updating for single call

app.py

@@ -22,6 +22,7 @@ from llama_index.core import load_index_from_storage
 storage_context = StorageContext.from_defaults(persist_dir="arv_metadata")
 index = load_index_from_storage(storage_context)
 query_engine = index.as_query_engine(similarity_top_k=3, llm=llm)
+retriever = index.as_retriever(similarity_top_k = 3)
 
 import gradio as gr
 
@@ -30,12 +31,24 @@ def nishauri(question: str, conversation_history: list[str]):
     
     context = " ".join([item["user"] + " " + item["chatbot"] for item in conversation_history])
 
-    lang_question = detect(question)
+   # Split the string into words
+    words = question.split()
+
+    # Count the number of words
+    num_words = len(words)
+
+    lang_question = "en"
+    
+    if num_words > 4:
+        lang_question = detect(question)
     
     if lang_question=="sw":
         question = GoogleTranslator(source='sw', target='en').translate(question)
         
-    response = query_engine.query(question)
+    sources = retriever.retrieve(question)
+    source0 = sources[0].text
+    source1 = sources[1].text
+    source2 = sources[2].text
 
     background = ("The person who asked the question is a person living with HIV."
                   " If the person says sasa or niaje, that is swahili slang for hello."
@@ -50,15 +63,17 @@ def nishauri(question: str, conversation_history: list[str]):
            " A high viral load or non-suppressed viral load is any viral load above 200 copies/ml."
            " A suppressed viral load is one below 200 copies / ml.")
 
-    question_final = (
-        f"The user previously asked and answered the following: {context}"
-        f" The user just asked the following question: {question}"
-        f" The following response was generated in response: {response}"
-        f" Please update the response provided only if needed, based on the following background information {background}"
+     question_final = (
+        f" The user previously asked and answered the following: {context}. "
+        f" The user just asked the following question: {question}."
+        f" Please use the following content to generate a response: {source0} {source1} {source2}."
+        f" Please update the response provided only if needed, based on the following background information {background}."
+        " Keep answers brief and limited to the question that was asked."
+        " Do not provide information the user did not ask about. If they start with a greeting, just greet them in return and don't share anything else."
     )
 
     completion = client.chat.completions.create(
-      model="gpt-3.5-turbo",
+      model="gpt-4-turbo",
         messages=[
         {"role": "user", "content": question_final}
       ]
@@ -69,7 +84,7 @@ def nishauri(question: str, conversation_history: list[str]):
     if lang_question=="sw":
         reply_to_user = GoogleTranslator(source='auto', target='sw').translate(reply_to_user)
     
-    conversation_history.append({"user": question, "chatbot": response.response})  
+    conversation_history.append({"user": question, "chatbot": reply_to_user})  
 
     source1 = ("File Name: " +
       response.source_nodes[0].metadata["file_name"] +