File size: 4,809 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "bc35afd0",
   "metadata": {},
   "source": [
    "# Maximal Marginal Relevance ExampleSelector\n",
    "\n",
    "The MaxMarginalRelevanceExampleSelector selects examples based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs, and then iteratively adding them while penalizing them for closeness to already selected examples.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ac95c968",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector\n",
    "from langchain.vectorstores import FAISS\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": 4,
   "id": "db579bea",
   "metadata": {},
   "outputs": [],
   "source": [
    "example_selector = MaxMarginalRelevanceExampleSelector.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",
    "    FAISS, \n",
    "    # This is the number of examples to produce.\n",
    "    k=2\n",
    ")\n",
    "mmr_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": 5,
   "id": "cd76e344",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Give the antonym of every input\n",
      "\n",
      "Input: happy\n",
      "Output: sad\n",
      "\n",
      "Input: windy\n",
      "Output: calm\n",
      "\n",
      "Input: worried\n",
      "Output:\n"
     ]
    }
   ],
   "source": [
    "# Input is a feeling, so should select the happy/sad example as the first one\n",
    "print(mmr_prompt.format(adjective=\"worried\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "cf82956b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Give the antonym of every input\n",
      "\n",
      "Input: happy\n",
      "Output: sad\n",
      "\n",
      "Input: windy\n",
      "Output: calm\n",
      "\n",
      "Input: worried\n",
      "Output:\n"
     ]
    }
   ],
   "source": [
    "# Let's compare this to what we would just get if we went solely off of similarity\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",
    ")\n",
    "similar_prompt.example_selector.k = 2\n",
    "print(similar_prompt.format(adjective=\"worried\"))"
   ]
  },
  {
   "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
}