{
"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": [
""
],
"text/plain": [
""
]
},
"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
}