Create explore_metadata.ipynb

explore_metadata.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a600d7fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json \n",
+    "with open('metadata.jsonl', 'r') as f: \n",
+    "    json_list = list(f)\n",
+    "\n",
+    "json_QA = []\n",
+    "for json_str in json_list: \n",
+    "    json_data = json.loads(json_str)\n",
+    "    json_QA.append(json_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "fa5d8eb8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "==================================================\n",
+      "Task ID: d1af70ea-a9a4-421a-b9cc-94b5e02f1788\n",
+      "Question: As of the 2020 census, what was the population difference between the largest county seat and smallest county seat, by land area of the county seat, in Washington state? For population figures, please use the official data from data.census.gov. Please report the integer difference.\n",
+      "Level: 2\n",
+      "Final Answer: 736455\n",
+      "Annotator Metadata: \n",
+      "  ├── Steps: \n",
+      "  │      ├── Step 1: Using a web browser, access a search engine and conduct a search, \"Washington cities by area\"\n",
+      "  │      ├── Step 2: Navigate to the second search result, https://en.wikipedia.org/wiki/List_of_municipalities_in_Washington\n",
+      "  │      ├── Step 3: Evaluate the page contents, finding the largest and smallest county seats by land area, Seattle and Cathlamet\n",
+      "  │      ├── Step 4: Using a web browser, navigate to https://data.census.gov/\n",
+      "  │      ├── Step 5: Using the website's search area, conduct a search, Seattle, Washington\n",
+      "  │      ├── Step 6: Record the reported 2020 Decennial Census population of Seattle, Washington, 737,015\n",
+      "  │      ├── Step 7: Using the website's search area, conduct a search, Cathlamet, Washington\n",
+      "  │      ├── Step 8: Record the reported 2020 Decennial Census population of Cathlamet, Washington, 560\n",
+      "  │      ├── Step 9: Using a calculator, find the difference in populations,\n",
+      "  │      ├── \n",
+      "  │      ├── 737,015 - 560\n",
+      "  │      ├── 736,455\n",
+      "  │      ├── Step 10: Report the correct answer to my user in the requested format, \"736,455\"\n",
+      "  ├── Number of steps: 10\n",
+      "  ├── How long did this take?: 5 minutes\n",
+      "  ├── Tools:\n",
+      "  │      ├── 1. A web browser\n",
+      "  │      ├── 2. A search engine\n",
+      "  │      ├── 3. A calculator\n",
+      "  └── Number of tools: 3\n",
+      "==================================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "import random\n",
+    "random_samples = random.sample(json_QA, 1)\n",
+    "for sample in random_samples:\n",
+    "    print(\"=\" * 50)\n",
+    "    print(f\"Task ID: {sample['task_id']}\")\n",
+    "    print(f\"Question: {sample['Question']}\")\n",
+    "    print(f\"Level: {sample['Level']}\")\n",
+    "    print(f\"Final Answer: {sample['Final answer']}\")\n",
+    "    print(f\"Annotator Metadata: \")\n",
+    "    print(f\"  ├── Steps: \")\n",
+    "    for step in sample['Annotator Metadata']['Steps'].split('\\n'):\n",
+    "        print(f\"  │      ├── {step}\")\n",
+    "    print(f\"  ├── Number of steps: {sample['Annotator Metadata']['Number of steps']}\")\n",
+    "    print(f\"  ├── How long did this take?: {sample['Annotator Metadata']['How long did this take?']}\")\n",
+    "    print(f\"  ├── Tools:\")\n",
+    "    for tool in sample['Annotator Metadata']['Tools'].split('\\n'):\n",
+    "        print(f\"  │      ├── {tool}\")\n",
+    "    print(f\"  └── Number of tools: {sample['Annotator Metadata']['Number of tools']}\")\n",
+    "print(\"=\" * 50)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "05076516",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
+    "from langchain_community.vectorstores import SupabaseVectorStore\n",
+    "from supabase.client import Client, create_client\n",
+    "\n",
+    "\n",
+    "load_dotenv()\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-mpnet-base-v2\") #  dim=768\n",
+    "\n",
+    "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
+    "supabase_key = os.environ.get(\"SUPABASE_SERVICE_ROLE_KEY\")\n",
+    "supabase: Client = create_client(supabase_url, supabase_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "aa1402e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema import Document\n",
+    "docs = []\n",
+    "cnt = 0 \n",
+    "for sample in json_QA:\n",
+    "    content = f\"Question : {sample['Question']}\\n\\nFinal answer : {sample['Final answer']}\"\n",
+    "    doc = {\n",
+    "        \"id\" : cnt,\n",
+    "        \"content\" : content,\n",
+    "        \"metadata\" : {\n",
+    "            \"source\" : sample['task_id']\n",
+    "        },\n",
+    "        \"embedding\" : embeddings.embed_query(content),\n",
+    "    }\n",
+    "    docs.append(doc)\n",
+    "    cnt += 1\n",
+    "\n",
+    "# upload the documents to the vector database\n",
+    "try:\n",
+    "    response = (\n",
+    "        supabase.table(\"documents2\")\n",
+    "        .insert(docs)\n",
+    "        .execute()\n",
+    "    )\n",
+    "except Exception as exception:\n",
+    "    print(\"Error inserting data into Supabase:\", exception)\n",
+    "\n",
+    "# # Save the documents (a list of dict) into a csv file, and manually upload it to Supabase\n",
