{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "0bf0e410-0031-4983-a868-f2f1253f6947",
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Optional\n",
    "from pydantic_settings import BaseSettings\n",
    "from functools import lru_cache\n",
    "from dotenv import load_dotenv\n",
    "import os\n",
    "\n",
    "\n",
    "class LLMProviderSettings(BaseSettings):\n",
    "    temperature: float = 0.0\n",
    "    max_tokens: Optional[int] = None\n",
    "    max_retries: int = 3\n",
    "\n",
    "class LlamaSettings(LLMProviderSettings):\n",
    "    api_key: str = \"key\"  # required, but not used\n",
    "    # default_model: str = \"phi3:3.8b\"\n",
    "    # default_model: str = \"llama3.2:latest\"\n",
    "    # default_model: str = \"deepseek-coder-v2:latest\"\n",
    "    # default_model: str = \"gemma2:27b\"\n",
    "    # default_model: str = \"solar-pro:latest\" # Need to upgrade Ollama\n",
    "    # default_model: str = \"phi3:14b\"\n",
    "    default_model: str = \"qwen2:0.5b\" # String validation errors \n",
    "    \n",
    "    \n",
    "    base_url: str = 'http://192.168.20.30:7869/v1'\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "class Settings(BaseSettings):\n",
    "    app_name: str = \"GenAI Project Template\"\n",
    "    # openai: OpenAISettings = OpenAISettings()\n",
    "    # anthropic: AnthropicSettings = AnthropicSettings()\n",
    "    llama: LlamaSettings = LlamaSettings()\n",
    "    \n",
    "\n",
    "@lru_cache\n",
    "def get_settings():\n",
    "    return Settings()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "f4993f4b-398e-4ad3-938f-5421677939c4",
   "metadata": {},
   "outputs": [
    {
     "ename": "InstructorRetryException",
     "evalue": "2 validation errors for CompletionModel\nresponse\n  Input should be a valid string [type=string_type, input_value={'reasoning': 'To find ou...s) * (rate per shirt).'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/string_type\nreasoning\n  Field required [type=missing, input_value={'response': {'reasoning'...odel', 'type': 'object'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/missing",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/retry.py:178\u001b[0m, in \u001b[0;36mretry_sync\u001b[0;34m(func, response_model, args, kwargs, context, max_retries, strict, mode, hooks)\u001b[0m\n\u001b[1;32m    172\u001b[0m                 kwargs \u001b[38;5;241m=\u001b[39m handle_reask_kwargs(\n\u001b[1;32m    173\u001b[0m                     kwargs\u001b[38;5;241m=\u001b[39mkwargs,\n\u001b[1;32m    174\u001b[0m                     mode\u001b[38;5;241m=\u001b[39mmode,\n\u001b[1;32m    175\u001b[0m                     response\u001b[38;5;241m=\u001b[39mresponse,\n\u001b[1;32m    176\u001b[0m                     exception\u001b[38;5;241m=\u001b[39me,\n\u001b[1;32m    177\u001b[0m                 )\n\u001b[0;32m--> 178\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    179\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RetryError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/retry.py:161\u001b[0m, in \u001b[0;36mretry_sync\u001b[0;34m(func, response_model, args, kwargs, context, max_retries, strict, mode, hooks)\u001b[0m\n\u001b[1;32m    158\u001b[0m     response \u001b[38;5;241m=\u001b[39m update_total_usage(\n\u001b[1;32m    159\u001b[0m         response\u001b[38;5;241m=\u001b[39mresponse, total_usage\u001b[38;5;241m=\u001b[39mtotal_usage\n\u001b[1;32m    160\u001b[0m     )\n\u001b[0;32m--> 161\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mprocess_response\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore\u001b[39;49;00m\n\u001b[1;32m    162\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    163\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresponse_model\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    164\u001b[0m \u001b[43m        \u001b[49m\u001b[43mvalidation_context\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    165\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    166\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    167\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    168\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    169\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (ValidationError, JSONDecodeError) \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/process_response.py:164\u001b[0m, in \u001b[0;36mprocess_response\u001b[0;34m(response, response_model, stream, validation_context, strict, mode)\u001b[0m\n\u001b[1;32m    162\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m model\n\u001b[0;32m--> 164\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mresponse_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_response\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    165\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    166\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvalidation_context\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalidation_context\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    167\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    168\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    169\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    171\u001b[0m \u001b[38;5;66;03m# ? This really hints at the fact that we need a better way of\u001b[39;00m\n\u001b[1;32m    172\u001b[0m \u001b[38;5;66;03m# ? attaching usage data and the raw response to the model we return.\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/function_calls.py:166\u001b[0m, in \u001b[0;36mOpenAISchema.from_response\u001b[0;34m(cls, completion, validation_context, strict, mode)\u001b[0m\n\u001b[1;32m    158\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mode \u001b[38;5;129;01min\u001b[39;00m {\n\u001b[1;32m    159\u001b[0m     Mode\u001b[38;5;241m.