Update app.py

app.py

@@ -1,37 +1,43 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-
-# Load the pre-trained model and tokenizer from Hugging Face Model Hub
-model_id = "HridaAI/Hrida-T2SQL-3B-128k-V0.1"
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, trust_remote_code=True)
-
-# Define the function to generate SQL query from natural language input
-def generate_sql(query):
-    # Tokenize input
-    inputs = tokenizer(query, return_tensors="pt")
-    
-    # Generate the SQL query
-    outputs = model.generate(**inputs, max_new_tokens=256)
-    
-    # Decode the generated output into a string
-    sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    return sql_query
-"""
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=generate_sql,
-    inputs=gr.Textbox(lines=2, placeholder="Enter your natural language question here..."),
-    outputs="text",
-    title="Text to SQL Converter",
-    description="Convert natural language questions into SQL queries using the Hrida-T2SQL-3B model."
-)
+from huggingface_hub import InferenceClient
 
-# Launch the interface
-iface.launch(server_port=8080)
 """
+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("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],åç
+    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]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    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
+
+        response += token
+        yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -54,4 +60,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()