Update app.py

app.py

@@ -1,52 +1,54 @@
 import pandas as pd
-
-context_data = pd.read_csv("drugs_side_effects_drugs_com.csv")
-
 import os
 from langchain_groq import ChatGroq
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from langchain_core.prompts import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+import gradio as gr
 
-llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=os.environ.get("GROQ_API_KEY"))
+# Load data
+context_data = pd.read_csv("drugs_side_effects_drugs_com.csv")
 
-## Embedding model!
-from langchain_huggingface import HuggingFaceEmbeddings
-embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+# Initialize LLM
+llm = ChatGroq(
+    model="llama-3.1-70b-versatile",
+    api_key=os.environ.get("GROQ_API_KEY")
+)
 
-# create vector store!
-from langchain_chroma import Chroma
+# Initialize embedding model
+embed_model = HuggingFaceEmbeddings(
+    model_name="mixedbread-ai/mxbai-embed-large-v1"
+)
 
+# Create and populate vector store
 vectorstore = Chroma(
     collection_name="medical_dataset_store",
     embedding_function=embed_model,
     persist_directory="./",
 )
-
-# add data to vector nstore
-vectorstore.add_texts(context_data)
-
+vectorstore.add_texts(texts=context_data.values.tolist())  # Convert DataFrame to list of texts
 retriever = vectorstore.as_retriever()
 
-from langchain_core.prompts import PromptTemplate
+# Set up RAG prompt template
+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.
 
-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:""")
+Context: {context}
+Question: {question}
+Answer:"""
 
 rag_prompt = PromptTemplate.from_template(template)
 
-from langchain_core.output_parsers import StrOutputParser
-from langchain_core.runnables import RunnablePassthrough
-
+# Create RAG chain
 rag_chain = (
     {"context": retriever, "question": RunnablePassthrough()}
     | rag_prompt
     | llm
     | StrOutputParser()
 )
-import gradio as gr
 
 def rag_memory_stream(message, history):
     partial_text = ""
@@ -54,29 +56,26 @@ def rag_memory_stream(message, history):
         partial_text += new_text
         yield partial_text
 
-greetingsmessage = """Hello! Welcome to MediGuide ChatBot. I'm here to provide you with quick and accurate information on medical drugs. 
-Whether you need details on usage, side effects , etc feel free to ask. Let's enhance patient care together!"""
-
-initial_history = [("", greetingsmessage)]
-
-title = "MediGuide ChatBot"
+# Gradio interface setup
+greetings_message = """Hello! Welcome to MediGuide ChatBot. I'm here to provide you with quick and 
+accurate information on medical drugs. Whether you need details on usage, side effects, etc. feel 
+free to ask. Let's enhance patient care together!"""
 
+initial_history = [("", greetings_message)]
 
+# Create Gradio interface
 demo = gr.Interface(
-    title=title,
+    title="MediGuide ChatBot",
     fn=rag_memory_stream,
     inputs=[
-    gr.Chatbot(value=initial_history, label="Chat History"),"text"
+        gr.Chatbot(value=initial_history, label="Chat History"),
+        gr.Textbox(label="Your Message", placeholder="Type your message here...")
     ],
     outputs=gr.Chatbot(label="Chat History"),
     allow_flagging="never",
-    fill_height=True,
-    theme="glass",
+    theme="glass"
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
-
-
-
+    # Launch with sharing enabled to avoid localhost issues
+    demo.launch(share=True)