added app infra

app.py

@@ -1,10 +1,21 @@
 import streamlit as st
+from mental_health_raqa import mh_assistant
 
-st.title('OpenAI Key Input')
+
+st.title('Mental Health Assistant :broken_heart:')
 
 # Create a text input box for the OpenAI key
 openai_key = st.text_input('Enter your OpenAI Key', type='password')
 
 # Display the key when the user presses the 'Submit' button
 if st.button('Submit'):
-    st.write(f'Your OpenAI Key is: {openai_key}')
+    if openai_key:
+        query = st.text_input('Enter your query', type='default')
+        if st.button('Ask'):
+            try:
+                response = mh_assistant(openai_key,query)
+                st.write(response)
+            except Exception as e:
+                st.error(f'An error occurred: {e}',icon=':no_entry_sign:')
+    else:
+        st.error('Please enter your OpenAI key',icon=':no_entry_sign:')

mental_health_raqa.py

@@ -1,6 +1,53 @@
 import pandas as pd
+import os 
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.storage import LocalFileStore
+from langchain_openai import ChatOpenAI
+from langchain.chains import RetrievalQA
+from langchain.callbacks import StdOutCallbackHandler
 
-def mental_health_raqa(openai_key):
-    # Load the data
-    data = pd.read_csv('data/raqa.csv')
-    return openai_key
+def create_index():
+    # load the data
+    df_path = 'data/mental_health_QnA2.csv'
+    loader = CSVLoader(file_path = df_path)
+    data = loader.load()
+
+    # create the embeddings model
+    embeddings_model = OpenAIEmbeddings()
+
+    # create the cache backed embeddings in vector store
+    store = LocalFileStore("./cache")
+    cached_embeder = CacheBackedEmbeddings.from_bytes_store(
+        embeddings_model, store, namespace=embeddings_model.model
+    )
+    vector_store = FAISS.from_documents(data, embeddings_model)
+
+    return vector_store.as_retriever()
+
+def setup(openai_key):
+     # Set the API key for OpenAI
+    os.environ["OPENAI_API_KEY"] = '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'
+    retriver = create_index()
+    llm = ChatOpenAI(model="gpt-4")
+    return retriver, llm
+
+
+def mh_assistant(openai_key,query):
+
+    # Setup
+    retriever,llm = setup(openai_key)
+    # Create the QA chain
+    handler = StdOutCallbackHandler()
+
+    qa_with_sources_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=retriever,
+        callbacks=[handler],
+        return_source_documents=True
+    )
+
+    # Ask a question
+    return qa_with_sources_chain({"query":query})