Adding intention detection

app.py

@@ -26,24 +26,107 @@ retriever = index.as_retriever(similarity_top_k = 3)
 
 import gradio as gr
 
+import re
+
+acknowledgment_keywords_sw = ["sawa", "ndiyo", "naam", "hakika", "asante", "nimeelewa", "nimekupata", "ni kweli",
+                             "kwa hakika", "nimesikia"]
+acknowledgment_keywords_en = ["thanks", "thank you", "thx", "ok", "okay", "great", "got it", "appreciate", "good", "makes sense"]
+follow_up_keywords = ["but", "also", "and", "what", "how", "why", "when",
+                     "lakini", "pia", "na", "nini", "vipi", "kwanini", "wakati"]
+greeting_keywords_sw = ["sasa", "niaje", "habari", "mambo", "jambo", "shikamoo", "marahaba", "hujambo", "hamjambo", "salama", "vipi"]
+greeting_keywords_en = ["hi", "hello", "hey", "how's it", "what's up", "yo", "howdy"]
+
+def contains_exact_word_or_phrase(text, keywords):
+    text = text.lower()
+    for keyword in keywords:
+        if re.search(r'\b' + re.escape(keyword) + r'\b', text):
+            return True
+    return False
+
+def contains_greeting_sw(question):
+    # Check if the question contains acknowledgment keywords
+    # words = question.lower().split()
+    # return any(keyword in words for keyword in greeting_keywords_sw)
+    return contains_exact_word_or_phrase(question, greeting_keywords_sw)
+
+def contains_greeting_en(question):
+    # Check if the question contains acknowledgment keywords
+    # words = question.lower().split()
+    # return any(keyword in words for keyword in greeting_keywords_en)
+    return contains_exact_word_or_phrase(question, greeting_keywords_en)
+
+def contains_acknowledgment_sw(question):
+    # Check if the question contains acknowledgment keywords
+    # words = question.lower().split()
+    # return any(keyword in words for keyword in acknowledgment_keywords_sw)
+    return contains_exact_word_or_phrase(question, acknowledgment_keywords_sw)
+
+def contains_acknowledgment_en(question):
+    # Check if the question contains acknowledgment keywords
+    # words = question.lower().split()
+    # return any(keyword in words for keyword in acknowledgment_keywords_en)
+    return contains_exact_word_or_phrase(question, acknowledgment_keywords_en)
+
+def contains_follow_up(question):
+    # Check if the question contains follow-up indicators
+    return contains_exact_word_or_phrase(question, follow_up_keywords)
+
+def process_acknowledgment_response(question):
+    # Handle simple acknowledgment
+    if contains_acknowledgment_en(question) and not contains_follow_up(question):
+        return "You're welcome! Is there anything else I can help with?"
+    elif contains_acknowledgment_sw(question) and not contains_follow_up(question):
+        return "Karibu! Kuna kitu kingine chochote ninachoweza kusaidia?"
+    return None
+
+def process_greeting_response(question):
+    # Handle simple acknowledgment
+    if contains_greeting_en(question):
+        return "Hi! Can I assist with any question related to HIV?"
+    elif contains_greeting_sw(question):
+        return "Habari! Je, ninaweza kusaidia kwa swali lolote linalohusiana na virusi vya ukimwe?"
+    return None
+
 def nishauri(question: str, conversation_history: list[str]):
+
+    ## If a greeting, then respond accordingly and do not proceed with RAG
+    # Process greeting
+    greet_response = process_greeting_response(question)
+    if greet_response:
+        conversation_history.append({"user": question, "chatbot": greet_response})
+        return greet_response, conversation_history
+
+    ## If user is acknowledging chatbot's response and not asking a follow up, then respond accordingly
+    # Process acknowledgment
+    ack_response = process_acknowledgment_response(question)
+    if ack_response:
+        conversation_history.append({"user": question, "chatbot": ack_response})
+        return ack_response, conversation_history
+
+    ## Otherwise, proceed with RAG
     
+    # Create user history
     context = " ".join([item["user"] + " " + item["chatbot"] for item in conversation_history])
 
+    ## Language detection - we want to run the pipeline in English since our sources are in English
     # Split the string into words
     words = question.split()
 
     # Count the number of words
     num_words = len(words)
 
+    # By default, let's assume the language is English
     lang_question = "en"
-    
+
+    # Language detection is unreliable with fewer that five words, so only check if at least five words
     if num_words > 4:
         lang_question = detect(question)
-    
+        
+    # If language is swahili, then translate question to english
     if lang_question=="sw":
         question = GoogleTranslator(source='sw', target='en').translate(question)
-        
+
+    # Now, retrieve relevant sources
     sources = retriever.retrieve(question)
     source0 = sources[0].text
     source1 = sources[1].text
@@ -69,9 +152,9 @@ def nishauri(question: str, conversation_history: list[str]):
     f" Please use the following content to generate a response: {source0} {source1} {source2}."
     f" Please consider the following background information when generating a response: {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."
+    " If they start with a greeting, just greet them in return and don't share anything else."
     " Do not change the subject or address anything the user didn't directly ask about."
-    " If they respond with an acknowledgement such as 'ok' or 'thanks', simply thank them ask if there is anything else that you can help with.")
+    " If they respond with an acknowledgement, simply thank them ask if there is anything else that you can help with."
 
     completion = client.chat.completions.create(
       model="gpt-4o",