initial commit

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer
+
+# Assuming you have loaded your model and tokenizer
+# Replace this with your actual model and tokenizer
+
+
+# Define the model function for Gradio
+def generate_summary(input_text):
+    # # Tokenize the input text
+    # inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)
+
+    # # Generate summary using the model
+    # outputs = model.generate(**inputs)
+
+    # # Decode the generated summary
+    # summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # return summary
+
+
+    # Create a text generation pipeline
+    # text_generation_pipeline = pipeline("Falconsai/medical_summarization", model=model, tokenizer=tokenizer)
+
+    tokenizer = AutoTokenizer.from_pretrained("Shariar00/medical_summarization_finetune_medical_qa")
+    model = AutoModelForSeq2SeqLM.from_pretrained("Shariar00/medical_summarization_finetune_medical_qa")
+    text_generation_pipeline = pipeline("summarization", model=model, tokenizer=tokenizer)
+
+    # Generate text using the pipeline
+    prompt = "Hello, I am feeling very pain on my leg, I can not walk properly. I have some knee pain also. what can I do now?"
+    output = text_generation_pipeline(input_text, max_length=512, num_return_sequences=1)
+
+    # Print the generated text
+    generated_text = output[0]
+
+
+    return generated_text
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=generate_summary,
+    inputs="text",
+    outputs="text",
+     # Set to True for live updates without restarting the server
+)
+
+# Launch the Gradio interface
+iface.launch()