Update app.py

app.py

@@ -1,64 +1,22 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("gaussalgo/T5-LM-Large-text2sql-spider")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+model_path = 'gaussalgo/T5-LM-Large-text2sql-spider'
+model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
+question = "What is the average, minimum, and maximum age for all French musicians?"
+schema = """
+   "stadium" "Stadium_ID" int , "Location" text , "Name" text , "Capacity" int , "Highest" int , "Lowest" int , "Average" int , foreign_key:  primary key: "Stadium_ID" [SEP] "singer" "Singer_ID" int , "Name" text , "Country" text , "Song_Name" text , "Song_release_year" text , "Age" int , "Is_male" bool , foreign_key:  primary key: "Singer_ID" [SEP] "concert" "concert_ID" int , "concert_Name" text , "Theme" text , "Year" text , foreign_key: "Stadium_ID" text from "stadium" "Stadium_ID" , primary key: "concert_ID" [SEP] "singer_in_concert"  foreign_key: "concert_ID" int from "concert" "concert_ID" , "Singer_ID" text from "singer" "Singer_ID" , primary key: "concert_ID" "Singer_ID"
+"""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+input_text = " ".join(["Question: ",question, "Schema:", schema])
 
-        response += token
-        yield response
+model_inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**model_inputs, max_length=512)
 
+output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+print("SQL Query:")
+print(output_text)
 
 
-if __name__ == "__main__":
-    demo.launch()