\u001b[39mJSON,\n\u001b[1;32m    160\u001b[0m     Mode\u001b[38;5;241m.\u001b[39mJSON_SCHEMA,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    164\u001b[0m     Mode\u001b[38;5;241m.\u001b[39mFIREWORKS_JSON,\n\u001b[1;32m    165\u001b[0m }:\n\u001b[0;32m--> 166\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[43mparse_json\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcompletion\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalidation_context\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstrict\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mInvalid patch mode: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmode\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/function_calls.py:384\u001b[0m, in \u001b[0;36mOpenAISchema.parse_json\u001b[0;34m(cls, completion, validation_context, strict)\u001b[0m\n\u001b[1;32m    382\u001b[0m message \u001b[38;5;241m=\u001b[39m extract_json_from_codeblock(message)\n\u001b[0;32m--> 384\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[43mmodel_validate_json\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    385\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmessage\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    386\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalidation_context\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    387\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    388\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/pydantic/main.py:656\u001b[0m, in \u001b[0;36mBaseModel.model_validate_json\u001b[0;34m(cls, json_data, strict, context)\u001b[0m\n\u001b[1;32m    655\u001b[0m __tracebackhide__ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m--> 656\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[43m__pydantic_validator__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalidate_json\u001b[49m\u001b[43m(\u001b[49m\u001b[43mjson_data\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[0;31mValidationError\u001b[0m: 2 validation errors for CompletionModel\nresponse\n  Input should be a valid string [type=string_type, input_value={'reasoning': 'To find ou...s) * (rate per shirt).'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/string_type\nreasoning\n  Field required [type=missing, input_value={'response': {'reasoning'...odel', 'type': 'object'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/missing",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mRetryError\u001b[0m                                Traceback (most recent call last)",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/retry.py:151\u001b[0m, in \u001b[0;36mretry_sync\u001b[0;34m(func, response_model, args, kwargs, context, max_retries, strict, mode, hooks)\u001b[0m\n\u001b[1;32m    150\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 151\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mattempt\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mmax_retries\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    152\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mwith\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mattempt\u001b[49m\u001b[43m:\u001b[49m\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/tenacity/__init__.py:443\u001b[0m, in \u001b[0;36mBaseRetrying.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    442\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 443\u001b[0m     do \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mretry_state\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretry_state\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    444\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(do, DoAttempt):\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/tenacity/__init__.py:376\u001b[0m, in \u001b[0;36mBaseRetrying.iter\u001b[0;34m(self, retry_state)\u001b[0m\n\u001b[1;32m    375\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m action \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_state\u001b[38;5;241m.\u001b[39mactions:\n\u001b[0;32m--> 376\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43maction\u001b[49m\u001b[43m(\u001b[49m\u001b[43mretry_state\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    377\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/tenacity/__init__.py:419\u001b[0m, in \u001b[0;36mBaseRetrying._post_stop_check_actions.<locals>.exc_check\u001b[0;34m(rs)\u001b[0m\n\u001b[1;32m    418\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m retry_exc\u001b[38;5;241m.\u001b[39mreraise()\n\u001b[0;32m--> 419\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m retry_exc \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfut\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mexception\u001b[39;00m()\n",
      "\u001b[0;31mRetryError\u001b[0m: RetryError[<Future at 0x7a6435069450 state=finished raised ValidationError>]",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mInstructorRetryException\u001b[0m                  Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[47], line 57\u001b[0m\n\u001b[1;32m     48\u001b[0m messages \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     49\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrole\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msystem\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou are a helpful assistant.\u001b[39m\u001b[38;5;124m\"\u001b[39m},\n\u001b[1;32m     50\u001b[0m     {\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     53\u001b[0m     },\n\u001b[1;32m     54\u001b[0m ]\n\u001b[1;32m     56\u001b[0m llm \u001b[38;5;241m=\u001b[39m LLMFactory(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mllama\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 57\u001b[0m completion \u001b[38;5;241m=\u001b[39m \u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate_completion\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     58\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresponse_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mCompletionModel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     59\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     60\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     61\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(completion, CompletionModel)\n\u001b[1;32m     63\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mResponse: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mcompletion\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
