{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/adityasugandhi/Documents/GitHub/LLM_Playground/.newenv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/adityasugandhi/Documents/GitHub/LLM_Playground\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Batches: 100%|██████████| 1/1 [00:03<00:00,  3.22s/it]\n",
      "/Users/adityasugandhi/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx.tar.gz: 100%|██████████| 79.3M/79.3M [00:11<00:00, 7.14MiB/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'retriever': {'documents': [Document(id=fee80856fdb487fb694c739e089614d733502a7bd6d8b192f29ed6dad2088f44, content: 'Vishwam Shah is a highly motivated and skilled Computer Science professional currently pursuing a Ma...', meta: {'file_path': '/Users/adityasugandhi/Documents/GitHub/LLM_Playground/data/mf.txt', 'source_id': '99393e97120fcb9e88daa2d490060e9a91385ae63c7890d12b351978c02d3d93'}, score: 1.0066444873809814, embedding: vector of size 384), Document(id=e700bf2b5df175311a60ca00ffb6ed77b65b09c4221a2466b68e4802d90a831a, content: 'VISHWAM SHAH\n",
      "Tallahassee, FL |shahvishwam7@gmail.com |+1 (850) 666 - 0095 |https://www.linkedin.com/...', meta: {'file_path': '/Users/adityasugandhi/Documents/GitHub/LLM_Playground/data/Resume_Vishwam_Shah_Back_end.pdf', 'source_id': 'd23089ee94ea955eb9ef0045999019220184668c96631b25686fc002722e8753'}, score: 1.5628944635391235, embedding: vector of size 384), Document(id=299afa7bfc84e7700fd38b178933ab2bf3a67b09298662651b173af03fde7968, content: ' The\n",
      "“ECMWF Parameter ID” column is a ECMWF’s numeric label, and can be used to construct the URL fo...', meta: {'file_path': '/Users/adityasugandhi/Documents/GitHub/LLM_Playground/data/2212.12794.pdf', 'source_id': '314ee646f1f3143cad0677f2cdf057f1d625e5f2a1891449011557e1f75249d5'}, score: 1.6514018774032593, embedding: vector of size 384)]}}\n"
     ]
    }
   ],
   "source": [
    "from pathlib import Path\n",
    "import os\n",
    "from haystack import Pipeline\n",
    "from haystack.components.embedders import SentenceTransformersDocumentEmbedder,SentenceTransformersTextEmbedder\n",
    "from haystack.components.converters import PyPDFToDocument, TextFileToDocument\n",
    "from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter\n",
    "from haystack.components.routers import FileTypeRouter\n",
    "from haystack.components.joiners import DocumentJoiner\n",
    "from haystack.components.writers import DocumentWriter\n",
    "from haystack_integrations.document_stores.chroma import ChromaDocumentStore\n",
    "from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever\n",
    "\n",
    "HERE = Path(os.getcwd())\n",
    "print(HERE)\n",
    "\n",
    "data_path = HERE / \"data\"\n",
    "file_paths = [str(data_path / name) for name in os.listdir(data_path)]\n",
    "\n",
    "chroma_store = ChromaDocumentStore()\n",
    "\n",
    "pipeline = Pipeline()\n",
    "pipeline.add_component(\"FileTypeRouter\", FileTypeRouter(mime_types=[\"text/plain\", \"application/pdf\"]))\n",
    "pipeline.add_component(\"TextFileConverter\", TextFileToDocument())\n",
    "pipeline.add_component(\"PdfFileConverter\", PyPDFToDocument())\n",
    "\n",
    "pipeline.add_component(\"Joiner\", DocumentJoiner())\n",
    "pipeline.add_component(\"Cleaner\", DocumentCleaner())\n",
    "pipeline.add_component(\"Splitter\", DocumentSplitter(split_by=\"sentence\", split_length=250, split_overlap=30))\n",
    "# pipeline.add_component(\"TextEmbedder\", SentenceTransformersTextEmbedder())\n",
    "pipeline.add_component(\"Embedder\", SentenceTransformersDocumentEmbedder(model=\"sentence-transformers/all-MiniLM-L6-v2\"))\n",
    "\n",
    "pipeline.add_component(\"Writer\", DocumentWriter(document_store=chroma_store))\n",
    "\n",
    "pipeline.connect(\"FileTypeRouter.text/plain\", \"TextFileConverter.sources\")\n",
    "pipeline.connect(\"FileTypeRouter.application/pdf\", \"PdfFileConverter.sources\")\n",
    "pipeline.connect(\"TextFileConverter.documents\", \"Joiner.documents\")\n",
    "pipeline.connect(\"PdfFileConverter.documents\", \"Joiner.documents\")\n",
    "pipeline.connect(\"Joiner.documents\", \"Cleaner.documents\")\n",
