Spaces:
Configuration error
Configuration error
File size: 11,424 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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install litellm # version 0.1.724 or higher "
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Call Ollama - llama2 with Streaming"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<generator object get_ollama_response_stream at 0x109096c10>\n",
"{'role': 'assistant', 'content': ' I'}\n",
"{'role': 'assistant', 'content': \"'\"}\n",
"{'role': 'assistant', 'content': 'm'}\n",
"{'role': 'assistant', 'content': ' L'}\n",
"{'role': 'assistant', 'content': 'La'}\n",
"{'role': 'assistant', 'content': 'MA'}\n",
"{'role': 'assistant', 'content': ','}\n",
"{'role': 'assistant', 'content': ' an'}\n",
"{'role': 'assistant', 'content': ' A'}\n",
"{'role': 'assistant', 'content': 'I'}\n",
"{'role': 'assistant', 'content': ' assistant'}\n",
"{'role': 'assistant', 'content': ' developed'}\n",
"{'role': 'assistant', 'content': ' by'}\n",
"{'role': 'assistant', 'content': ' Meta'}\n",
"{'role': 'assistant', 'content': ' A'}\n",
"{'role': 'assistant', 'content': 'I'}\n",
"{'role': 'assistant', 'content': ' that'}\n",
"{'role': 'assistant', 'content': ' can'}\n",
"{'role': 'assistant', 'content': ' understand'}\n",
"{'role': 'assistant', 'content': ' and'}\n",
"{'role': 'assistant', 'content': ' respond'}\n",
"{'role': 'assistant', 'content': ' to'}\n",
"{'role': 'assistant', 'content': ' human'}\n",
"{'role': 'assistant', 'content': ' input'}\n",
"{'role': 'assistant', 'content': ' in'}\n",
"{'role': 'assistant', 'content': ' a'}\n",
"{'role': 'assistant', 'content': ' convers'}\n",
"{'role': 'assistant', 'content': 'ational'}\n",
"{'role': 'assistant', 'content': ' manner'}\n",
"{'role': 'assistant', 'content': '.'}\n"
]
}
],
"source": [
"from litellm import completion\n",
"\n",
"response = completion(\n",
" model=\"ollama/llama2\", \n",
" messages=[{ \"content\": \"respond in 20 words. who are you?\",\"role\": \"user\"}], \n",
" api_base=\"http://localhost:11434\",\n",
" stream=True\n",
")\n",
"print(response)\n",
"for chunk in response:\n",
" print(chunk['choices'][0]['delta'])\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Call Ollama - Llama2 with Acompletion + Streaming"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Defaulting to user installation because normal site-packages is not writeable\n",
"Requirement already satisfied: async_generator in /Users/ishaanjaffer/Library/Python/3.9/lib/python/site-packages (1.10)\n"
]
}
],
"source": [
"# litellm uses async_generator for ollama async streaming, ensure it's installed\n",
"!pip install async_generator"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'choices': [{'delta': {'role': 'assistant', 'content': ' I'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': \"'\"}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': 'm'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' just'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' an'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' A'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': 'I'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ','}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' I'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' don'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': \"'\"}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': 't'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' have'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' access'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' to'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' real'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': '-'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': 'time'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' weather'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' information'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' or'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' current'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' conditions'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' in'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' your'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' specific'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' location'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': '.'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' живело'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' can'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' provide'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' you'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' with'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' weather'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' forec'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': 'asts'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' and'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' information'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' for'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' your'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' location'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' if'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' you'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' would'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' like'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': '.'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' Please'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' let'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' me'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' know'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' where'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' you'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' are'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' located'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ','}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' and'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' I'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' will'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' do'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' my'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' best'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' to'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' assist'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': ' you'}}]}\n",
"{'choices': [{'delta': {'role': 'assistant', 'content': '.'}}]}\n",
"None\n"
]
}
],
"source": [
"import litellm\n",
"\n",
"async def async_ollama():\n",
" response = await litellm.acompletion(\n",
" model=\"ollama/llama2\", \n",
" messages=[{ \"content\": \"what's the weather\" ,\"role\": \"user\"}], \n",
" api_base=\"http://localhost:11434\", \n",
" stream=True\n",
" )\n",
" async for chunk in response:\n",
" print(chunk)\n",
"\n",
"result = await async_ollama()\n",
"print(result)\n",
"\n",
"try:\n",
" async for chunk in result:\n",
" print(chunk)\n",
"except TypeError: # the last chunk is None from Ollama, this raises an error with async streaming\n",
" pass"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Completion Call"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{\n",
" \"object\": \"chat.completion\",\n",
" \"choices\": [\n",
" {\n",
" \"finish_reason\": \"stop\",\n",
" \"index\": 0,\n",
" \"message\": {\n",
" \"content\": \" I'm LLaMA, an AI assistant developed by Meta AI that can understand and respond to human input in a conversational manner.\",\n",
" \"role\": \"assistant\",\n",
" \"logprobs\": null\n",
" }\n",
" }\n",
" ],\n",
" \"id\": \"chatcmpl-ea7b8242-791f-4656-ba12-e098edeb960e\",\n",
" \"created\": 1695324686.6696231,\n",
" \"response_ms\": 4072.3050000000003,\n",
" \"model\": \"ollama/llama2\",\n",
" \"usage\": {\n",
" \"prompt_tokens\": 10,\n",
" \"completion_tokens\": 27,\n",
" \"total_tokens\": 37\n",
" }\n",
"}\n"
]
}
],
"source": [
"from litellm import completion\n",
"\n",
"response = completion(\n",
" model=\"ollama/llama2\", \n",
" messages=[{ \"content\": \"respond in 20 words. who are you?\",\"role\": \"user\"}], \n",
" api_base=\"http://localhost:11434\"\n",
")\n",
"print(response)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.9.6"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|