Spaces:
Configuration error
Configuration error
File size: 13,809 Bytes
447ebeb |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "MZ01up0p7wOJ"
},
"source": [
"## 🚅 liteLLM Quick Start Demo\n",
"### TLDR: Call 50+ LLM APIs using chatGPT Input/Output format\n",
"https://github.com/BerriAI/litellm\n",
"\n",
"liteLLM is package to simplify calling **OpenAI, Azure, Llama2, Cohere, Anthropic, Huggingface API Endpoints**. LiteLLM manages\n",
"\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "RZtzCnQS7rW-"
},
"source": [
"## Installation and setting Params"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "rsrN5W-N7L8d"
},
"outputs": [],
"source": [
"!pip install litellm"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "ArrWyG5b7QAG"
},
"outputs": [],
"source": [
"from litellm import completion\n",
"import os"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "bbhJRt34_NJ1"
},
"source": [
"## Set your API keys\n",
"- liteLLM reads your .env, env variables or key manager for Auth\n",
"\n",
"Set keys for the models you want to use below"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"id": "-h8Ga5cR7SvV"
},
"outputs": [],
"source": [
"# Only set keys for the LLMs you want to use\n",
"os.environ['OPENAI_API_KEY'] = \"\" #@param\n",
"os.environ[\"ANTHROPIC_API_KEY\"] = \"\" #@param\n",
"os.environ[\"REPLICATE_API_KEY\"] = \"\" #@param\n",
"os.environ[\"COHERE_API_KEY\"] = \"\" #@param\n",
"os.environ[\"AZURE_API_BASE\"] = \"\" #@param\n",
"os.environ[\"AZURE_API_VERSION\"] = \"\" #@param\n",
"os.environ[\"AZURE_API_KEY\"] = \"\" #@param"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "fhqpKv6L8fBj"
},
"source": [
"## Call chatGPT"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "speIkoX_8db4",
"outputId": "331a6c65-f121-4e65-e121-bf8aaad05d9d"
},
"outputs": [
{
"data": {
"text/plain": [
"<OpenAIObject chat.completion id=chatcmpl-820kPkRwSLml4X6165fWbZlEDOedr at 0x12ff93630> JSON: {\n",
" \"id\": \"chatcmpl-820kPkRwSLml4X6165fWbZlEDOedr\",\n",
" \"object\": \"chat.completion\",\n",
" \"created\": 1695490221,\n",
" \"model\": \"gpt-3.5-turbo-0613\",\n",
" \"choices\": [\n",
" {\n",
" \"index\": 0,\n",
" \"message\": {\n",
" \"role\": \"assistant\",\n",
" \"content\": \"I'm sorry, but as an AI text-based model, I don't have real-time information. However, you can check the current weather in San Francisco by searching for \\\"weather in SF\\\" on any search engine or checking a weather website or app.\"\n",
" },\n",
" \"finish_reason\": \"stop\"\n",
" }\n",
" ],\n",
" \"usage\": {\n",
" \"prompt_tokens\": 13,\n",
" \"completion_tokens\": 51,\n",
" \"total_tokens\": 64\n",
" },\n",
" \"response_ms\": 2385.592\n",
"}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"completion(model=\"gpt-3.5-turbo\", messages=[{ \"content\": \"what's the weather in SF\",\"role\": \"user\"}])"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "Q3jV1Uxv8zNo"
},
"source": [
"## Call Claude-2"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "V8yTWYzY8m9S",
"outputId": "8b6dd32d-f9bf-4e89-886d-47cb8020f025"
},
"outputs": [
{
"data": {
"text/plain": [
"<ModelResponse chat.completion id=chatcmpl-6d1a40c0-19c0-4bd7-9ca2-a91d8b8c2295 at 0x12ff85a40> JSON: {\n",
" \"object\": \"chat.completion\",\n",
" \"choices\": [\n",
" {\n",
" \"finish_reason\": \"stop_sequence\",\n",
" \"index\": 0,\n",
" \"message\": {\n",
" \"content\": \" Unfortunately I don't have enough context to know the exact location you are asking about when you say \\\"SF\\\". SF could refer to San Francisco, California, or potentially other cities that go by SF as an abbreviation. To get an accurate weather report, it would be helpful if you could provide the full city name and state/country. If you are looking for the weather in San Francisco, California, I would be happy to provide that forecast. Please let me know the specific location you want the weather for.\",\n",
" \"role\": \"assistant\",\n",
" \"logprobs\": null\n",
" }\n",
" }\n",
" ],\n",
" \"id\": \"chatcmpl-6d1a40c0-19c0-4bd7-9ca2-a91d8b8c2295\",\n",
" \"created\": 1695490260.983768,\n",
" \"response_ms\": 6351.544,\n",
" \"model\": \"claude-2\",\n",
" \"usage\": {\n",
" \"prompt_tokens\": 14,\n",
" \"completion_tokens\": 102,\n",
" \"total_tokens\": 116\n",
" }\n",
