{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
    "\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "llm = ChatOpenAI(model=\"gpt-4o-mini\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "ename": "RateLimitError",
     "evalue": "Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mRateLimitError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[14], line 23\u001b[0m\n\u001b[1;32m     21\u001b[0m text_splitter \u001b[38;5;241m=\u001b[39m RecursiveCharacterTextSplitter(chunk_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1000\u001b[39m, chunk_overlap\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m200\u001b[39m)\n\u001b[1;32m     22\u001b[0m splits \u001b[38;5;241m=\u001b[39m text_splitter\u001b[38;5;241m.\u001b[39msplit_documents(docs)\n\u001b[0;32m---> 23\u001b[0m vectorstore \u001b[38;5;241m=\u001b[39m \u001b[43mChroma\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_documents\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdocuments\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msplits\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43membedding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mOpenAIEmbeddings\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     25\u001b[0m \u001b[38;5;66;03m# Retrieve and generate using the relevant snippets of the blog.\u001b[39;00m\n\u001b[1;32m     26\u001b[0m retriever \u001b[38;5;241m=\u001b[39m vectorstore\u001b[38;5;241m.\u001b[39mas_retriever()\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_chroma/vectorstores.py:1128\u001b[0m, in \u001b[0;36mChroma.from_documents\u001b[0;34m(cls, documents, embedding, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)\u001b[0m\n\u001b[1;32m   1126\u001b[0m texts \u001b[38;5;241m=\u001b[39m [doc\u001b[38;5;241m.\u001b[39mpage_content \u001b[38;5;28;01mfor\u001b[39;00m doc \u001b[38;5;129;01min\u001b[39;00m documents]\n\u001b[1;32m   1127\u001b[0m metadatas \u001b[38;5;241m=\u001b[39m [doc\u001b[38;5;241m.\u001b[39mmetadata \u001b[38;5;28;01mfor\u001b[39;00m doc \u001b[38;5;129;01min\u001b[39;00m documents]\n\u001b[0;32m-> 1128\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_texts\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1129\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtexts\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtexts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1130\u001b[0m \u001b[43m    \u001b[49m\u001b[43membedding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1131\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1132\u001b[0m \u001b[43m    \u001b[49m\u001b[43mids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1133\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcollection_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1134\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpersist_directory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpersist_directory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1135\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclient_settings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclient_settings\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1136\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1137\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcollection_metadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcollection_metadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1138\u001b[0m \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   1139\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_chroma/vectorstores.py:1089\u001b[0m, in \u001b[0;36mChroma.from_texts\u001b[0;34m(cls, texts, embedding, metadatas, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)\u001b[0m\n\u001b[1;32m   1083\u001b[0m         chroma_collection\u001b[38;5;241m.\u001b[39madd_texts(\n\u001b[1;32m   1084\u001b[0m             texts\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m3\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m batch[\u001b[38;5;241m3\u001b[39m] \u001b[38;5;28;01melse\u001b[39;00m [],\n\u001b[1;32m   1085\u001b[0m             metadatas\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m batch[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,  \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[1;32m   1086\u001b[0m             ids\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m   1087\u001b[0m         )\n\u001b[1;32m   1088\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1089\u001b[0m     \u001b[43mchroma_collection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43madd_texts\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtexts\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtexts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mids\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1090\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m chroma_collection\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_chroma/vectorstores.py:508\u001b[0m, in \u001b[0;36mChroma.add_texts\u001b[0;34m(self, texts, metadatas, ids, **kwargs)\u001b[0m\n\u001b[1;32m    506\u001b[0m texts \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(texts)\n\u001b[1;32m    507\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_embedding_function \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[0;32m--> 508\u001b[0m     embeddings \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_embedding_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membed_documents\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtexts\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    509\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m metadatas:\n\u001b[1;32m    510\u001b[0m     \u001b[38;5;66;03m# fill metadatas with empty dicts if somebody\u001b[39;00m\n\u001b[1;32m    511\u001b[0m     \u001b[38;5;66;03m# did not specify metadata for all texts\u001b[39;00m\n\u001b[1;32m    512\u001b[0m     length_diff \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(texts) \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mlen\u001b[39m(metadatas)\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_openai/embeddings/base.py:588\u001b[0m, in \u001b[0;36mOpenAIEmbeddings.embed_documents\u001b[0;34m(self, texts, chunk_size)\u001b[0m\n\u001b[1;32m    585\u001b[0m \u001b[38;5;66;03m# NOTE: to keep things simple, we assume the list may contain texts longer\u001b[39;00m\n\u001b[1;32m    586\u001b[0m \u001b[38;5;66;03m#       than the maximum context and use length-safe embedding function.\u001b[39;00m\n\u001b[1;32m    587\u001b[0m engine \u001b[38;5;241m=\u001b[39m cast(\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeployment)\n\u001b[0;32m--> 588\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_len_safe_embeddings\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtexts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mengine\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_openai/embeddings/base.py:483\u001b[0m, in \u001b[0;36mOpenAIEmbeddings._get_len_safe_embeddings\u001b[0;34m(self, texts, engine, chunk_size)\u001b[0m\n\u001b[1;32m    481\u001b[0m batched_embeddings: List[List[\u001b[38;5;28mfloat\u001b[39m]] \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m    482\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m _iter:\n\u001b[0;32m--> 483\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    484\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtokens\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m_chunk_size\u001b[49m\u001b[43m]\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[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_invocation_params\u001b[49m\n\u001b[1;32m    485\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    486\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response, \u001b[38;5;28mdict\u001b[39m):\n\u001b[1;32m    487\u001b[0m         response \u001b[38;5;241m=\u001b[39m response\u001b[38;5;241m.\u001b[39mmodel_dump()\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/resources/embeddings.py:124\u001b[0m, in \u001b[0;36mEmbeddings.create\u001b[0;34m(self, input, model, dimensions, encoding_format, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    118\u001b[0m         embedding\u001b[38;5;241m.\u001b[39membedding \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mfrombuffer(  \u001b[38;5;66;03m# type: ignore[no-untyped-call]\u001b[39;00m\n\u001b[1;32m    119\u001b[0m             base64\u001b[38;5;241m.\u001b[39mb64decode(data), dtype\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfloat32\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    120\u001b[0m         )\u001b[38;5;241m.