Create app.py

app.py

@@ -0,0 +1,57 @@
+import os
+import gradio as gr
+
+from langchain.agents.agent_types import AgentType
+from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
+
+from langchain_openai import AzureChatOpenAI
+
+from sklearn.datasets import fetch_openml
+
+
+gpt35 = AzureChatOpenAI(
+    api_key=os.environ["AZURE_OPENAI_KEY"],
+    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
+    api_version="2023-05-15",
+    deployment_name="gpt-35-turbo"
+)
+
+bank_data, _ = fetch_openml(data_id=43718, return_X_y=True)
+
+pandas_agent = create_pandas_dataframe_agent(
+    llm=gpt35,
+    df=bank_data,
+    verbose=True,
+    agent_type=AgentType.OPENAI_FUNCTIONS,
+)
+
+
+def predict(user_input):
+
+    try:
+        response = pandas_agent.invoke(user_input)
+
+        prediction = response['output']
+
+    except Exception as e:
+        prediction = e
+        
+    return prediction
+
+
+textbox = gr.Textbox(placeholder="Enter your query here", lines=6)
+
+interface = gr.Interface(
+    inputs=textbox, fn=predict, outputs="text",
+    title="Query BFSI customer information",
+    description="This web API presents an interface to ask questions on customer information stored in a database.",
+    examples=[["What is the average balance maintained by the users?", ""],
+              ["How many users have subscribed to a term deposit?", ""]
+             ]
+)
+
+with gr.Blocks() as demo:
+    interface.launch()
+
+demo.queue(concurrency_count=16)
+demo.launch()