    "pipeline.connect(\"Cleaner.documents\", \"Splitter.documents\")\n",
    "pipeline.connect(\"Splitter.documents\", \"Embedder.documents\")\n",
    "# pipeline.connect(\"TextEmbedder.embeddings\", \"Embedder.documents\")\n",
    "pipeline.connect(\"Embedder.documents\", \"Writer.documents\")\n",
    "\n",
    "pipeline.run(\n",
    "    {\"FileTypeRouter\": {\"sources\": file_paths}},\n",
    ")\n",
    "\n",
    "# Querying pipeline\n",
    "querying = Pipeline()\n",
    "querying.add_component(\"retriever\", ChromaQueryTextRetriever(chroma_store))\n",
    "results = querying.run({\"retriever\": {\"query\": \"Vishwam\", \"top_k\": 3}})\n",
    "print(results)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#Information Retriver"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'retriever': {'documents': [Document(id=ce02ebe3fa97972f0c76b2c175f658873b2d0e19987e9cbc38dcacb25b8ebdba, content: 'Aditya Sugandhi's journey as a Software Engineer is characterized by a deep commitment to excellence...', meta: {'file_path': '/unity/f2/asugandhi/Downloads/LLM_Playground/data/Aditya_train.txt', 'source_id': '228fb178549cb032d67e0b2da301131f48d7c88c814b6d6920c92727b1c8f5fd'}, score: 1.1221085786819458, embedding: vector of size 384), Document(id=11f7061bb8c56ae79965f1ba0d1a0283188dc031309394e1a03470d5d72207a9, content: 'Aditya Sugandhi is a seasoned Software Engineer with a rich background and diverse skill set, encomp...', meta: {'file_path': '/unity/f2/asugandhi/Downloads/LLM_Playground/data/Aditya_test.txt', 'source_id': 'c85a2287836cae980897693decb5e9d07e80f60b7c96b4e542ef3057e11fc228'}, score: 1.2236461639404297, embedding: vector of size 384), Document(id=a6ad41c3febd74d1f6825aac59c2d6dd7589ae8088bb3b449ea239c97d6f1b1c, content: ' . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18\n",
      "1.2 HRES . . . . . . . . . . . . . ....', meta: {'file_path': '/unity/f2/asugandhi/Downloads/LLM_Playground/data/2212.12794.pdf', 'source_id': 'aa504618a25e65b870dde2fe288f395a44ff6a05c640fa7a2e6c5a5d3a9a44ef'}, score: 1.6584246158599854, embedding: vector of size 384)]}}\n"
     ]
    }
   ],
   "source": [
    "# # Querying pipeline\n",
    "# querying = Pipeline()\n",
    "# querying.add_component(\"retriever\", ChromaQueryTextRetriever(chroma_store))\n",
    "# results = querying.run({\"retriever\": {\"query\": \"Aditya\", \"top_k\": 3}})\n",
    "# print(results)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'str' object has no attribute 'resolve_value'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[28], line 29\u001b[0m\n\u001b[1;32m     25\u001b[0m api_key \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39menviron\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOPENAI_API_KEY\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     27\u001b[0m \u001b[38;5;66;03m#ExtractiveReader to extract answers from the relevant context\u001b[39;00m\n\u001b[1;32m     28\u001b[0m \u001b[38;5;66;03m# api_key = Secret.from_token(\"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\")\u001b[39;00m\n\u001b[0;32m---> 29\u001b[0m llm \u001b[38;5;241m=\u001b[39m \u001b[43mOpenAIGenerator\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-3.5-turbo-0125\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43mapi_key\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mapi_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     30\u001b[0m reader \u001b[38;5;241m=\u001b[39m ExtractiveReader(model\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdeepset/roberta-base-squad2-distilled\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     32\u001b[0m extractive_qa_pipeline \u001b[38;5;241m=\u001b[39m Pipeline()\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/site-packages/haystack/core/component/component.py:122\u001b[0m, in \u001b[0;36mComponentMeta.__call__\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m    117\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    118\u001b[0m \u001b[38;5;124;03mThis method is called when clients instantiate a Component and\u001b[39;00m\n\u001b[1;32m    119\u001b[0m \u001b[38;5;124;03mruns before __new__ and __init__.