"}"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"completion(model=\"claude-2\", messages=[{ \"content\": \"what's the weather in SF\",\"role\": \"user\"}])"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "yu0LPDmW9PJa"
},
"source": [
"## Call llama2 on replicate"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "0GWV5mtO9Jbu",
"outputId": "38538825-b271-406d-a437-f5cf0eb7e548"
},
"outputs": [
{
"data": {
"text/plain": [
"<ModelResponse chat.completion id=chatcmpl-3151c2eb-b26f-4c96-89b5-ed1746b219e0 at 0x138b87e50> JSON: {\n",
" \"object\": \"chat.completion\",\n",
" \"choices\": [\n",
" {\n",
" \"finish_reason\": \"stop\",\n",
" \"index\": 0,\n",
" \"message\": {\n",
" \"content\": \" I'm happy to help! However, I must point out that the question \\\"what's the weather in SF\\\" doesn't make sense as \\\"SF\\\" could refer to multiple locations. Could you please clarify which location you are referring to? San Francisco, California or Sioux Falls, South Dakota? Once I have more context, I would be happy to provide you with accurate and reliable information.\",\n",
" \"role\": \"assistant\",\n",
" \"logprobs\": null\n",
" }\n",
" }\n",
" ],\n",
" \"id\": \"chatcmpl-3151c2eb-b26f-4c96-89b5-ed1746b219e0\",\n",
" \"created\": 1695490237.714101,\n",
" \"response_ms\": 12109.565,\n",
" \"model\": \"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1\",\n",
" \"usage\": {\n",
" \"prompt_tokens\": 6,\n",
" \"completion_tokens\": 78,\n",
" \"total_tokens\": 84\n",
" },\n",
" \"ended\": 1695490249.821266\n",
"}"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = \"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1\"\n",
"completion(model=model, messages=[{ \"content\": \"what's the weather in SF\",\"role\": \"user\"}])"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "HXdj5SEe9iLK"
},
"source": [
"## Call Command-Nightly"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "EaUq2xIx9fhr",
"outputId": "55fe6f52-b58b-4729-948a-74dac4b431b2"
},
"outputs": [
{
"data": {
"text/plain": [
"<ModelResponse chat.completion id=chatcmpl-dc0d8ead-071d-486c-a111-78975b38794b at 0x1389725e0> JSON: {\n",
" \"object\": \"chat.completion\",\n",
" \"choices\": [\n",
" {\n",
" \"finish_reason\": \"stop\",\n",
" \"index\": 0,\n",
" \"message\": {\n",
" \"content\": \" As an AI model I don't have access to real-time data, so I can't tell\",\n",
" \"role\": \"assistant\",\n",
" \"logprobs\": null\n",
" }\n",
" }\n",
" ],\n",
" \"id\": \"chatcmpl-dc0d8ead-071d-486c-a111-78975b38794b\",\n",
" \"created\": 1695490235.936903,\n",
" \"response_ms\": 1022.6759999999999,\n",
" \"model\": \"command-nightly\",\n",
" \"usage\": {\n",
" \"prompt_tokens\": 6,\n",
" \"completion_tokens\": 19,\n",
" \"total_tokens\": 25\n",
" }\n",
"}"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"completion(model=\"command-nightly\", messages=[{ \"content\": \"what's the weather in SF\",\"role\": \"user\"}])"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "1g9hSgsL9soJ"
},
"source": [
"## Call Azure OpenAI"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"For azure openai calls ensure to add the `azure/` prefix to `model`. If your deployment-id is `chatgpt-test` set `model` = `azure/chatgpt-test`"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "AvLjR-PF-lt0",
"outputId": "deff2db3-b003-48cd-ea62-c03a68a4464a"
},
"outputs": [
{
"data": {
"text/plain": [
"<OpenAIObject chat.completion id=chatcmpl-820kZyCwbNvZATiLkNmXmpxxzvTKO at 0x138b84ae0> JSON: {\n",
" \"id\": \"chatcmpl-820kZyCwbNvZATiLkNmXmpxxzvTKO\",\n",
" \"object\": \"chat.completion\",\n",
" \"created\": 1695490231,\n",
" \"model\": \"gpt-35-turbo\",\n",
" \"choices\": [\n",
" {\n",
" \"index\": 0,\n",
" \"finish_reason\": \"stop\",\n",
" \"message\": {\n",
" \"role\": \"assistant\",\n",
" \"content\": \"Sorry, as an AI language model, I don't have real-time information. Please check your preferred weather website or app for the latest weather updates of San Francisco.\"\n",
" }\n",
" }\n",
" ],\n",
" \"usage\": {\n",
" \"completion_tokens\": 33,\n",
" \"prompt_tokens\": 14,\n",
" \"total_tokens\": 47\n",
" },\n",
" \"response_ms\": 1499.529\n",
"}"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"completion(model=\"azure/chatgpt-v-2\", messages=[{ \"content\": \"what's the weather in SF\",\"role\": \"user\"}])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|