161 lines
5.1 KiB
Python
161 lines
5.1 KiB
Python
|
|
from pathlib import Path
|
|
from shared_config import AgenticAIConfig, create_logger, logger
|
|
import streamlit as st
|
|
from dotenv import load_dotenv
|
|
from agent_workflows.orchestration import runAgenticWorkflow
|
|
from utilities.pdf_tools_v2 import export_to_pdf
|
|
from datetime import datetime
|
|
|
|
|
|
#2- Loading Env Variables
|
|
load_dotenv() # It will load all the Env Variables
|
|
|
|
#3- Set Page Config
|
|
st.set_page_config(
|
|
page_title="Simplilearn Capstone Project", #Show it in the Tab
|
|
page_icon="🤖",
|
|
layout="wide"
|
|
)
|
|
|
|
#4- Initialize Config
|
|
if "config" not in st.session_state:
|
|
st.session_state.config = AgenticAIConfig()
|
|
config = st.session_state.config
|
|
|
|
#5- Initialize Streamlit- Conversation History
|
|
if "chat_history" not in st.session_state:
|
|
st.session_state.chat_history=[]
|
|
|
|
#6- Setting dict for Available Models
|
|
#llm_model = "gpt-5-nano" #Output~ 0.4 US$ / 1M tokens
|
|
#llm_model = "gpt-4o-mini" #Output~ 0.6 US$ / 1M tokens
|
|
#llm_model = "gpt-5.4-nano" #Output~ 1.25 US$ / 1M tokens
|
|
#llm_model = "gpt-5-mini" #Output~ 2 US$ / 1M tokens
|
|
#llm_model = "gpt-5.4-mini" #Output~ 4.50 US$ / 1M tokens
|
|
#llm_model = "gpt-4o" #Output~ 10 US$ / 1M tokens
|
|
#llm_model = "gpt-5.5" #Output~ 30 US$ / 1M tokens
|
|
MODEL_REGISTRY={
|
|
"OpenAI":["gpt-4o-mini","gpt-5-mini","gpt-5.4-nano","gpt-4.1","gpt-4o","gpt-3.5-turbo"],
|
|
"Ollama":["llama3.1","gemma4:e4b","gpt-oss:20b","qwen2.5-coder:14b","mistral-small3.2"],
|
|
}
|
|
|
|
#7- Creating Sidebar
|
|
with st.sidebar:
|
|
st.title("LLM Configuration")
|
|
config.provider = st.selectbox(
|
|
"LLM Provider",
|
|
list(MODEL_REGISTRY.keys())
|
|
)
|
|
|
|
#Dynamic Model Selection Logic
|
|
available_models = MODEL_REGISTRY[config.provider]
|
|
|
|
config.model = st.selectbox(
|
|
"Model",
|
|
available_models
|
|
)
|
|
|
|
config.temperature= st.slider(
|
|
"Temperature",
|
|
min_value=0.0,
|
|
max_value=2.0,
|
|
value=config.temperature,
|
|
step=0.1
|
|
)
|
|
|
|
config.max_tokens=st.slider(
|
|
"Max Tokens",
|
|
min_value=100,
|
|
max_value=10000,
|
|
value=config.max_tokens,
|
|
step=100
|
|
)
|
|
|
|
st.divider()
|
|
|
|
# Display Current Configurations Separately
|
|
st.subheader("Current Configuration:")
|
|
|
|
st.write(f"**Provider:** {config.provider}")
|
|
st.write(f"**Model:** {config.model}")
|
|
st.write(f"**Temperature:** {config.temperature}")
|
|
st.write(f"**Max Token:** {config.max_tokens}")
|
|
|
|
|
|
#8- Setting Page Title
|
|
st.title("🤖 Simplilearn Agentic AI Capstone: Research and GTM Planning")
|
|
|
|
#9- Creating User Input Section
|
|
config.user_query = st.text_area(
|
|
"Enter the product or service you want to research and plan a GTM strategy: ",
|
|
value = config.user_query,
|
|
height=200,
|
|
placeholder = "Example: Electrical bicycle, Burger shop in Tokyo, New AI-powered project management tool targeting small businesses, ..."
|
|
)
|
|
# Create Response Button
|
|
if st.button("Generate Response", type="primary"):
|
|
if not config.user_query.strip():
|
|
st.warning("Please enter a prompt before clicking the button")
|
|
else:
|
|
#Create logger
|
|
if logger is not None:
|
|
if logger.hasHandlers():
|
|
logger.removeHandler(logger.handlers[0]) # Remove existing handlers
|
|
create_logger()
|
|
#Store the User Query for displaying in conversation History on Streamlit
|
|
st.session_state.chat_history.append(
|
|
{
|
|
"role": "user",
|
|
"message": config.user_query
|
|
}
|
|
)
|
|
|
|
logger.info("Product or service to research and plan a GTM strategy: "+config.user_query)
|
|
|
|
# Create a Spinner until response is generated
|
|
with st.spinner("AI Agent is Thinking..."):
|
|
# Call CrewAI FLow
|
|
runAgenticWorkflow(config)
|
|
|
|
#Export the final GTM document to PDF
|
|
logger.info("Creating PDF...")
|
|
pdf_fiename_prefix = "Agentic_AI_Generated_GTM_Document"
|
|
script_dir = Path(__file__).parent
|
|
target_dir = script_dir / "output"
|
|
target_dir.mkdir(parents=True, exist_ok=True)
|
|
now = datetime.now()
|
|
formatted_DateTime = now.strftime("%Y-%m-%d_%H%M%S")
|
|
pdfpath = f"""output/{pdf_fiename_prefix}_{formatted_DateTime}.pdf"""
|
|
export_to_pdf(
|
|
llm_response=config.response,
|
|
output_filename=pdfpath)
|
|
|
|
logger.info("PDF Exported Successfully at: "+pdfpath)
|
|
|
|
|
|
#Store the response for display in conversation history
|
|
st.session_state.chat_history.append(
|
|
{
|
|
"role": "assistant",
|
|
"message": config.response
|
|
}
|
|
)
|
|
st.session_state.config= config
|
|
|
|
|
|
#10- Creating Response Section
|
|
st.subheader("Conversation History")
|
|
|
|
for chat in st.session_state.chat_history:
|
|
if chat["role"]=="user":
|
|
with st.chat_message("user"):
|
|
st.write(chat["message"])
|
|
else:
|
|
with st.chat_message("assistant"):
|
|
st.write(chat["message"])
|
|
|
|
#11- Creating the button for Users to clear all the chats from the UI
|
|
if st.sidebar.button("Clear Chat"):
|
|
st.session_state.chat_history=[]
|
|
st.rerun() |