\u001b[39;00m\n\u001b[1;32m    120\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    121\u001b[0m \u001b[38;5;66;03m# This will call __new__ then __init__, giving us back the Component instance\u001b[39;00m\n\u001b[0;32m--> 122\u001b[0m instance \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    124\u001b[0m \u001b[38;5;66;03m# Before returning, we have the chance to modify the newly created\u001b[39;00m\n\u001b[1;32m    125\u001b[0m \u001b[38;5;66;03m# Component instance, so we take the chance and set up the I/O sockets\u001b[39;00m\n\u001b[1;32m    126\u001b[0m \n\u001b[1;32m    127\u001b[0m \u001b[38;5;66;03m# If `component.set_output_types()` was called in the component constructor,\u001b[39;00m\n\u001b[1;32m    128\u001b[0m \u001b[38;5;66;03m# `__haystack_output__` is already populated, no need to do anything.\u001b[39;00m\n\u001b[1;32m    129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(instance, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m__haystack_output__\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m    130\u001b[0m     \u001b[38;5;66;03m# If that's not the case, we need to populate `__haystack_output__`\u001b[39;00m\n\u001b[1;32m    131\u001b[0m     \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    134\u001b[0m     \u001b[38;5;66;03m# We deepcopy the content of the cache to transfer ownership from the class method\u001b[39;00m\n\u001b[1;32m    135\u001b[0m     \u001b[38;5;66;03m# to the actual instance, so that different instances of the same class won't share this data.\u001b[39;00m\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/site-packages/haystack/components/generators/openai.py:103\u001b[0m, in \u001b[0;36mOpenAIGenerator.__init__\u001b[0;34m(self, api_key, model, streaming_callback, api_base_url, organization, system_prompt, generation_kwargs)\u001b[0m\n\u001b[1;32m    101\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapi_base_url \u001b[38;5;241m=\u001b[39m api_base_url\n\u001b[1;32m    102\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morganization \u001b[38;5;241m=\u001b[39m organization\n\u001b[0;32m--> 103\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclient \u001b[38;5;241m=\u001b[39m OpenAI(api_key\u001b[38;5;241m=\u001b[39m\u001b[43mapi_key\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresolve_value\u001b[49m(), organization\u001b[38;5;241m=\u001b[39morganization, base_url\u001b[38;5;241m=\u001b[39mapi_base_url)\n",
      "\u001b[0;31mAttributeError\u001b[0m: 'str' object has no attribute 'resolve_value'"
     ]
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "\n",
    "load_dotenv() \n",
    "from haystack import Pipeline\n",
    "from haystack.utils import Secret\n",
    "from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever\n",
    "from haystack.components.readers import ExtractiveReader\n",
    "from haystack.components.generators import GPTGenerator\n",
    "from haystack.components.builders.prompt_builder import PromptBuilder\n",
    "from haystack.components.generators import OpenAIGenerator\n",
    "\n",
    "template = \"\"\"\n",
    "  `    Answer the question using the provided context based on Aditya.\n",
    "\n",
    "      Context:\n",
    "      {% for context in answers %}\n",
    "      {{ context }}\n",
    "      {% endfor %}\n",
    "      Question: {{question}}\n",
    "      Answer:\n",
    "      \"\"\"\n",
    "\n",
    "prompt_builder = PromptBuilder(template=template)\n",
    "retriever = ChromaQueryTextRetriever(document_store = chroma_store)\n",
    "api_key = os.environ.get(\"OPENAI_API_KEY\")\n",
    "\n",
    "#ExtractiveReader to extract answers from the relevant context\n",
    "api_key = Secret.from_token(api_key)\n",
    "llm = OpenAIGenerator(model=\"gpt-3.5-turbo-0125\",api_key=api_key)\n",
    "reader = ExtractiveReader(model=\"deepset/roberta-base-squad2-distilled\")\n",
    "\n",
    "extractive_qa_pipeline = Pipeline()\n",
    "extractive_qa_pipeline.add_component(\"retriever\", retriever)\n",
    "extractive_qa_pipeline.add_component('reader', reader)\n",
    "extractive_qa_pipeline.add_component(instance=prompt_builder,   name=\"prompt_builder\")\n",
    "extractive_qa_pipeline.add_component(\"llm\", llm)\n",
    "\n",
