{
 "cells": [
  {
   "cell_type": "raw",
   "id": "94c3ad61",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_position: 3\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b91e03f1",
   "metadata": {},
   "source": [
    "# How to use few shot examples\n",
    "\n",
    ":::info Prerequisites\n",
    "\n",
    "This guide assumes familiarity with the following concepts:\n",
    "- [Prompt templates](/docs/concepts/prompt_templates)\n",
    "- [Example selectors](/docs/concepts/example_selectors)\n",
    "- [LLMs](/docs/concepts/text_llms)\n",
    "- [Vectorstores](/docs/concepts/vectorstores)\n",
    "\n",
    ":::\n",
    "\n",
    "In this guide, we'll learn how to create a simple prompt template that provides the model with example inputs and outputs when generating. Providing the LLM with a few such examples is called few-shotting, and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.\n",
    "\n",
    "A few-shot prompt template can be constructed from either a set of examples, or from an [Example Selector](https://python.langchain.com/api_reference/core/example_selectors/langchain_core.example_selectors.base.BaseExampleSelector.html) class responsible for choosing a subset of examples from the defined set.\n",
    "\n",
    "This guide will cover few-shotting with string prompt templates. For a guide on few-shotting with chat messages for chat models, see [here](/docs/how_to/few_shot_examples_chat/).\n",
    "\n",
    "## Create a formatter for the few-shot examples\n",
    "\n",
    "Configure a formatter that will format the few-shot examples into a string. This formatter should be a `PromptTemplate` object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4e70bce2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.prompts import PromptTemplate\n",
    "\n",
    "example_prompt = PromptTemplate.from_template(\"Question: {question}\\n{answer}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50846ad4",
   "metadata": {},
   "source": [
    "## Creating the example set\n",
    "\n",
    "Next, we'll create a list of few-shot examples. Each example should be a dictionary representing an example input to the formatter prompt we defined above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a44be840",
   "metadata": {},
   "outputs": [],
   "source": [
    "examples = [\n",
    "    {\n",
    "        \"question\": \"Who lived longer, Muhammad Ali or Alan Turing?\",\n",
    "        \"answer\": \"\"\"\n",
    "Are follow up questions needed here: Yes.\n",
    "Follow up: How old was Muhammad Ali when he died?\n",
    "Intermediate answer: Muhammad Ali was 74 years old when he died.\n",
    "Follow up: How old was Alan Turing when he died?\n",
    "Intermediate answer: Alan Turing was 41 years old when he died.\n",
    "So the final answer is: Muhammad Ali\n",
    "\"\"\",\n",
    "    },\n",
    "    {\n",
    "        \"question\": \"When was the founder of craigslist born?\",\n",
    "        \"answer\": \"\"\"\n",
    "Are follow up questions needed here: Yes.\n",
    "Follow up: Who was the founder of craigslist?\n",
    "Intermediate answer: Craigslist was founded by Craig Newmark.\n",
    "Follow up: When was Craig Newmark born?\n",
    "Intermediate answer: Craig Newmark was born on December 6, 1952.\n",
    "So the final answer is: December 6, 1952\n",
    "\"\"\",\n",
    "    },\n",
    "    {\n",
    "        \"question\": \"Who was the maternal grandfather of George Washington?\",\n",
    "        \"answer\": \"\"\"\n",
    "Are follow up questions needed here: Yes.\n",
    "Follow up: Who was the mother of George Washington?\n",
    "Intermediate answer: The mother of George Washington was Mary Ball Washington.\n",
    "Follow up: Who was the father of Mary Ball Washington?\n",
    "Intermediate answer: The father of Mary Ball Washington was Joseph Ball.\n",
    "So the final answer is: Joseph Ball\n",
    "\"\"\",\n",
    "    },\n",
    "    {\n",
    "        \"question\": \"Are both the directors of Jaws and Casino Royale from the same country?\",\n",
    "        \"answer\": \"\"\"\n",
    "Are follow up questions needed here: Yes.\n",
    "Follow up: Who is the director of Jaws?\n",
    "Intermediate Answer: The director of Jaws is Steven Spielberg.\n",
    "Follow up: Where is Steven Spielberg from?\n",
    "Intermediate Answer: The United States.\n",
    "Follow up: Who is the director of Casino Royale?\n",
    "Intermediate Answer: The director of Casino Royale is Martin Campbell.\n",
