app.py

from omegaconf import OmegaConf
import streamlit as st
import os
from PIL import Image
import sys

from dotenv import load_dotenv
load_dotenv(override=True)

from pydantic import Field, BaseModel
from vectara_agent.agent import Agent, AgentStatusType
from vectara_agent.tools import ToolsFactory
from vectara_agent.tools_catalog import rephrase_text

teaching_styles = ['Inquiry-based', 'Socratic', 'traditional']
languages = {'English': 'en', 'Spanish': 'es', 'French': 'fr', 'German': 'de', 'Arabic': 'ar', 'Chinese': 'zh-cn', 
             'Hebrew': 'he', 'Hindi': 'hi', 'Italian': 'it', 'Japanese': 'ja', 'Korean': 'ko', 'Portuguese': 'pt'}
initial_prompt = "How can I help you today?"


def create_tools(cfg):        

    def adjust_response_to_student(
            text: str = Field(description='the text to adjust. may include citations in markdown format.'), 
            age: int = Field(description='the age of the student. An integer'), 
            style: str = Field(description='teaching style'), 
            language: str = Field(description='the language')

        ) -> str:
        """
        Rephrase the provided text to match the student's age, desired teaching style and language
        """
        instructions = f'''
        The following is some text.
        Adjust the response to match the student's age of {age}, the {style} teaching style.
        For example, in the inquiry-based teaching style, choose to ask questions that encourage the student to think critically instead of repsonding directly with the answer.
        Or in the socratic teaching style, choose to ask questions that lead the student to the answer.
        Always respond in the {language} language.''' \
            .replace("{style}", cfg.style) \
            .replace("{language}", cfg.language) \
            .replace("{student_age}", str(cfg.student_age))

        return rephrase_text(text, instructions)


    class JusticeHarvardArgs(BaseModel):
        query: str = Field(..., description="The user query.")

    tools_factory = ToolsFactory(vectara_api_key=cfg.api_key, 
                                 vectara_customer_id=cfg.customer_id, 
                                 vectara_corpus_id=cfg.corpus_id)
    query_tool = tools_factory.create_rag_tool(
        tool_name = "justice_harvard_query",
        tool_description = """
        Answer questions about the justice, morality, politics and related topics,
        based on transcripts of recordings from the Justice Harvard class that includes a lot of content on these topics.
        When using the tool it's best to ask simple short questions. You can break complex questions into sub-queries.
        """,
        tool_args_schema = JusticeHarvardArgs,
        reranker = "multilingual_reranker_v1", rerank_k = 100, 
        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
        summary_num_results = 10,
        vectara_summarizer = 'vectara-summary-ext-24-05-med-omni',
        include_citations = True,
    )

    return (tools_factory.get_tools(
                [
                    adjust_response_to_student,
                ]
            ) +
            tools_factory.standard_tools() + 
            tools_factory.guardrail_tools() +
            [query_tool]
    )

def initialize_agent(_cfg):
    if 'agent' in st.session_state:
        return st.session_state.agent

    bot_instructions = f"""
    - You are a helpful teacher assistant, with expertise in education in various teaching styles.
    - Obtain information using tools to answer the user's query.
    - If the tool cannot provide information relevant to the user's query, tell the user that you are unable to provide an answer.
    - If the tool can provide relevant information, use the adjust_response_to_student tool 
      to rephrase the text (including citations if any) to ensure it fits the student's age of {_cfg.student_age}, 
      the {_cfg.style} teaching style and the {_cfg.language} language.
    - When showing citations, adjust the URL to incorporate the start time of the video, as included in the metadata.
    - When showing citations, use sequential numbers to reference the citations.
    - Response in a concise and clear manner, and provide the most relevant information to the student.
    - Never discuss politics, and always respond politely.
    """

    def update_func(status_type: AgentStatusType, msg: str):
        if status_type != AgentStatusType.AGENT_UPDATE:
            output = f"{status_type.value} - {msg}"
            st.session_state.log_messages.append(output)

    agent = Agent(
        tools=create_tools(_cfg),
        topic="justice, morality, politics, and philosophy",
        custom_instructions=bot_instructions,
        update_func=update_func
    )
    return agent

