from omegaconf import OmegaConf import streamlit as st import os from PIL import Image import re import sys import datetime from dotenv import load_dotenv 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?" load_dotenv(override=True) def create_tools(cfg): def adjust_response_to_student( text: str = Field(description='the original text.'), 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 text to match the student's age, desired teaching style and language """ instructions = f''' The following is response the teacher is planning to provide to a student based on their question. Please 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 = """ Given a user query, returns a response (str) based on the content of the Justice Harvard lecture transcripts. It can 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, tool_filter_template = '', reranker = "multilingual_reranker_v1", rerank_k = 100, n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.01, summary_num_results = 10, vectara_summarizer = 'vectara-summary-ext-24-05-med-omni', ) return (tools_factory.get_tools( [ adjust_response_to_student, ] ) + tools_factory.standard_tools() + tools_factory.guardrail_tools() + [query_tool] ) def initialize_agent(_cfg): date = datetime.datetime.now().strftime("%Y-%m-%d") bot_instructions = f""" - You are a helpful teacher assistant, with expertise in education in various teaching styles. - Today's date is {date}. - Response in a concise and clear manner, and provide the most relevant information to the student. - Use tools when available instead of depending on your own knowledge. - Always use the rephrase tool at the end in order to ensure it fits the student's age of {_cfg.student_age}, the {_cfg.style} teaching style and the {_cfg.language} language - Always use any guardrails tools to ensure your responses are polite and do not discuss politices. """ def update_func(status_type: AgentStatusType, msg: str): output = f"{status_type.value} - {msg}" st.session_state.log_messages.append(output) agent = Agent( tools=create_tools(_cfg), topic="An educator with expertise in philosophy", custom_instructions=bot_instructions, update_func=update_func ) return agent 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.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=250) 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, 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, bc2 = st.columns([1, 1]) with bc1: if st.button('Start Over'): reset() with bc2: if st.button('Show Logs'): st.session_state.show_logs = not st.session_state.show_logs 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": '🧑‍💻'}) with st.chat_message("user", avatar='🧑‍💻'): print(f"Starting new question: {prompt}\n") st.write(prompt) if st.session_state.messages[-1]["role"] != "assistant": with st.chat_message("assistant", avatar='🤖'): with st.spinner(st.session_state.thinking_message): res = st.session_state.agent.chat(prompt) cleaned = re.sub(r'\[\d+\]', '', res).replace('$', '\\$') message = {"role": "assistant", "content": cleaned, "avatar": '🤖'} st.session_state.messages.append(message) st.rerun() # Display log messages in an expander if st.session_state.show_logs: with st.expander("Agent Log Messages", expanded=True): for msg in st.session_state.log_messages: st.write(msg) if st.button('Close Logs'): st.session_state.show_logs = False st.rerun() sys.stdout.flush() if __name__ == "__main__": launch_bot()