\u001b[39mtolist()\n\u001b[1;32m    122\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m obj\n\u001b[0;32m--> 124\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    125\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/embeddings\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    126\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43membedding_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mEmbeddingCreateParams\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    127\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    128\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    129\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    130\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    131\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    132\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpost_parser\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    133\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    134\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mCreateEmbeddingResponse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    135\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1278\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1264\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1265\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1266\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1273\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1274\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m   1275\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1276\u001b[0m         method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m   1277\u001b[0m     )\n\u001b[0;32m-> 1278\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:955\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m    952\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    953\u001b[0m     retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 955\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    956\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    957\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    958\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    959\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    960\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    961\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1044\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1042\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1043\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1044\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1045\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1046\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1054\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1093\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1089\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1090\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1091\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1093\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1094\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1095\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1044\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1042\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1043\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1044\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1045\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1046\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1054\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1093\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1089\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1090\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1091\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1093\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1094\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1095\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1059\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1056\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1058\u001b[0m     log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1059\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1061\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m   1062\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1063\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1067\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m   1068\u001b[0m )\n",
      "\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}"
     ]
    }
   ],
   "source": [
    "import bs4\n",
    "from langchain import hub\n",
    "from langchain_chroma import Chroma\n",
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from langchain_core.output_parsers import StrOutputParser\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "\n",
    "# Load, chunk and index the contents of the blog.\n",
    "loader = WebBaseLoader(\n",
    "    web_paths=(\"https://lilianweng.github.io/posts/2023-06-23-agent/\",),\n",
    "    bs_kwargs=dict(\n",
    "        parse_only=bs4.SoupStrainer(\n",
    "            class_=(\"post-content\", \"post-title\", \"post-header\")\n",
    "        )\n",
    "    ),\n",
    ")\n",
    "docs = loader.load()\n",
    "\n",
    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
    "splits = text_splitter.split_documents(docs)\n",
    "vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())\n",
    "\n",
    "# Retrieve and generate using the relevant snippets of the blog.\n",
    "retriever = vectorstore.as_retriever()\n",
    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
    "\n",
    "\n",
    "def format_docs(docs):\n",
    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
    "\n",
    "\n",
    "rag_chain = (\n",
    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
    "    | prompt\n",
    "    | llm\n",
    "    | StrOutputParser()\n",
    ")\n",
    "\n",
    "rag_chain.invoke(\"What is Task Decomposition?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from bs4 import BeautifulSoup\n",
    "from langchain_chroma import Chroma\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
    "\n",
    "loader = WebBaseLoader(\n",
    "    web_paths=[\n",
    "        \"https://www.economist.com/united-states/2024/11/15/what-would-robert-kennedy-junior-mean-for-american-health\"\n",
    "    ],\n",
    "    bs_kwargs=dict(parse_only=bs4.SoupStrainer([\"article\", \"title\", \"content\"]))\n",
    ")\n",
    "docs = loader.load()\n",
    "\n",
    "\n",
    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
    "splits = text_splitter.split_documents(docs)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(metadata={'source': 'https://www.economist.com/united-states/2024/11/15/what-would-robert-kennedy-junior-mean-for-american-health', 'title': 'What would Robert Kennedy junior mean for American health?'}, page_content='What would Robert Kennedy junior mean for American health?The EconomistThe EconomistSearchUnited States | MAGA meets MAHAWhat would Robert Kennedy junior mean for American health?Donald Trump’s nomination for health secretary is sceptical about vaccines and mainstream medicinePhotograph: Getty Images Nov 15th 2024|WASHINGTON, DCShareAS IN MOST marriages of convenience, Donald Trump and Robert F. Kennedy junior make unusual bedfellows. One enjoys junk food, hates exercise and loves oil. The other talks of clean food, getting America moving again and wants to eliminate oils of all sorts (from seed oil to Mr Trump’s beloved “liquid gold”). One has called the covid-19 vaccine a “miracle”, the other is a long-term vaccine sceptic. Yet on November 14th Mr Trump announced that Mr Kennedy was his pick for secretary of health and human services (HHS).Explore moreDonald TrumpUnited StatesShareReuse this contentDiscover moreBack to the 1850sImmigrant voters may have won America’s presidential'),\n",
       " Document(metadata={'source': 'https://www.economist.com/united-states/2024/11/15/what-would-robert-kennedy-junior-mean-for-american-health', 'title': 'What would Robert Kennedy junior mean for American health?'}, page_content='pick for secretary of health and human services (HHS).Explore moreDonald TrumpUnited StatesShareReuse this contentDiscover moreBack to the 1850sImmigrant voters may have won America’s presidential election for the nativist candidateClimate change and the next administrationThere are obstacles to Donald Trump’s attempts to reverse progressThe promise Donald Trump is sure to keepHe wants more freedom to fire civil servants, but he should weigh the long-term consequencesSenate Republicans flex their independenceTrump doesn’t weigh in on a leadership contest, but real conflicts will soon comeRepublicans finally win the coveted trifectaYet the party’s grip on power could be less reliable than it appearsThe man picked as defence secretary wants to purge the PentagonPete Hegseth, a Fox News host, takes aim at “woke shit”LinkedInFacebookXInstagramThreadsTikTokYouTubeRSS')]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "splits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}