      "Cell \u001b[0;32mIn[47], line 39\u001b[0m, in \u001b[0;36mLLMFactory.create_completion\u001b[0;34m(self, response_model, messages, **kwargs)\u001b[0m\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate_completion\u001b[39m(\n\u001b[1;32m     29\u001b[0m     \u001b[38;5;28mself\u001b[39m, response_model: Type[BaseModel], messages: List[Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]], \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m     30\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m     31\u001b[0m     completion_params \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m     32\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m: kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msettings\u001b[38;5;241m.\u001b[39mdefault_model),\n\u001b[1;32m     33\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtemperature\u001b[39m\u001b[38;5;124m\"\u001b[39m: kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtemperature\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msettings\u001b[38;5;241m.\u001b[39mtemperature),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     37\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m: messages,\n\u001b[1;32m     38\u001b[0m     }\n\u001b[0;32m---> 39\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[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mchat\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompletions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mcompletion_params\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/client.py:176\u001b[0m, in \u001b[0;36mInstructor.create\u001b[0;34m(self, response_model, messages, max_retries, validation_context, context, strict, **kwargs)\u001b[0m\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    165\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    166\u001b[0m     response_model: \u001b[38;5;28mtype\u001b[39m[T] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    172\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    173\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T \u001b[38;5;241m|\u001b[39m Any \u001b[38;5;241m|\u001b[39m Awaitable[T] \u001b[38;5;241m|\u001b[39m Awaitable[Any]:\n\u001b[1;32m    174\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_kwargs(kwargs)\n\u001b[0;32m--> 176\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[43mcreate_fn\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    177\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresponse_model\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    178\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    179\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmax_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    180\u001b[0m \u001b[43m        \u001b[49m\u001b[43mvalidation_context\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalidation_context\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    181\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    182\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    183\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhooks\u001b[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[43mhooks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    184\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    185\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/patch.py:193\u001b[0m, in \u001b[0;36mpatch.<locals>.new_create_sync\u001b[0;34m(response_model, validation_context, context, max_retries, strict, hooks, *args, **kwargs)\u001b[0m\n\u001b[1;32m    187\u001b[0m response_model, new_kwargs \u001b[38;5;241m=\u001b[39m handle_response_model(\n\u001b[1;32m    188\u001b[0m     response_model\u001b[38;5;241m=\u001b[39mresponse_model, mode\u001b[38;5;241m=\u001b[39mmode, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m    189\u001b[0m )  \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[1;32m    191\u001b[0m new_kwargs \u001b[38;5;241m=\u001b[39m handle_templating(new_kwargs, context)\n\u001b[0;32m--> 193\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mretry_sync\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    194\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfunc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore\u001b[39;49;00m\n\u001b[1;32m    195\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresponse_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresponse_model\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    196\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    197\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmax_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    198\u001b[0m \u001b[43m    \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    199\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhooks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhooks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    200\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstrict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstrict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    201\u001b[0m \u001b[43m    \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnew_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    202\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    203\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    204\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
