initial app commit

app.py

@@ -0,0 +1,128 @@
+import os
+os.environ["OPENAI_API_KEY"] = "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"
+
+from llama_index.llms.openai import OpenAI
+from llama_index.core.schema import MetadataMode
+import openai
+from openai import OpenAI as OpenAIOG
+import logging
+import sys
+llm = OpenAI(temperature=0.0, model="gpt-4-turbo")
+client = OpenAIOG()
+
+from langdetect import detect
+from langdetect import DetectorFactory
+DetectorFactory.seed = 0
+from deep_translator import GoogleTranslator
+
+# Load index
+from llama_index.core import VectorStoreIndex
+from llama_index.core import StorageContext
+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
+
+def nishauri(question: str, ccc_user: str, conversation_history: list[str]):
+    
+    context = " ".join([item["user"] + " " + item["chatbot"] for item in conversation_history])
+
+    # Get patient info from DB
+    engine = create_engine('sqlite:///nishauri.db')
+    
+    with engine.connect() as connection:
+        # Select data using a parameterized query
+        result = connection.execute(
+            text("SELECT visit_date, visit_type, regimen, viral_load FROM nishauri WHERE ccc_no = :ccc_no"),
+            {"ccc_no": ccc_user}
+        )
+    
+    # Fetch and print results
+    row = result.fetchall()
+
+    last_appt = row[0][0]
+    appt_purpose = row[0][1]
+    regimen = row[0][2]
+    vl_result = row[0][3]
+    
+    
+    # Detect language of question - if Swahili, translate to English
+    # only do this if there are at least 5 words in the text, otherwise lang detection is unreliable
+    
+    # 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)
+    
+#     lang_question = detect(question)
+
+    if lang_question=="sw":
+        question = GoogleTranslator(source='sw', target='en').translate(question)                   
+    
+    sources = retriever.retrieve(question)
+    source0 = sources[0].text
+    source1 = sources[1].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. Just say hello back and ask how you can help."
+                  " Recognize that they already have HIV and do not suggest that they have to get tested"
+                  " for HIV or take post-exposure prophylaxis, as that is not relevant, though their partners perhaps should."  
+                  " Do not suggest anything that is not relevant to someone who already has HIV."
+                  " Do not mention in the response that the person is living with HIV."
+                  f" The person's last appointment was on {last_appt} and the purpose was {appt_purpose}. "
+                  f" The person is on the following regimen for HIV: {regimen}. "
+                  f" The person's most recent viral load result was {vl_result}. "
+                  " The following information about viral loads is authoritative for any question about viral loads:"
+                  " Under 50 copies/ml is low detectable level,"
+                  " 50 - 199 copies/ml is low level viremia, 200 - 999 is high level viremia, and "
+                  " 1000 and above is suspected treatment failure." 
+                  " 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" Please use the following content to generate a response: {source0} {source1}."
+        f" The following background on the user should also inform the response as needed: {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-4-turbo",
+        messages=[
+        {"role": "user", "content": question_final}
+      ]
+    )
+
+    reply_to_user = completion.choices[0].message.content
+    
+    
+    # If initial question was in Swahili, translate response back to Swahili
+    if lang_question=="sw":
+        reply_to_user = GoogleTranslator(source='auto', target='sw').translate(reply_to_user)
+    
+    conversation_history.append({"user": question, "chatbot": reply_to_user})   
+
+    return reply_to_user, conversation_history
+
+
+demo = gr.Interface(
+    title = "Nishauri Chatbot Demo",
+    fn=nishauri,
+    inputs=[gr.Textbox(label="question", placeholder="Type your question here..."),
+            gr.Textbox(label="CCC", placeholder="Type your ccc here..."),
+            gr.State(value = [])],
+    outputs=["text", gr.State()],
+)
+
+demo.launch()