    "extractive_qa_pipeline.connect(\"retriever.documents\", \"reader.documents\")\n",
    "extractive_qa_pipeline.connect(\"reader.answers\", \"prompt_builder.answers\")\n",
    "extractive_qa_pipeline.connect(\"prompt_builder\", \"llm\")\n",
    "\n",
    "\n",
    "query = \"what is Aditya Pursuing ?\"\n",
    "print(query)\n",
    "# Define the input data for the pipeline components\n",
    "input_data = {\n",
    "    \"retriever\": {\"query\": query, \"top_k\": 2},\n",
    "    \"reader\": {\"query\": query, \"top_k\": 2},\n",
    "    \"prompt_builder\": {\"question\": query},\n",
    "     # Use 'max_tokens' instead of 'max_new_tokens'\n",
    "}\n",
    "\n",
    "# Run the pipeline with the updated input data\n",
    "results = extractive_qa_pipeline.run(input_data)\n",
    "print(results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "isinstance() arg 2 must be a type, a tuple of types, or a union",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[5], line 9\u001b[0m\n\u001b[1;32m      7\u001b[0m             \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m\n\u001b[1;32m      8\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mdefault(obj)\n\u001b[0;32m----> 9\u001b[0m json_results \u001b[38;5;241m=\u001b[39m \u001b[43mjson\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdumps\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresults\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mExtractedAnswerEncoder\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28mprint\u001b[39m(json_results)\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/__init__.py:238\u001b[0m, in \u001b[0;36mdumps\u001b[0;34m(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)\u001b[0m\n\u001b[1;32m    232\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    233\u001b[0m     \u001b[38;5;28mcls\u001b[39m \u001b[38;5;241m=\u001b[39m JSONEncoder\n\u001b[1;32m    234\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m    235\u001b[0m \u001b[43m    \u001b[49m\u001b[43mskipkeys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskipkeys\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mensure_ascii\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mensure_ascii\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    236\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcheck_circular\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheck_circular\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_nan\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mallow_nan\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    237\u001b[0m \u001b[43m    \u001b[49m\u001b[43mseparators\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mseparators\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdefault\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdefault\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msort_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m--> 238\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkw\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:201\u001b[0m, in \u001b[0;36mJSONEncoder.encode\u001b[0;34m(self, o)\u001b[0m\n\u001b[1;32m    199\u001b[0m chunks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miterencode(o, _one_shot\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m    200\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(chunks, (\u001b[38;5;28mlist\u001b[39m, \u001b[38;5;28mtuple\u001b[39m)):\n\u001b[0;32m--> 201\u001b[0m     chunks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mchunks\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    202\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(chunks)\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:431\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode\u001b[0;34m(o, _current_indent_level)\u001b[0m\n\u001b[1;32m    429\u001b[0m     \u001b[38;5;28;01myield from\u001b[39;00m _iterencode_list(o, _current_indent_level)\n\u001b[1;32m    430\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(o, \u001b[38;5;28mdict\u001b[39m):\n\u001b[0;32m--> 431\u001b[0m     \u001b[38;5;28;01myield from\u001b[39;00m _iterencode_dict(o, _current_indent_level)\n\u001b[1;32m    432\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    