AISearchEngine.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e1d5b361-1136-479d-b9a7-0fe69c9e949e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import dotenv\n",
    "\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "_ = load_dotenv(find_dotenv()) # read local .env file\n",
    "\n",
    "dotenv.load_dotenv()\n",
    "hf_api_key = os.environ['HF_API_KEY']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9844aadb-ca4e-4af9-8b4e-8d2e7c68c141",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Helper function\n",
    "import requests, json\n",
    "\n",
    "#Summarization endpoint\n",
    "def get_summary(inputs, parameters=None,ENDPOINT_URL=os.environ['HF_API_SUMMARY_BASE']): \n",
    "    headers = {\n",
    "      \"Authorization\": f\"Bearer {hf_api_key}\",\n",
    "      \"Content-Type\": \"application/json\"\n",
    "    }\n",
    "    data = { \"inputs\": inputs }\n",
    "    if parameters is not None:\n",
    "        data.update({\"parameters\": parameters})\n",
    "    response = requests.request(\"POST\",\n",
    "                                ENDPOINT_URL, headers=headers,\n",
    "                                data=json.dumps(data)\n",
    "                               )\n",
    "    \n",
    "    return json.loads(response.content.decode(\"utf-8\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8db16da1-edbf-479e-956f-e182b6efebc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.document_loaders import WebBaseLoader\n",
    "from langchain.chains.summarize import load_summarize_chain\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "97d04666-3245-46c0-913a-be4e459b2224",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.tools import Tool\n",
    "from langchain.utilities import GoogleSearchAPIWrapper\n",
    "\n",
    "search = GoogleSearchAPIWrapper()\n",
    "\n",
    "def top5_results(query):\n",
    "    return search.results(query, 5)\n",
    "\n",
    "\n",
    "tool5 = Tool(\n",
    "    name=\"Google Search Snippets\",\n",
    "    description=\"Search Google for recent results.\",\n",
    "    func=top5_results,\n",
    ")\n",
    "\n",
    "tool1 = Tool(\n",
    "    name=\"Google Search\",\n",
    "    description=\"Search Google for recent results.\",\n",
    "    func=search.run,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "07d9710c-b770-48ec-9df6-a22014f28f39",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import WebBaseLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "ff430a0f-4d9d-4abb-b28c-2e1e7210e0c5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get1Result(query):\n",
    "    return tool1.run(query)\n",
    "    \n",
    "def getLinks(query):\n",
    "    results = tool5.run(query)\n",
    "    #This will return Title, Link and Snippet however for now we are interested in only getting the link\n",
    "    links = []\n",
    "    for item in results:\n",
    "        links.append(item['link'])   \n",
    "    return links\n",
    "    \n",
    "def getContent(query):\n",
    "    summaries = []\n",
    "    links = getLinks(query)\n",
    "    #for now just taking the first website and generating the summary of it.\n",
    "    loader = WebBaseLoader(links)\n",
    "    docs = loader.load()\n",
    "    \n",
    "    # Split the document_list into individual lists\n",
    "    all_documents = [[document] for document in docs]\n",
    "    llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-16k\")\n",
    "    chain = load_summarize_chain(llm, chain_type=\"stuff\")\n",
    "    \n",
    "    # Now, each element in individual_lists is a list containing one Document object\n",
    "    for individual_docs in all_documents:\n",
    "        #reducing the content limit so that it doesn't exceeds openAI context window\n",
    "        individual_docs[0].page_content = individual_docs[0].page_content[:5000]\n",
    "        summary = chain.run(individual_docs)\n",
    "        summaries.append(summary)   \n",
    "   \n",
    "    return summaries, links\n",
    "    \n",
    "def get5Results(query):\n",
    "    output_text = \"\"\n",
    "    i = 1\n",
    "    summaries, links = getContent(query)\n",
    "    for summary, link in zip(summaries, links):\n",
    "        output_text += f\"{i}. Summary: {summary} \\n\\nLink: {link} \\n\\n\"\n",
    "        i += 1\n",
    "    return output_text\n",
    "\n",
    "def AIGoogleSearch(query):\n",
    "    #output = get1Result(query)\n",
    "    output = get5Results(query)\n",
    "    return output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "c051bce0-0067-4362-948f-c64b2adb1b1c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7863\n",
      "Running on public URL: https://63c6dd458928e0fa28.gradio.live\n",
      "\n",
      "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"https://63c6dd458928e0fa28.gradio.live\" 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": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import gradio as gr\n",
    "\n",
    "with gr.Blocks() as demo:\n",
    "    gr.Markdown(\"Welcome to AI Search\")\n",
    "    with gr.Column():\n",
    "        inp = gr.Textbox(label=\"Search Query\")\n",
    "        out = gr.Textbox(label=\"Result\")\n",
    "    btn = gr.Button(\"Run\")\n",
    "    btn.click(fn=AIGoogleSearch, inputs=inp, outputs=out)\n",
    "\n",
    "gr.close_all()\n",
    "\n",
    "demo.launch(share=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1ef468f8-1a5d-4cfe-a2cc-cdb694816599",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}