Update app.py

app.py

@@ -1,105 +1,111 @@
 import pandas as pd
-
-
-df = pd.read_csv('./Mental_Health_FAQ.csv')
-
-import pandas as pd
-from sentence_transformers import SentenceTransformer
-# Assuming your DataFrame is already loaded as 'df'
-
-context_data = []
-
-for i in range(len(df)):
-  context = f"Question: {df.iloc[i]['Questions']} Answer: {df.iloc[i]['Answers']}"
-  context_data.append(context)
-# print(context_data)
-
-# Embed the contexts
-embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
-context_embeddings = embedding_model.encode(context_data)
-
-#print(f"Number of contexts: {len(context_data)}")
-#print(f"Shape of embeddings: {context_embeddings.shape}")
-
-
 import os
-
-# Get the secret key from the environment
-groq_key = os.environ.get('new_chatAPI_key')
-
-## LLM used for RAG
+from sentence_transformers import SentenceTransformer
 from langchain_groq import ChatGroq
-
-llm = ChatGroq(model="llama-3.3-70b-versatile",api_key=groq_key)
-
-## Embedding model!
 from langchain_huggingface import HuggingFaceEmbeddings
-embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
-
-# create vector store!
 from langchain_chroma import Chroma
-
-vectorstore = Chroma(
-    collection_name="medical_dataset_store",
-    embedding_function=embed_model,
-)
-
-# add data to vector nstore
-vectorstore.add_texts(context_data)
-
-retriever = vectorstore.as_retriever()
-
 from langchain_core.prompts import PromptTemplate
-
-template = ("""You are a mental health professional.
-    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)
-
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
-
-rag_chain = (
-    {"context": retriever, "question": RunnablePassthrough()}
-    | rag_prompt
-    | llm
-    | StrOutputParser()
-)
-
 import gradio as gr
-
-def rag_memory_stream(message, history):
-    partial_text = ""
-    for new_text in rag_chain.stream(message):
-        partial_text += new_text
-        yield partial_text
-
-examples = [
-    "I am not in a good mood", 
-    "what is the possible symptompts of depression?"
-]
-
-description = "Real-time AI App with Groq API and LangChain to Answer medical questions"
-
-
-title = "ThriveTalk Expert :) Try me!"
-demo = gr.ChatInterface(fn=rag_memory_stream,
-                        type="messages",
-                        title=title,
-                        description=description,
-                        fill_height=True,
-                        examples=examples,
-                        theme="glass",
-)
+import logging
+
+# Set up basic logging (optional, but useful)
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+
+try:
+    # Load the data - check for the file path
+    df = pd.read_csv('./Mental_Health_FAQ.csv')
+
+    context_data = []
+    for i in range(len(df)):
+      context = f"Question: {df.iloc[i]['Questions']} Answer: {df.iloc[i]['Answers']}"
+      context_data.append(context)
+
+    # Embed the contexts
+    embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
+    context_embeddings = embedding_model.encode(context_data)
+
+
+    # Get the API Key - important to check this is set
+    groq_key = os.environ.get('new_chatAPI_key')
+    if not groq_key:
+        raise ValueError("Groq API key not found in environment variables.")
+
+
+    # LLM used for RAG
+    llm = ChatGroq(model="llama-3.3-70b-versatile",api_key=groq_key)
+
+    # Embedding model
+    embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+
+
+    # Create the Vector Store!
+    vectorstore = Chroma(
+        collection_name="medical_dataset_store",
+        embedding_function=embed_model,
+    )
+
+    # Add data to vector store
+    vectorstore.add_texts(context_data)
+
+    retriever = vectorstore.as_retriever()
+
+    # Create the prompt template
+    template = ("""You are a mental health professional.
+        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)
+    rag_chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | rag_prompt
+        | llm
+        | StrOutputParser()
+    )
+
+
+    def rag_memory_stream(message, history):
+        partial_text = ""
+        for new_text in rag_chain.stream(message):
+            partial_text += new_text
+            yield partial_text
+
+    examples = [
+        "I am not in a good mood", 
+        "what is the possible symptompts of depression?"
+    ]
+
+    description = "Real-time AI App with Groq API and LangChain to Answer medical questions"
+    title = "ThriveTalk Expert :) Try me!"
+    demo = gr.ChatInterface(fn=rag_memory_stream,
+                            type="messages",
+                            title=title,
+                            description=description,
+                            fill_height=True,
+                            examples=examples,
+                            theme="glass",
+    )
+
+except Exception as e:
+    logging.error(f"An error occurred during initialization: {e}")
+    # If there is an error then return a dummy error text to tell user
+    def error_function(message, history):
+         yield "An error has occurred. Please check the logs"
+    demo = gr.ChatInterface(fn=error_function,
+                         type="messages",
+                         title="ERROR :(",
+                         description="Please check the logs",
+                         fill_height=True,
+                         theme="glass",
+    )
 
 
 if __name__ == "__main__":
     demo.launch()
+