ddd

app.py

@@ -2,7 +2,6 @@ import streamlit as st
 import pandas as pd
 from transformers import pipeline, AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
 from peft import PeftModel, PeftConfig
-import gradio as gr
 
 #Note this should be used always in compliance with applicable laws and regulations if used with real patient data.
 
@@ -16,7 +15,8 @@ peft_config = PeftConfig.from_pretrained("pseudolab/K23_MiniMed")
 peft_model = MistralForCausalLM.from_pretrained("pseudolab/K23_MiniMed", trust_remote_code=True)
 peft_model = PeftModel.from_pretrained(peft_model, "pseudolab/K23_MiniMed")
 
-text_generator = pipeline('text-generation', model=peft_model, tokenizer=tokenizer)
+#Upload Patient Data
+uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
 
 # Prepare the context
 def prepare_context(data):
@@ -24,25 +24,23 @@ def prepare_context(data):
     data_str = data.to_string(index=False, header=False)
 
     # Tokenize the data
-    # input_ids = tokenizer.encode(data_str, return_tensors="pt")
+    input_ids = tokenizer.encode(data_str, return_tensors="pt")
 
     # Truncate the input if it's too long for the model
-    # max_length = tokenizer.model_max_length
-    # if input_ids.shape[1] > max_length:
-    #     input_ids = input_ids[:, :max_length]
-    input_ids = data_str
+    max_length = tokenizer.model_max_length
+    if input_ids.shape[1] > max_length:
+        input_ids = input_ids[:, :max_length]
 
     return input_ids
 
-def fn(uploaded_file) -> str:
+if uploaded_file is not None:
     data = pd.read_csv(uploaded_file)
-    ret = ""
+    st.write(data)
 
     # Generate text based on the context
     context = prepare_context(data)
-    # generated_text = pipeline('text-generation', model=peft_model, tokenizer=tokenizer)(context)[0]['generated_text']
-    generated_text = text_generator(context)[0]['generated_text']
-    ret += generated_text
+    generated_text = pipeline('text-generation', model=model)(context)[0]['generated_text']
+    st.write(generated_text)
 
     # Internally prompt the model to data analyze the EHR patient data
     prompt = "You are an Electronic Health Records analyst with nursing school training. Please analyze patient data that you are provided here. Give an organized, step-by-step, formatted health records analysis. You will always be truthful and if you do nont know the answer say you do not know."
@@ -52,15 +50,10 @@ def fn(uploaded_file) -> str:
         input_ids = tokenizer.encode(prompt, return_tensors="pt")
 
         # Generate text based on the prompt
-        # generated_text = pipeline('text-generation', model=peft_model, tokenizer=tokenizer)(input_ids=input_ids)[0]['generated_text']
-        generated_text = text_generator(prompt)[0]['generated_text']
-        ret += generated_text
-
-    return ret
-
-
-demo = gr.Interface(fn=fn, inputs="file", outputs="text", theme="pseudolab/huggingface-korea-theme")
-
-
-if __name__ == "__main__":
-    demo.launch(show_api=False)
+        generated_text = pipeline('text-generation', model=model)(input_ids=input_ids)[0]['generated_text']
+        st.write(generated_text)
+    else:
+        st.write("Please enter patient data")
+        
+else:
+    st.write("No file uploaded")