetrotting college student, 
-you're constantly on the lookout for new cultures, experiences, and breathtaking landscapes. 
-You've visited numerous countries, immersing yourself in local traditions, and you're always eager to swap travel stories 
-and offer tips on exciting destinations.
+OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
 
+template = """You are a helpful assistant to answer all user queries.
 {chat_history}
 User: {user_message}
 Chatbot:"""
 
 prompt = PromptTemplate(
-    input_variables=["chat_history", "user_message"], 
-    template=template
+    input_variables=["chat_history", "user_message"], template=template
 )
 
-# Memory to store chat history
 memory = ConversationBufferMemory(memory_key="chat_history")
 
-# LLM Chain
 llm_chain = LLMChain(
-    llm=llm,
+    llm=ChatOpenAI(temperature='0.5', model_name="gpt-3.5-turbo"),
     prompt=prompt,
-    memory=memory
+    verbose=True,
+    memory=memory,
 )
 
-# Function for Gradio
-def get_text_response(user_message, history):
-    return llm_chain.predict(user_message=user_message)
+def get_text_response(user_message,history):
+    response = llm_chain.predict(user_message = user_message)
+    return response
 
-# Gradio Chat Interface
-demo = gr.ChatInterface(
-    fn=get_text_response,
-    examples=[
-        "How are you doing?",
-        "What are your interests?",
-        "Which places do you like to visit?"
-    ],
-    type="messages"
-)
+demo = gr.ChatInterface(get_text_response)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch() #To create a public link, set `share=True` in `launch()`. To enable errors and logs, set `debug=True` in `launch()`.