Spaces:
Runtime error
Runtime error
File size: 4,436 Bytes
ed4d993 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "cd835d40",
"metadata": {},
"source": [
"# Multi-modal outputs: Image & Text"
]
},
{
"cell_type": "markdown",
"id": "fa88e03a",
"metadata": {},
"source": [
"This notebook shows how non-text producing tools can be used to create multi-modal agents.\n",
"\n",
"This example is limited to text and image outputs and uses UUIDs to transfer content across tools and agents. \n",
"\n",
"This example uses Steamship to generate and store generated images. Generated are auth protected by default. \n",
"\n",
"You can get your Steamship api key here: https://steamship.com/account/api"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0653da01",
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"\n",
"from IPython.display import Image, display\n",
"from steamship import Block, Steamship"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6933033",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import AgentType, initialize_agent\n",
"from langchain.tools import SteamshipImageGenerationTool\n",
"from langchain_openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "71e51e53",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "a9fc769d",
"metadata": {},
"source": [
"## Dall-E "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cd177dfe",
"metadata": {},
"outputs": [],
"source": [
"tools = [SteamshipImageGenerationTool(model_name=\"dall-e\")]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c71b1e46",
"metadata": {},
"outputs": [],
"source": [
"mrkl = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "603aeb9a",
"metadata": {},
"outputs": [],
"source": [
"output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "25eb4efe",
"metadata": {},
"outputs": [],
"source": [
"def show_output(output):\n",
" \"\"\"Display the multi-modal output from the agent.\"\"\"\n",
" UUID_PATTERN = re.compile(\n",
" r\"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{12})\"\n",
" )\n",
"\n",
" outputs = UUID_PATTERN.split(output)\n",
" outputs = [\n",
" re.sub(r\"^\\W+\", \"\", el) for el in outputs\n",
" ] # Clean trailing and leading non-word characters\n",
"\n",
" for output in outputs:\n",
" maybe_block_id = UUID_PATTERN.search(output)\n",
" if maybe_block_id:\n",
" display(Image(Block.get(Steamship(), _id=maybe_block_id.group()).raw()))\n",
" else:\n",
" print(output, end=\"\\n\\n\")"
]
},
{
"cell_type": "markdown",
"id": "e247b2c4",
"metadata": {},
"source": [
"## StableDiffusion "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "315025e7",
"metadata": {},
"outputs": [],
"source": [
"tools = [SteamshipImageGenerationTool(model_name=\"stable-diffusion\")]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7930064a",
"metadata": {},
"outputs": [],
"source": [
"mrkl = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "611a833d",
"metadata": {},
"outputs": [],
"source": [
"output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
]
}
],
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|