433\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m markers \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:405\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode_dict\u001b[0;34m(dct, _current_indent_level)\u001b[0m\n\u001b[1;32m    403\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    404\u001b[0m             chunks \u001b[38;5;241m=\u001b[39m _iterencode(value, _current_indent_level)\n\u001b[0;32m--> 405\u001b[0m         \u001b[38;5;28;01myield from\u001b[39;00m chunks\n\u001b[1;32m    406\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m newline_indent \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    407\u001b[0m     _current_indent_level \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:405\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode_dict\u001b[0;34m(dct, _current_indent_level)\u001b[0m\n\u001b[1;32m    403\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    404\u001b[0m             chunks \u001b[38;5;241m=\u001b[39m _iterencode(value, _current_indent_level)\n\u001b[0;32m--> 405\u001b[0m         \u001b[38;5;28;01myield from\u001b[39;00m chunks\n\u001b[1;32m    406\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m newline_indent \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    407\u001b[0m     _current_indent_level \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:325\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode_list\u001b[0;34m(lst, _current_indent_level)\u001b[0m\n\u001b[1;32m    323\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    324\u001b[0m             chunks \u001b[38;5;241m=\u001b[39m _iterencode(value, _current_indent_level)\n\u001b[0;32m--> 325\u001b[0m         \u001b[38;5;28;01myield from\u001b[39;00m chunks\n\u001b[1;32m    326\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m newline_indent \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    327\u001b[0m     _current_indent_level \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n",
      "File \u001b[0;32m/conda/asugandhi/miniconda3/envs/RAGAPP/lib/python3.10/json/encoder.py:438\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode\u001b[0;34m(o, _current_indent_level)\u001b[0m\n\u001b[1;32m    436\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCircular reference detected\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    437\u001b[0m     markers[markerid] \u001b[38;5;241m=\u001b[39m o\n\u001b[0;32m--> 438\u001b[0m o \u001b[38;5;241m=\u001b[39m \u001b[43m_default\u001b[49m\u001b[43m(\u001b[49m\u001b[43mo\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    439\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m _iterencode(o, _current_indent_level)\n\u001b[1;32m    440\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m markers \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "Cell \u001b[0;32mIn[5], line 5\u001b[0m, in \u001b[0;36mExtractedAnswerEncoder.default\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdefault\u001b[39m(\u001b[38;5;28mself\u001b[39m, obj):\n\u001b[0;32m----> 5\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28;43misinstance\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresults\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[1;32m      6\u001b[0m         \u001b[38;5;66;03m# Convert ExtractedAnswer to a dictionary\u001b[39;00m\n\u001b[1;32m      7\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m\n\u001b[1;32m      8\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mdefault(obj)\n",
      "\u001b[0;31mTypeError\u001b[0m: isinstance() arg 2 must be a type, a tuple of types, or a union"
     ]
    }
   ],
   "source": [
    "import json\n",
    "\n",
    "class ExtractedAnswerEncoder(json.JSONEncoder):\n",
    "    def default(self, obj):\n",
    "        if isinstance(obj, results):\n",
    "            # Convert ExtractedAnswer to a dictionary\n",
    "            return obj.__dict__\n",
    "        return super().default(obj)\n",
    "json_results = json.dumps(results, indent=2, cls=ExtractedAnswerEncoder)\n",
    "\n",
    "print(json_results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "RAGAPP",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}