app.py

import json 
import openai
import os

import pandas as pd

import gradio as gr
from collections import deque
from typing import Dict, List, Optional, Any

from langchain import LLMChain, OpenAI, PromptTemplate
from langchain.embeddings import OpenAIEmbeddings
from langchain.llms import BaseLLM
from langchain.vectorstores.base import VectorStore
from pydantic import BaseModel, Field
from langchain.chains.base import Chain
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
from langchain import OpenAI, LLMChain
from langchain.chat_models import ChatOpenAI
import datetime
from datetime import datetime, date, time, timedelta
from llama_index  import GPTSimpleVectorIndex, SimpleDirectoryReader, LLMPredictor, Document, ServiceContext
from langchain.llms import OpenAIChat

import feedparser
import pandas as pd
import numpy as np

from duckduckgo_search import ddg_videos
from duckduckgo_search import ddg

def get_learning_curriculum(openapikey,topic):
    dateforfilesave=datetime.today().strftime("%d-%m-%Y %I:%M%p")
    print(topic)
    print(dateforfilesave)
    if openapikey=='':
        return pd.DataFrame(["Please provide OpenAPI Key"],columns=['ERROR'])
    
    os.environ['OPENAI_API_KEY'] = str(openapikey)

    prompt='You are a training center AI. Give me a detailed curriculum to learn about "{topicforquery}" using search. The curriculum will be a series of learning tasks to be achieved. Give output as a python list of jsons with "task name", "search keyword" to search to complete the task. Donot repeat the taks. For each task name also add a list of "questions" to ask the search results data to select specific articles and complete the curriculum. Remember the search list will be a dataframe of titles & body of the searched article and you may not be able to go through the full article hence these questions should be of types "Which article best suits a learning curriculum?", "Which article is learning oriented?. To reiterate output should be in json with keys task name ex: get beginner training articles for painting, search keyword ex: beginner painting & questions ex: What are top articles for painting?'.format(topicforquery=topic)

    openai.api_key = os.getenv("OPENAI_API_KEY")
    resp=openai.ChatCompletion.create(
      model="gpt-3.5-turbo",
      messages=[
        {"role": "user", "content": prompt}
      ]
    )
    tasklist=json.loads(resp['choices'][0]['message']['content'])

    llm = ChatOpenAI(temperature=0)

    def research_search(search_keyword,question_to_ask,topic):
      llm_predictor = LLMPredictor(llm=OpenAIChat(temperature=0, model_name="gpt-3.5-turbo"))
      service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor)
      keyword=search_keyword
      keyword="+".join(keyword.lower().split())
      keyword=keyword.replace(' and ',' AND ')
      posts = ddg(keyword+' '+topic, safesearch='Off', page=1)
      latestnews_df=pd.DataFrame(posts)
      print(latestnews_df.columns)
      #latestnews_df=latestnews_df.drop_duplicates(subset=['title','link','published'])
      latestnews_df['text']='Title: '+latestnews_df['title']+' Description: '+latestnews_df['body']
      print(latestnews_df['text'].tolist())
      documents=[Document(t) for t in latestnews_df['text'].tolist()]
      index = GPTSimpleVectorIndex.from_documents(documents)
      prompt_query=question_to_ask
      respstr=str(index.query(prompt_query, 
                    service_context=service_context,
                    response_mode="tree_summarize",
                    similarity_top_k=10))
      print("Search response: ",respstr)
      return respstr
    
    finallist=[]
    list1=[]
    list2=[]
    list3=[]
    for i in range(len(tasklist)):
      taskstuff=tasklist[i]
      search_keyword=taskstuff['search keyword']
      print('Task Name: '+taskstuff['task name'])
      finallist.append('Task Name: '+taskstuff['task name'])
      
      for question in taskstuff['questions']:
        response_string=research_search(search_keyword,question,topic)
        finallist.append("  Question: "+question) 
        finallist.append("     "+response_string)
    
        list1.append(taskstuff['task name'])
        list2.append(question) 
        list3.append(response_string)
    
    outputdf=pd.DataFrame()
    outputdf['Task']=list1
    outputdf['Question']=list2
    outputdf['Learning']=list3
    
    return outputdf

with gr.Blocks() as demo:
    gr.Markdown("<h1><center>BabyAGI creates Learning Curriculum</center></h1>")
    gr.Markdown(
        """What are the sectors with positive momentum? What are the macro trends? Which companies have momentum? Sector summaries and much more. \n\nThis is a demo & showcases ChatGPT integrated with real data. It shows how to get real-time data and marry it with ChatGPT capabilities. This demonstrates 'Chain of Thought' thinking using ChatGPT.\n\n4 snapshots are provided for illustration (trends, sector outlook, news summary email, macro trends email)\n\nNote: llama-index & gpt-3.5-turbo are used. The analysis takes roughly 120 secs & may not always be consistent. If ChatGPT API is overloaded you will get an error\n ![visitors](https://visitor-badge.glitch.me/badge?page_id=hra.chatgpt-stock-news-snapshots)"""
        )
    
    with gr.Row() as row:
        with gr.Column():
            textboxtopic = gr.Textbox(placeholder="Enter Topic for Curriculum...", lines=1,label='Topic')
        with gr.Column():
            textboxopenapi = gr.Textbox(placeholder="Enter OpenAPI Key...", lines=1,label='OpenAPI Key')
        
    with gr.Row() as row:
        btn = gr.Button("Generate \nCurriculum")
        
    with gr.Row() as row:
        table1=gr.Dataframe(
            #headers=["Item", "Cost"],
            #datatype=["str", "str","str"],
            label="Learning Curriculum",
        )
    

    btn.click(getstuff, inputs=[textboxopenapi,textboxtopic],outputs=[table1])
    
    
demo.launch(debug=True)