{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "aa0c6e52",
   "metadata": {},
   "source": [
    "Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "06252c0a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from dotenv import load_dotenv\n",
    "from openai import OpenAI\n",
    "import json\n",
    "import os\n",
    "import requests\n",
    "from pypdf import PdfReader\n",
    "import gradio as gr\n",
    "\n",
    "from agents import Agent, WebSearchTool, trace, Runner, gen_trace_id, function_tool\n",
    "from agents.model_settings import ModelSettings\n",
    "from pydantic import BaseModel, Field\n",
    "import asyncio\n",
    "import os\n",
    "from typing import Dict\n",
    "from IPython.display import display, Markdown"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "aa257a14",
   "metadata": {},
   "outputs": [],
   "source": [
    "load_dotenv(override=True)\n",
    "openai = OpenAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dd36390e",
   "metadata": {},
   "outputs": [],
   "source": [
    "reader = PdfReader(\"input/dashie_bot_input.pdf\")\n",
    "input = \"\"\n",
    "for page in reader.pages:\n",
    "    text = page.extract_text()\n",
    "    if text:\n",
    "        input += text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6a704414",
   "metadata": {},
   "outputs": [],
   "source": [
    "instructions = f\"You are a data analyst helping connect people having a question about data to the correct dashboard containing the needed data. \\\n",
    "    You are given the full descriptions of the dashboards and each graph and filtering that they contain in the file dashie_bot_input\\\n",
    "    Do not use any information outside of the information provided. If requested data is not in described in the sheet or you do not know answer, refer the requester to #ask_product_owners channel on Slack or directly to Audrius\\\n",
    "    When giving answers, be coincise and practical, share the link to the relevant dashboard\"\n",
    "\n",
    "instructions += f\"\\n\\n## Dashie_bot_input:\\n{input}\\n\\n\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "74fd2e85",
   "metadata": {},
   "outputs": [],
   "source": [
    "sales_manager = Agent(\n",
    "    name=\"@dashie_bot\",\n",
    "    instructions=instructions,\n",
    "    model=\"gpt-4o-mini\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f812f272",
   "metadata": {},
   "outputs": [],
   "source": [
    "def chat(message, history):\n",
    "    messages = [{\"role\": \"system\", \"content\": instructions}] + history + [{\"role\": \"user\", \"content\": message}]\n",
    "    done = False\n",
    "    while not done:\n",
    "\n",
    "        # This is the call to the LLM - see that we pass in the tools json\n",
    "\n",
    "        response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
    "\n",
    "        finish_reason = response.choices[0].finish_reason\n",
    "        \n",
    "        # If the LLM wants to call a tool, we do that!\n",
    "         \n",
    "        if finish_reason==\"tool_calls\":\n",
    "            message = response.choices[0].message\n",
    "            tool_calls = message.tool_calls\n",
    "            results = handle_tool_calls(tool_calls)\n",
    "            messages.append(message)\n",
    "            messages.extend(results)\n",
    "        else:\n",
    "            done = True\n",
    "    return response.choices[0].message.content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "b33f35dc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "* Running on local URL:  http://127.0.0.1:7862\n",
      "* To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7862/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gr.ChatInterface(chat, type=\"messages\").launch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "4d825d46",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\berno\\projects\\agents\\.venv\\Scripts\\python.exe: No module named uv\n"
     ]
    }
   ],
   "source": [
    "uv run gradio deploy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "98bf06fa",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}