Spaces:
Sleeping
Sleeping
| import os | |
| os.environ["OPENAI_API_KEY"] | |
| 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-3.5-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, conversation_history: list[str]): | |
| context = " ".join([item["user"] + " " + item["chatbot"] for item in conversation_history]) | |
| # 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) | |
| 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." | |
| " 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." | |
| " 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} {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-4-turbo", | |
| messages=[ | |
| {"role": "user", "content": question_final} | |
| ] | |
| ) | |
| reply_to_user = completion.choices[0].message.content | |
| 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}) | |
| source1 = ("File Name: " + | |
| response.source_nodes[0].metadata["file_name"] + | |
| "\nPage Number: " + | |
| response.source_nodes[0].metadata["page_label"] + | |
| "\n Source Text: " + | |
| response.source_nodes[0].text) | |
| source2 = ("File Name: " + | |
| response.source_nodes[1].metadata["file_name"] + | |
| "\nPage Number: " + | |
| response.source_nodes[1].metadata["page_label"] + | |
| "\n Source Text: " + | |
| response.source_nodes[1].text) | |
| source3 = ("File Name: " + | |
| response.source_nodes[2].metadata["file_name"] + | |
| "\nPage Number: " + | |
| response.source_nodes[2].metadata["page_label"] + | |
| "\n Source Text: " + | |
| response.source_nodes[2].text) | |
| return response, source1, source2, source3, conversation_history | |
| inputs = [gr.Textbox(lines=10, label="Question"), | |
| gr.State(value=[])] | |
| outputs = [ | |
| gr.Textbox(label="Chatbot Response", type="text"), | |
| gr.Textbox(label="Source 1", max_lines = 10, autoscroll = False, type="text"), | |
| gr.Textbox(label="Source 2", max_lines = 10, autoscroll = False, type="text"), | |
| gr.Textbox(label="Source 3", max_lines = 10, autoscroll = False, type="text"), | |
| gr.State() | |
| ] | |
| gr.Interface(fn=nishauri, inputs=inputs, outputs=outputs, title="Nishauri Chatbot", | |
| description="Enter a question and see the processed outputs in collapsible boxes.").launch() |