def toggle_logs():
    st.session_state.show_logs = not st.session_state.show_logs

def launch_bot():
    def reset():
        cfg = st.session_state.cfg
        st.session_state.messages = [{"role": "assistant", "content": initial_prompt, "avatar": "🦖"}]
        st.session_state.thinking_message = "Agent at work..."
        st.session_state.agent = initialize_agent(cfg)
        st.session_state.log_messages = []
        st.session_state.prompt = None
        st.session_state.show_logs = False

    st.set_page_config(page_title="Justice Harvard Teaching Assistant", layout="wide")
    if 'cfg' not in st.session_state:
        cfg = OmegaConf.create({
            'customer_id': str(os.environ['VECTARA_CUSTOMER_ID']),
            'corpus_id': str(os.environ['VECTARA_CORPUS_ID']),
            'api_key': str(os.environ['VECTARA_API_KEY']),
            'style': teaching_styles[0],
            'language': 'English',
            'student_age': 18

        })
        st.session_state.cfg = cfg
        st.session_state.style = cfg.style
        st.session_state.language = cfg.language
        st.session_state.student_age = cfg.student_age

        reset()
    cfg = st.session_state.cfg

    # left side content
    with st.sidebar:
        image = Image.open('Vectara-logo.png')
        st.image(image, width=175)
        st.markdown("## Welcome to the Justice Harvard e-learning assistant demo.\n\n\n")

        st.markdown("\n")
        cfg.style = st.selectbox('Teacher Style:', teaching_styles)
        if st.session_state.style != cfg.style:
            st.session_state.style = cfg.style
            reset()

        st.markdown("\n")
        cfg.language = st.selectbox('Language:', languages.keys())
        if st.session_state.language != cfg.language:
            st.session_state.langage = cfg.language
            reset()

        st.markdown("\n") 
        cfg.student_age = st.number_input(
            'Student age:',  min_value=13, max_value=99, value=cfg.student_age,
            step=1, format='%i'
        )
        if st.session_state.student_age != cfg.student_age:
            st.session_state.student_age = cfg.student_age
            reset()

        st.markdown("\n\n")
        bc1, _ = st.columns([1, 1])
        with bc1:
            if st.button('Start Over'):
                reset()

        st.markdown("---")
        st.markdown(
            "## How this works?\n"
            "This app was built with [Vectara](https://vectara.com).\n\n"
            "It demonstrates the use of Agentic Chat functionality with Vectara"
        )
        st.markdown("---")


    if "messages" not in st.session_state.keys():
        reset()
    
    # Display chat messages
    for message in st.session_state.messages:
        with st.chat_message(message["role"], avatar=message["avatar"]):
            st.write(message["content"])

    # User-provided prompt
    if prompt := st.chat_input():
        st.session_state.messages.append({"role": "user", "content": prompt, "avatar": '🧑‍💻'})
        st.session_state.prompt = prompt  # Save the prompt in session state
        st.session_state.log_messages = []
        st.session_state.show_logs = False
        with st.chat_message("user", avatar='🧑‍💻'):
            print(f"Starting new question: {prompt}\n")
            st.write(prompt)
        
    # Generate a new response if last message is not from assistant
    if st.session_state.prompt:
        with st.chat_message("assistant", avatar='🤖'):
            with st.spinner(st.session_state.thinking_message):
                res = st.session_state.agent.chat(st.session_state.prompt)
                res = res.replace('$', '\\$')  # escape dollar sign for markdown
            message = {"role": "assistant", "content": res, "avatar": '🤖'}
            st.session_state.messages.append(message)
            st.markdown(res)
            st.session_state.prompt = None

    log_placeholder = st.empty()
    with log_placeholder.container():
        if st.session_state.show_logs:
            st.button("Hide Logs", on_click=toggle_logs)
            for msg in st.session_state.log_messages:
                st.text(msg)
        else:
            if len(st.session_state.log_messages) > 0:
                st.button("Show Logs", on_click=toggle_logs)

    sys.stdout.flush()
    
 
if __name__ == "__main__":
    launch_bot()