    "Follow up: Where is Martin Campbell from?\n",
    "Intermediate Answer: New Zealand.\n",
    "So the final answer is: No\n",
    "\"\"\",\n",
    "    },\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d1ec9d5",
   "metadata": {},
   "source": [
    "Let's test the formatting prompt with one of our examples:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "8c6e48ad",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question: Who lived longer, Muhammad Ali or Alan Turing?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: How old was Muhammad Ali when he died?\n",
      "Intermediate answer: Muhammad Ali was 74 years old when he died.\n",
      "Follow up: How old was Alan Turing when he died?\n",
      "Intermediate answer: Alan Turing was 41 years old when he died.\n",
      "So the final answer is: Muhammad Ali\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(example_prompt.invoke(examples[0]).to_string())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dad66af1",
   "metadata": {},
   "source": [
    "### Pass the examples and formatter to `FewShotPromptTemplate`\n",
    "\n",
    "Finally, create a [`FewShotPromptTemplate`](https://python.langchain.com/api_reference/core/prompts/langchain_core.prompts.few_shot.FewShotPromptTemplate.html) object. This object takes in the few-shot examples and the formatter for the few-shot examples. When this `FewShotPromptTemplate` is formatted, it formats the passed examples using the `example_prompt`, then and adds them to the final prompt before `suffix`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e76fa1ba",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question: Who lived longer, Muhammad Ali or Alan Turing?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: How old was Muhammad Ali when he died?\n",
      "Intermediate answer: Muhammad Ali was 74 years old when he died.\n",
      "Follow up: How old was Alan Turing when he died?\n",
      "Intermediate answer: Alan Turing was 41 years old when he died.\n",
      "So the final answer is: Muhammad Ali\n",
      "\n",
      "\n",
      "Question: When was the founder of craigslist born?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: Who was the founder of craigslist?\n",
      "Intermediate answer: Craigslist was founded by Craig Newmark.\n",
      "Follow up: When was Craig Newmark born?\n",
      "Intermediate answer: Craig Newmark was born on December 6, 1952.\n",
      "So the final answer is: December 6, 1952\n",
      "\n",
      "\n",
      "Question: Who was the maternal grandfather of George Washington?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: Who was the mother of George Washington?\n",
      "Intermediate answer: The mother of George Washington was Mary Ball Washington.\n",
      "Follow up: Who was the father of Mary Ball Washington?\n",
      "Intermediate answer: The father of Mary Ball Washington was Joseph Ball.\n",
      "So the final answer is: Joseph Ball\n",
      "\n",
      "\n",
      "Question: Are both the directors of Jaws and Casino Royale from the same country?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: Who is the director of Jaws?\n",
      "Intermediate Answer: The director of Jaws is Steven Spielberg.\n",
      "Follow up: Where is Steven Spielberg from?\n",
      "Intermediate Answer: The United States.\n",
      "Follow up: Who is the director of Casino Royale?\n",
      "Intermediate Answer: The director of Casino Royale is Martin Campbell.\n",
      "Follow up: Where is Martin Campbell from?\n",
      "Intermediate Answer: New Zealand.\n",
      "So the final answer is: No\n",
      "\n",
      "\n",
      "Question: Who was the father of Mary Ball Washington?\n"
     ]
    }
   ],
   "source": [
    "from langchain_core.prompts import FewShotPromptTemplate\n",
    "\n",
    "prompt = FewShotPromptTemplate(\n",
    "    examples=examples,\n",
    "    example_prompt=example_prompt,\n",
    "    suffix=\"Question: {input}\",\n",
    "    input_variables=[\"input\"],\n",
    ")\n",
    "\n",
    "print(\n",
    "    prompt.invoke({\"input\": \"Who was the father of Mary Ball Washington?\"}).to_string()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59c6f332",
   "metadata": {},
   "source": [
    "By providing the model with examples like this, we can guide the model to a better response."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bbe1f843",
   "metadata": {},
   "source": [
    "## Using an example selector\n",