      "File \u001b[0;32m~/miniconda3/envs/LLMatie/lib/python3.13/site-packages/instructor/retry.py:181\u001b[0m, in \u001b[0;36mretry_sync\u001b[0;34m(func, response_model, args, kwargs, context, max_retries, strict, mode, hooks)\u001b[0m\n\u001b[1;32m    179\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RetryError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    180\u001b[0m     logger\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRetry error: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 181\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m InstructorRetryException(\n\u001b[1;32m    182\u001b[0m         e\u001b[38;5;241m.\u001b[39mlast_attempt\u001b[38;5;241m.\u001b[39m_exception,\n\u001b[1;32m    183\u001b[0m         last_completion\u001b[38;5;241m=\u001b[39mresponse,\n\u001b[1;32m    184\u001b[0m         n_attempts\u001b[38;5;241m=\u001b[39mattempt\u001b[38;5;241m.\u001b[39mretry_state\u001b[38;5;241m.\u001b[39mattempt_number,\n\u001b[1;32m    185\u001b[0m         \u001b[38;5;66;03m#! deprecate messages soon\u001b[39;00m\n\u001b[1;32m    186\u001b[0m         messages\u001b[38;5;241m=\u001b[39mkwargs\u001b[38;5;241m.\u001b[39mget(\n\u001b[1;32m    187\u001b[0m             \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontents\u001b[39m\u001b[38;5;124m\"\u001b[39m, kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mchat_history\u001b[39m\u001b[38;5;124m\"\u001b[39m, []))\n\u001b[1;32m    188\u001b[0m         ),\n\u001b[1;32m    189\u001b[0m         create_kwargs\u001b[38;5;241m=\u001b[39mkwargs,\n\u001b[1;32m    190\u001b[0m         total_usage\u001b[38;5;241m=\u001b[39mtotal_usage,\n\u001b[1;32m    191\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "\u001b[0;31mInstructorRetryException\u001b[0m: 2 validation errors for CompletionModel\nresponse\n  Input should be a valid string [type=string_type, input_value={'reasoning': 'To find ou...s) * (rate per shirt).'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/string_type\nreasoning\n  Field required [type=missing, input_value={'response': {'reasoning'...odel', 'type': 'object'}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.10/v/missing"
     ]
    }
   ],
   "source": [
    "from typing import Any, Dict, List, Type\n",
    "\n",
    "import instructor\n",
    "# from anthropic import Anthropic\n",
    "# from config.settings import get_settings\n",
    "from openai import OpenAI\n",
    "from pydantic import BaseModel, Field\n",
    "\n",
    "class LLMFactory:\n",
    "    def __init__(self, provider: str):\n",
    "        self.provider = provider\n",
    "        self.settings = getattr(get_settings(), provider)\n",
    "        self.client = self._initialize_client()\n",
    "\n",
    "    def _initialize_client(self) -> Any:\n",
    "        client_initializers = {\n",
    "            \"llama\": lambda s: instructor.from_openai(\n",
    "                OpenAI(base_url=s.base_url, api_key=s.api_key),\n",
    "                mode=instructor.Mode.JSON,\n",
    "            ),\n",
    "        }\n",
    "\n",
    "        initializer = client_initializers.get(self.provider)\n",
    "        if initializer:\n",
    "            return initializer(self.settings)\n",
    "        raise ValueError(f\"Unsupported LLM provider: {self.provider}\")\n",
    "\n",
    "    def create_completion(\n",
    "        self, response_model: Type[BaseModel], messages: List[Dict[str, str]], **kwargs\n",
    "    ) -> Any:\n",
    "        completion_params = {\n",
    "            \"model\": kwargs.get(\"model\", self.settings.default_model),\n",
    "            \"temperature\": kwargs.get(\"temperature\", self.settings.temperature),\n",
    "            \"max_retries\": kwargs.get(\"max_retries\", self.settings.max_retries),\n",
    "            \"max_tokens\": kwargs.get(\"max_tokens\", self.settings.max_tokens),\n",
    "            \"response_model\": response_model,\n",
    "            \"messages\": messages,\n",
    "        }\n",
    "        return self.client.chat.completions.create(**completion_params)\n",
    "\n",
    "\n",
    "if __name__ == \"__main__\":\n",
    "\n",
    "    class CompletionModel(BaseModel):\n",
    "        response: str = Field(description=\"Your response to the user.\")\n",
    "        reasoning: str = Field(description=\"Explain your reasoning for the response.\")\n",
    "\n",
    "    messages = [\n",
    "        {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
    "        {\n",
    "            \"role\": \"user\",\n",
    "            \"content\": \"If it takes 2 hours to dry 1 shirt out in the sun, how long will it take to dry 5 shirts?\",\n",
    "        },\n",
    "    ]\n",
    "\n",
    "    llm = LLMFactory(\"llama\")\n",
    "    completion = llm.create_completion(\n",
    "        response_model=CompletionModel,\n",
    "        messages=messages,\n",
    "    )\n",
    "    assert isinstance(completion, CompletionModel)\n",
    "\n",
    "    print(f\"Response: {completion.response}\\n\")\n",
    "    print(f\"Reasoning: {completion.reasoning}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa7ea636-7abe-4dc4-9665-1eb9bc4fde17",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}