Update app.py

app.py

@@ -4,10 +4,18 @@ from huggingface_hub import InferenceClient
 from textblob import TextBlob
 from langchain.prompts import PromptTemplate  
 from dotenv import load_dotenv
+import pandas as pd
 
 # Load environment variables
 load_dotenv()
 
+# Load the drug-side effects dataset
+df = pd.read_csv('./drugs_side_effects_drugs_com.csv')
+df = df[['drug_name', 'side_effects']].dropna()
+
+# Create a set of valid drug names to compare user queries
+valid_drugs = set(df['drug_name'].str.lower())
+
 # Configure Hugging Face API
 client = InferenceClient(
     "microsoft/Phi-3-mini-4k-instruct",
@@ -39,9 +47,9 @@ prompt_template = PromptTemplate(
     template="{system_prompt}\n\nUser: {user_input}\nAssistant:"
 )
 
-
 st.title("CareBot: AI Medical Assistant for Drug Information and Side Effects")
 
+# Initialize the session state
 if "messages" not in st.session_state:
     st.session_state["messages"] = [
         {
@@ -61,21 +69,15 @@ if "messages" not in st.session_state:
         }
     ]
 
-# if "messages" not in st.session_state:
-#     st.session_state["messages"] = [
-#         {"role": "assistant", "content": "Hi there! I'm Treasure, your friendly pharmacist. 
-#         This AI-powered chatbot provides reliable information about drugs, their side effects, and related medical conditions. Powered by the Groq API and LangChain, it delivers real-time, accurate responses.
-#         Example Questions:
-#             What are the side effects of aspirin?
-#             Can ibuprofen cause dizziness?
-#         Disclaimer: This chatbot is for informational purposes only and not a substitute for professional medical advice.
-#         How can I help you today?"}
-#     ]
-
 # Display previous messages
 for msg in st.session_state.messages:
     st.chat_message(msg["role"]).write(msg["content"])
 
+# Function to check if the user's query is relevant to the dataset
+def is_relevant_query(query):
+    query_tokens = set(query.lower().split())
+    return bool(valid_drugs.intersection(query_tokens))
+
 # Chat input and processing
 if prompt := st.chat_input():
     # Append user message to the session state
@@ -85,33 +87,37 @@ if prompt := st.chat_input():
     # Sentiment Analysis
     user_sentiment = TextBlob(prompt).sentiment.polarity
 
-    # Craft System Prompt based on sentiment
-    system_prompt = SYSTEM_PROMPT_GENERAL
-    if user_sentiment < 0:  # User expresses negative sentiment
-        system_prompt = f"""{system_prompt} 
-        The user seems to be feeling down. Prioritize empathetic responses and open-ended questions."""
-
-    # Format prompt using LangChain's PromptTemplate
-    formatted_prompt = prompt_template.format(
-        system_prompt=system_prompt,
-        user_input=prompt
-    )
-
-    # Generate a response using Hugging Face API
-    response = ""
-    for message in client.chat_completion(
-        messages=[{"role": "user", "content": formatted_prompt}],
-        max_tokens=500,
-        stream=True,
-    ):
-        response += message.choices[0].delta.content
-
-    # Process response for specific tokens
-    if "Ashley:" in response:
-        response = response.split("Treasure:")[1].strip()
-    elif "User:" in response:
-        response = response.split("Assistant:")[1].strip()
+    # Check if the query is relevant to the drug-side effects dataset
+    if not is_relevant_query(prompt):
+        response = "I'm sorry, but your question seems to be out of my scope. Please ask about drugs, side effects, or related medical conditions."
+    else:
+        # Craft System Prompt based on sentiment
+        system_prompt = SYSTEM_PROMPT_GENERAL
+        if user_sentiment < 0:  # User expresses negative sentiment
+            system_prompt = f"""{system_prompt} 
+            The user seems to be feeling down. Prioritize empathetic responses and open-ended questions."""
+
+        # Format prompt using LangChain's PromptTemplate
+        formatted_prompt = prompt_template.format(
+            system_prompt=system_prompt,
+            user_input=prompt
+        )
+
+        # Generate a response using Hugging Face API
+        response = ""
+        for message in client.chat_completion(
+            messages=[{"role": "user", "content": formatted_prompt}],
+            max_tokens=500,
+            stream=True,
+        ):
+            response += message.choices[0].delta.content
+
+        # Process response for specific tokens
+        if "Ashley:" in response:
+            response = response.split("Treasure:")[1].strip()
+        elif "User:" in response:
+            response = response.split("Assistant:")[1].strip()
 
     # Append assistant message to the session state
     st.session_state.messages.append({"role": "assistant", "content": response.strip()})
-    st.chat_message("assistant").write(response.strip())
+    st.chat_message("assistant").write(response.strip())