langchain/docs/modules/prompts/example_selectors/examples/similarity.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2d007b0a",
   "metadata": {},
   "source": [
    "# Similarity ExampleSelector\n",
    "\n",
    "The SemanticSimilarityExampleSelector selects examples based on which examples are most similar to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "241bfe80",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
    "from langchain.vectorstores import Chroma\n",
    "from langchain.embeddings import OpenAIEmbeddings\n",
    "from langchain.prompts import FewShotPromptTemplate, PromptTemplate\n",
    "\n",
    "example_prompt = PromptTemplate(\n",
    "    input_variables=[\"input\", \"output\"],\n",
    "    template=\"Input: {input}\\nOutput: {output}\",\n",
    ")\n",
    "\n",
    "# These are a lot of examples of a pretend task of creating antonyms.\n",
    "examples = [\n",
    "    {\"input\": \"happy\", \"output\": \"sad\"},\n",
    "    {\"input\": \"tall\", \"output\": \"short\"},\n",
    "    {\"input\": \"energetic\", \"output\": \"lethargic\"},\n",
    "    {\"input\": \"sunny\", \"output\": \"gloomy\"},\n",
    "    {\"input\": \"windy\", \"output\": \"calm\"},\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "50d0a701",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running Chroma using direct local API.\n",
      "Using DuckDB in-memory for database. Data will be transient.\n"
     ]
    }
   ],
   "source": [
    "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",
    "similar_prompt = FewShotPromptTemplate(\n",
    "    # We provide an ExampleSelector instead of examples.\n",
    "    example_selector=example_selector,\n",
    "    example_prompt=example_prompt,\n",
    "    prefix=\"Give the antonym of every input\",\n",
    "    suffix=\"Input: {adjective}\\nOutput:\", \n",
    "    input_variables=[\"adjective\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4c8fdf45",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Give the antonym of every input\n",
      "\n",
      "Input: happy\n",
      "Output: sad\n",
      "\n",
      "Input: worried\n",
      "Output:\n"
     ]
    }
   ],
   "source": [
    "# Input is a feeling, so should select the happy/sad example\n",
    "print(similar_prompt.format(adjective=\"worried\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "829af21a",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Give the antonym of every input\n",
      "\n",
      "Input: happy\n",
      "Output: sad\n",
      "\n",
      "Input: fat\n",
      "Output:\n"
     ]
    }
   ],
   "source": [
    "# Input is a measurement, so should select the tall/short example\n",
    "print(similar_prompt.format(adjective=\"fat\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3c16fe23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Give the antonym of every input\n",
      "\n",
      "Input: happy\n",
      "Output: sad\n",
      "\n",
      "Input: joyful\n",
      "Output:\n"
     ]
    }
   ],
   "source": [
    "# You can add new examples to the SemanticSimilarityExampleSelector as well\n",
    "similar_prompt.example_selector.add_example({\"input\": \"enthusiastic\", \"output\": \"apathetic\"})\n",
    "print(similar_prompt.format(adjective=\"joyful\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "39f30097",
   "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
}