Update app.py

app.py

@@ -1,13 +1,5 @@
 import pandas as pd
 
-df = pd.read_csv("./drugs_side_effects_drugs_com.csv")
-df.info()
-
-df = df[['drug_name', 'medical_condition', 'side_effects']]
-df.dropna(inplace=True)
-
-df.info()
-
 context_data = pd.read_csv("drugs_side_effects_drugs_com.csv")
 
 import os
@@ -28,15 +20,9 @@ vectorstore = Chroma(
     persist_directory="./",
 )
 
-vectorstore.get().keys()
-
 # add data to vector nstore
 vectorstore.add_texts(context_data)
 
-query = "What drug that causes these side effects hives ; difficulty breathing; swelling of your face, lips, tongue, or throat."
-docs = vectorstore.similarity_search(query)
-print(docs[0].page_content)
-
 retriever = vectorstore.as_retriever()
 
 from langchain_core.prompts import PromptTemplate
@@ -45,11 +31,8 @@ template = ("""You are a medical expert.
     Use the provided context to answer the question.
     If you don't know the answer, say so. Explain your answer in detail.
     Do not discuss the context in your response; just provide the answer directly.
-
     Context: {context}
-
     Question: {question}
-
     Answer:""")
 
 rag_prompt = PromptTemplate.from_template(template)
@@ -64,20 +47,6 @@ rag_chain = (
     | StrOutputParser()
 )
 
-from IPython.display import display, Markdown
-
-response = rag_chain.invoke("What drug that causes these side effects hives ; difficulty breathing; swelling of your face, lips, tongue, or throat")
-Markdown(response)
-
-from IPython.display import display, Markdown
-
-response = rag_chain.invoke("What is Capital of Greece?")
-Markdown(response)
-
-"""# Deployment
-
-"""
-
 import gradio as gr
 
 def rag_memory_stream(text):
@@ -86,6 +55,10 @@ def rag_memory_stream(text):
         partial_text += new_text
         yield partial_text
 
+examples = ['I feel dizzy', 'what is the possible sickness for fatigue']
+
+
+
 
 title = "MediGuide ChatBot"
 demo = gr.Interface(
@@ -93,6 +66,7 @@ demo = gr.Interface(
     fn=rag_memory_stream,
     inputs="text",
     outputs="text",
+    examples=examples,
     allow_flagging="never",
 )
 
@@ -100,36 +74,5 @@ demo = gr.Interface(
 if __name__ == "__main__":
     demo.launch()
 
-"""# Evaluating Using Blue Score and Rouge Score"""
-
-# qa_pair = []
-# for i in range(len(context_data)):
-#   drug_name = str(context_data['drug_name'][i])
-#   medical_condition = str(context_data['medical_condition'][i])
-#   side_effects = str(context_data['side_effects'][i])
-
-#   Question = f"What are the side effect of {drug_name} ?"
-#   Answer = f"Side Effects: {side_effects}"
-
-#   qa_pair.append([Question,Answer])
-
-# df = pd.DataFrame(qa_pair, columns=['Questions', 'Answers'])
-
-# question = [df['Questions'][0]]
-
-# import sacrebleu
-# from rouge_score import rouge_scorer
-
-# predicted_answer = rag_chain.invoke("What are the side effects of doxycycline?")
-# predicted_answer
-
-# reference_answer =df['Answers'][0]
-# reference_answer
-
-# blue_score = sacrebleu.corpus_bleu([predicted_answer], reference_answer).score
-# blue_score
 
-# scorer = rouge_scorer.RougeScorer(['rougeL'], use_stemmer=True)
-# rouge_score = scorer.score(reference_answer, predicted_answer)
-# rouge_score