Spaces:
Runtime error
Runtime error
File size: 26,080 Bytes
919910a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 |
{
"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 |[email protected] |+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
}
|