{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# LangChain Tutorial for Python Beginners\n",
        "Xenors practice notebook. Run each cell and compare the output with the tutorial page.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Compose a small runnable chain\n",
        "Use small composable steps so you can test each stage independently.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from langchain_core.runnables import RunnableLambda\n",
        "clean=RunnableLambda(lambda x:x.strip().lower())\n",
        "length=RunnableLambda(lambda x:{'text':x,'chars':len(x)})\n",
        "print((clean|length).invoke('  Hello LangChain  '))\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "**Expected/checkpoint**\n",
        "```text\n{'text': 'hello langchain', 'chars': 15}\n```\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Return structured data\n",
        "Structured output is easier to validate than free-form text.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from pydantic import BaseModel\n",
        "class Answer(BaseModel):\n",
        "    label:str\n",
        "    confidence:float\n",
        "print(Answer(label='positive',confidence=.91).model_dump())\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "**Expected/checkpoint**\n",
        "```text\n{'label': 'positive', 'confidence': 0.91}\n```\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.x"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}