Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import ConversationChain
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+# Load pre-trained model and tokenizer from Hugging Face
+model_name = "microsoft/DialoGPT-medium"  # You can replace this with other conversational models
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Create a pipeline for conversational tasks
+hf_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# Wrap the pipeline in a LangChain LLM
+llm = HuggingFacePipeline(pipeline=hf_pipeline)
+
+# Create a conversation chain with memory
+from langchain.memory import ConversationBufferMemory
+memory = ConversationBufferMemory()
+conversation = ConversationChain(llm=llm, memory=memory)
+
+# Define a function for Gradio to handle conversation
+def chatbot(user_input):
+    response = conversation.run(user_input)
+    return response
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 Chatbot with Hugging Face and LangChain")
+    chatbot_interface = gr.Chatbot()
+    user_input = gr.Textbox(label="Type your message:", placeholder="Say something...")
+    submit_button = gr.Button("Send")
+    
+    # Bind the input and output
+    submit_button.click(chatbot, inputs=user_input, outputs=chatbot_interface)
+
+# Launch the app
+demo.launch()