+    "# import pandas as pd\n",
+    "# df = pd.DataFrame(docs)\n",
+    "# df.to_csv('supabase_docs.csv',index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "9aa7eb5e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add items to vector database\n",
+    "vector_store = SupabaseVectorStore(\n",
+    "    client=supabase,\n",
+    "    embedding= embeddings,\n",
+    "    table_name=\"documents2\",\n",
+    "    query_name=\"match_documents_2\",\n",
+    ")\n",
+    "retriever = vector_store.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "9eecafd1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\"\n",
+    "# matched_docs = vector_store.similarity_search(query, k=2)\n",
+    "docs = retriever.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "ff917840",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': '840bfca7-4f7b-481a-8794-c560c340185d'}, page_content='Question : On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\\n\\nFinal answer : 80GSFC21M0002')"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "01c8f337",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "List of tools used in all samples:\n",
+      "Total number of tools used: 83\n",
+      "  ├── web browser: 107\n",
+      "  ├── image recognition tools (to identify and parse a figure with three axes): 1\n",
+      "  ├── search engine: 101\n",
+      "  ├── calculator: 34\n",
+      "  ├── unlambda compiler (optional): 1\n",
+      "  ├── a web browser.: 2\n",
+      "  ├── a search engine.: 2\n",
+      "  ├── a calculator.: 1\n",
+      "  ├── microsoft excel: 5\n",
+      "  ├── google search: 1\n",
+      "  ├── ne: 9\n",
+      "  ├── pdf access: 7\n",
+      "  ├── file handling: 2\n",
+      "  ├── python: 3\n",
+      "  ├── image recognition tools: 12\n",
+      "  ├── jsonld file access: 1\n",
+      "  ├── video parsing: 1\n",
+      "  ├── python compiler: 1\n",
+      "  ├── video recognition tools: 3\n",
+      "  ├── pdf viewer: 7\n",
+      "  ├── microsoft excel / google sheets: 3\n",
+      "  ├── word document access: 1\n",
+      "  ├── tool to extract text from images: 1\n",
+      "  ├── a word reversal tool / script: 1\n",
+      "  ├── counter: 1\n",
+      "  ├── excel: 3\n",
+      "  ├── image recognition: 5\n",
+      "  ├── color recognition: 3\n",
+      "  ├── excel file access: 3\n",
+      "  ├── xml file access: 1\n",
+      "  ├── access to the internet archive, web.archive.org: 1\n",
+      "  ├── text processing/diff tool: 1\n",
+      "  ├── gif parsing tools: 1\n",
+      "  ├── a web browser: 7\n",
+      "  ├── a search engine: 7\n",
+      "  ├── a speech-to-text tool: 2\n",
+      "  ├── code/data analysis tools: 1\n",
+      "  ├── audio capability: 2\n",
+      "  ├── pdf reader: 1\n",
+      "  ├── markdown: 1\n",
+      "  ├── a calculator: 5\n",
+      "  ├── access to wikipedia: 3\n",
+      "  ├── image recognition/ocr: 3\n",
+      "  ├── google translate access: 1\n",
+      "  ├── ocr: 4\n",
+      "  ├── bass note data: 1\n",
+      "  ├── text editor: 1\n",
+      "  ├── xlsx file access: 1\n",
+      "  ├── powerpoint viewer: 1\n",
+      "  ├── csv file access: 1\n",
+      "  ├── calculator (or use excel): 1\n",
+      "  ├── computer algebra system: 1\n",
+      "  ├── video processing software: 1\n",
+      "  ├── audio processing software: 1\n",
+      "  ├── computer vision: 1\n",
+      "  ├── google maps: 1\n",
+      "  ├── access to excel files: 1\n",
+      "  ├── calculator (or ability to count): 1\n",
+      "  ├── a file interface: 3\n",
+      "  ├── a python ide: 1\n",
+      "  ├── spreadsheet editor: 1\n",
+      "  ├── tools required: 1\n",
+      "  ├── b browser: 1\n",
+      "  ├── image recognition and processing tools: 1\n",
+      "  ├── computer vision or ocr: 1\n",
+      "  ├── c++ compiler: 1\n",
+      "  ├── access to google maps: 1\n",
+      "  ├── youtube player: 1\n",
+      "  ├── natural language processor: 1\n",
+      "  ├── graph interaction tools: 1\n",
+      "  ├── bablyonian cuniform -> arabic legend: 1\n",
+      "  ├── access to youtube: 1\n",
+      "  ├── image search tools: 1\n",
+      "  ├── calculator or counting function: 1\n",
+      "  ├── a speech-to-text audio processing tool: 1\n",
+      "  ├── access to academic journal websites: 1\n",
+      "  ├── pdf reader/extracter: 1\n",
+      "  ├── rubik's cube model: 1\n",
+      "  ├── wikipedia: 1\n",
+      "  ├── video capability: 1\n",
+      "  ├── image processing tools: 1\n",
+      "  ├── age recognition software: 1\n",
+      "  ├── youtube: 1\n"
+     ]
+    }
+   ],
+   "source": [
+    "# list of the tools used in all the samples\n",
+    "from collections import Counter, OrderedDict\n",
+    "\n",
+    "tools = []\n",
+    "for sample in json_QA:\n",
+    "    for tool in sample['Annotator Metadata']['Tools'].split('\\n'):\n",
+    "        tool = tool[2:].strip().lower()\n",
+    "        if tool.startswith(\"(\"):\n",
+    "            tool = tool[11:].strip()\n",
+    "        tools.append(tool)\n",
+    "tools_counter = OrderedDict(Counter(tools))\n",
+    "print(\"List of tools used in all samples:\")\n",
+    "print(\"Total number of tools used:\", len(tools_counter))\n",
+    "for tool, count in tools_counter.items():\n",
+    "    print(f\"  ├── {tool}: {count}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}