Spaces:
Sleeping
Sleeping
File size: 7,838 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 |
{
"cells": [
{
"cell_type": "markdown",
"id": "6eaf7e66-f49c-42da-8d11-22ea13bef718",
"metadata": {},
"source": [
"# How to stream LLM and Chat Model responses\n",
"\n",
"LangChain provides streaming support for LLMs. Currently, we support streaming for the `OpenAI`, `ChatOpenAI`, and `ChatAnthropic` implementations, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "4ac0ff54-540a-4f2b-8d9a-b590fec7fe07",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chat_models import ChatOpenAI, ChatAnthropic\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"from langchain.schema import HumanMessage"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "77f60a4b-f786-41f2-972e-e5bb8a48dcd5",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Verse 1\n",
"I'm sippin' on sparkling water,\n",
"It's so refreshing and light,\n",
"It's the perfect way to quench my thirst\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed.\n",
"\n",
"Verse 2\n",
"I'm sippin' on sparkling water,\n",
"It's so bubbly and bright,\n",
"It's the perfect way to cool me down\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed.\n",
"\n",
"Verse 3\n",
"I'm sippin' on sparkling water,\n",
"It's so light and so clear,\n",
"It's the perfect way to keep me cool\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed."
]
}
],
"source": [
"llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = llm(\"Write me a song about sparkling water.\")"
]
},
{
"cell_type": "markdown",
"id": "61fb6de7-c6c8-48d0-a48e-1204c027a23c",
"metadata": {
"tags": []
},
"source": [
"We still have access to the end `LLMResult` if using `generate`. However, `token_usage` is not currently supported for streaming."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a35373f1-9ee6-4753-a343-5aee749b8527",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Q: What did the fish say when it hit the wall?\n",
"A: Dam!"
]
},
{
"data": {
"text/plain": [
"LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {}, 'model_name': 'text-davinci-003'})"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm.generate([\"Tell me a joke.\"])"
]
},
{
"cell_type": "markdown",
"id": "a93a4d61-0476-49db-8321-7de92bd74059",
"metadata": {},
"source": [
"Here's an example with the `ChatOpenAI` chat model implementation:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "22665f16-e05b-473c-a4bd-ad75744ea024",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Verse 1:\n",
"Bubbles rising to the top\n",
"A refreshing drink that never stops\n",
"Clear and crisp, it's oh so pure\n",
"Sparkling water, I can't ignore\n",
"\n",
"Chorus:\n",
"Sparkling water, oh how you shine\n",
"A taste so clean, it's simply divine\n",
"You quench my thirst, you make me feel alive\n",
"Sparkling water, you're my favorite vibe\n",
"\n",
"Verse 2:\n",
"No sugar, no calories, just H2O\n",
"A drink that's good for me, don't you know\n",
"With lemon or lime, you're even better\n",
"Sparkling water, you're my forever\n",
"\n",
"Chorus:\n",
"Sparkling water, oh how you shine\n",
"A taste so clean, it's simply divine\n",
"You quench my thirst, you make me feel alive\n",
"Sparkling water, you're my favorite vibe\n",
"\n",
"Bridge:\n",
"You're my go-to drink, day or night\n",
"You make me feel so light\n",
"I'll never give you up, you're my true love\n",
"Sparkling water, you're sent from above\n",
"\n",
"Chorus:\n",
"Sparkling water, oh how you shine\n",
"A taste so clean, it's simply divine\n",
"You quench my thirst, you make me feel alive\n",
"Sparkling water, you're my favorite vibe\n",
"\n",
"Outro:\n",
"Sparkling water, you're the one for me\n",
"I'll never let you go, can't you see\n",
"You're my drink of choice, forevermore\n",
"Sparkling water, I adore."
]
}
],
"source": [
"chat = ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
]
},
{
"cell_type": "markdown",
"id": "909ae48b-0f07-4990-bbff-e627f706c93e",
"metadata": {},
"source": [
"Here is an example with the `ChatAnthropic` chat model implementation, which uses their `claude` model."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "eadae4ba-9f21-4ec8-845d-dd43b0edc2dc",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Here is my attempt at a song about sparkling water:\n",
"\n",
"Sparkling water, bubbles so bright, \n",
"Dancing in the glass with delight.\n",
"Refreshing and crisp, a fizzy delight,\n",
"Quenching my thirst with each sip I take.\n",
"The carbonation tickles my tongue,\n",
"As the refreshing water song is sung.\n",
"Lime or lemon, a citrus twist,\n",
"Makes sparkling water such a bliss.\n",
"Healthy and hydrating, a drink so pure,\n",
"Sparkling water, always alluring.\n",
"Bubbles ascending in a stream, \n",
"Sparkling water, you're my dream!"
]
}
],
"source": [
"chat = ChatAnthropic(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
]
}
],
"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
}
|