File size: 7,956 Bytes
acc4ffe |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 |
{
"cells": [
{
"cell_type": "markdown",
"id": "920a3c1a",
"metadata": {},
"source": [
"# Model Comparison\n",
"\n",
"Constructing your language model application will likely involved choosing between many different options of prompts, models, and even chains to use. When doing so, you will want to compare these different options on different inputs in an easy, flexible, and intuitive way. \n",
"\n",
"LangChain provides the concept of a ModelLaboratory to test out and try different models."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ab9e95ad",
"metadata": {},
"outputs": [],
"source": [
"from langchain import LLMChain, OpenAI, Cohere, HuggingFaceHub, PromptTemplate\n",
"from langchain.model_laboratory import ModelLaboratory"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "32cb94e6",
"metadata": {},
"outputs": [],
"source": [
"llms = [\n",
" OpenAI(temperature=0), \n",
" Cohere(model=\"command-xlarge-20221108\", max_tokens=20, temperature=0), \n",
" HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":1})\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "14cde09d",
"metadata": {},
"outputs": [],
"source": [
"model_lab = ModelLaboratory.from_llms(llms)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "f186c741",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1mInput:\u001b[0m\n",
"What color is a flamingo?\n",
"\n",
"\u001b[1mOpenAI\u001b[0m\n",
"Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n",
"\u001b[36;1m\u001b[1;3m\n",
"\n",
"Flamingos are pink.\u001b[0m\n",
"\n",
"\u001b[1mCohere\u001b[0m\n",
"Params: {'model': 'command-xlarge-20221108', 'max_tokens': 20, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}\n",
"\u001b[33;1m\u001b[1;3m\n",
"\n",
"Pink\u001b[0m\n",
"\n",
"\u001b[1mHuggingFaceHub\u001b[0m\n",
"Params: {'repo_id': 'google/flan-t5-xl', 'temperature': 1}\n",
"\u001b[38;5;200m\u001b[1;3mpink\u001b[0m\n",
"\n"
]
}
],
"source": [
"model_lab.compare(\"What color is a flamingo?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "248b652a",
"metadata": {},
"outputs": [],
"source": [
"prompt = PromptTemplate(template=\"What is the capital of {state}?\", input_variables=[\"state\"])\n",
"model_lab_with_prompt = ModelLaboratory.from_llms(llms, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "f64377ac",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1mInput:\u001b[0m\n",
"New York\n",
"\n",
"\u001b[1mOpenAI\u001b[0m\n",
"Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n",
"\u001b[36;1m\u001b[1;3m\n",
"\n",
"The capital of New York is Albany.\u001b[0m\n",
"\n",
"\u001b[1mCohere\u001b[0m\n",
"Params: {'model': 'command-xlarge-20221108', 'max_tokens': 20, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}\n",
"\u001b[33;1m\u001b[1;3m\n",
"\n",
"The capital of New York is Albany.\u001b[0m\n",
"\n",
"\u001b[1mHuggingFaceHub\u001b[0m\n",
"Params: {'repo_id': 'google/flan-t5-xl', 'temperature': 1}\n",
"\u001b[38;5;200m\u001b[1;3mst john s\u001b[0m\n",
"\n"
]
}
],
"source": [
"model_lab_with_prompt.compare(\"New York\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "54336dbf",
"metadata": {},
"outputs": [],
"source": [
"from langchain import SelfAskWithSearchChain, SerpAPIWrapper\n",
"\n",
"open_ai_llm = OpenAI(temperature=0)\n",
"search = SerpAPIWrapper()\n",
"self_ask_with_search_openai = SelfAskWithSearchChain(llm=open_ai_llm, search_chain=search, verbose=True)\n",
"\n",
"cohere_llm = Cohere(temperature=0, model=\"command-xlarge-20221108\")\n",
"search = SerpAPIWrapper()\n",
"self_ask_with_search_cohere = SelfAskWithSearchChain(llm=cohere_llm, search_chain=search, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "6a50a9f1",
"metadata": {},
"outputs": [],
"source": [
"chains = [self_ask_with_search_openai, self_ask_with_search_cohere]\n",
"names = [str(open_ai_llm), str(cohere_llm)]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "d3549e99",
"metadata": {},
"outputs": [],
"source": [
"model_lab = ModelLaboratory(chains, names=names)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "362f7f57",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1mInput:\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"\n",
"\u001b[1mOpenAI\u001b[0m\n",
"Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n",
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[33;1m\u001b[1;3mCarlos Alcaraz.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Follow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[33;1m\u001b[1;3mEl Palmar, Spain.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"So the final answer is: El Palmar, Spain\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[36;1m\u001b[1;3m\n",
"So the final answer is: El Palmar, Spain\u001b[0m\n",
"\n",
"\u001b[1mCohere\u001b[0m\n",
"Params: {'model': 'command-xlarge-20221108', 'max_tokens': 256, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}\n",
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[33;1m\u001b[1;3mCarlos Alcaraz.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"So the final answer is:\n",
"\n",
"Carlos Alcaraz\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[33;1m\u001b[1;3m\n",
"So the final answer is:\n",
"\n",
"Carlos Alcaraz\u001b[0m\n",
"\n"
]
}
],
"source": [
"model_lab.compare(\"What is the hometown of the reigning men's U.S. Open champion?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "94159131",
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|