    "\n",
    "We will reuse the example set and the formatter from the previous section. However, instead of feeding the examples directly into the `FewShotPromptTemplate` object, we will feed them into an implementation of `ExampleSelector` called [`SemanticSimilarityExampleSelector`](https://python.langchain.com/api_reference/core/example_selectors/langchain_core.example_selectors.semantic_similarity.SemanticSimilarityExampleSelector.html) instance. This class selects few-shot examples from the initial set based on their similarity to the input. It uses an embedding model to compute the similarity between the input and the few-shot examples, as well as a vector store to perform the nearest neighbor search.\n",
    "\n",
    "To show what it looks like, let's initialize an instance and call it in isolation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "80c5ac5c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Examples most similar to the input: Who was the father of Mary Ball Washington?\n",
      "\n",
      "\n",
      "answer: \n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: Who was the mother of George Washington?\n",
      "Intermediate answer: The mother of George Washington was Mary Ball Washington.\n",
      "Follow up: Who was the father of Mary Ball Washington?\n",
      "Intermediate answer: The father of Mary Ball Washington was Joseph Ball.\n",
      "So the final answer is: Joseph Ball\n",
      "\n",
      "question: Who was the maternal grandfather of George Washington?\n"
     ]
    }
   ],
   "source": [
    "from langchain_chroma import Chroma\n",
    "from langchain_core.example_selectors import SemanticSimilarityExampleSelector\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
    "example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
    "    # This is the list of examples available to select from.\n",
    "    examples,\n",
    "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
    "    OpenAIEmbeddings(),\n",
    "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
    "    Chroma,\n",
    "    # This is the number of examples to produce.\n",
    "    k=1,\n",
    ")\n",
    "\n",
    "# Select the most similar example to the input.\n",
    "question = \"Who was the father of Mary Ball Washington?\"\n",
    "selected_examples = example_selector.select_examples({\"question\": question})\n",
    "print(f\"Examples most similar to the input: {question}\")\n",
    "for example in selected_examples:\n",
    "    print(\"\\n\")\n",
    "    for k, v in example.items():\n",
    "        print(f\"{k}: {v}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89ac47fe",
   "metadata": {},
   "source": [
    "Now, let's create a `FewShotPromptTemplate` object. This object takes in the example selector and the formatter prompt for the few-shot examples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "de69a214",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question: Who was the maternal grandfather of George Washington?\n",
      "\n",
      "Are follow up questions needed here: Yes.\n",
      "Follow up: Who was the mother of George Washington?\n",
      "Intermediate answer: The mother of George Washington was Mary Ball Washington.\n",
      "Follow up: Who was the father of Mary Ball Washington?\n",
      "Intermediate answer: The father of Mary Ball Washington was Joseph Ball.\n",
      "So the final answer is: Joseph Ball\n",
      "\n",
      "\n",
      "Question: Who was the father of Mary Ball Washington?\n"
     ]
    }
   ],
   "source": [
    "prompt = FewShotPromptTemplate(\n",
    "    example_selector=example_selector,\n",
    "    example_prompt=example_prompt,\n",
    "    suffix=\"Question: {input}\",\n",
    "    input_variables=[\"input\"],\n",
    ")\n",
    "\n",
    "print(\n",
    "    prompt.invoke({\"input\": \"Who was the father of Mary Ball Washington?\"}).to_string()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b460794",
   "metadata": {},
   "source": [
    "## Next steps\n",
    "\n",
    "You've now learned how to add few-shot examples to your prompts.\n",
    "\n",
    "Next, check out the other how-to guides on prompt templates in this section, the related how-to guide on [few shotting with chat models](/docs/how_to/few_shot_examples_chat), or the other [example selector how-to guides](/docs/how_to/example_selectors/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf06d2a6",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}