Spaces:
Running
Running
File size: 3,492 Bytes
b247dc4 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use OpenAI\n",
"\n",
"Set you `OPENAI_API_KEY` environment variable."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'model_name': 'openaiembedding', 'engine': 'text-embedding-ada-002'}\n"
]
}
],
"source": [
"from manifest import Manifest\n",
"\n",
"manifest = Manifest(client_name=\"openaiembedding\")\n",
"print(manifest.client_pool.get_next_client().get_model_params())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(1536,)\n"
]
}
],
"source": [
"emb = manifest.run(\"Is this an embedding?\")\n",
"print(emb.shape)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Using Locally Hosted Huggingface LM\n",
"\n",
"Run\n",
"```\n",
"python3 manifest/api/app.py --model_type huggingface --model_name_or_path EleutherAI/gpt-neo-125M --device 0\n",
"```\n",
"or\n",
"```\n",
"python3 manifest/api/app.py --model_type sentence_transformers --model_name_or_path all-mpnet-base-v2 --device 0\n",
"```\n",
"\n",
"in a separate `screen` or `tmux`. Make sure to note the port. You can change this with `export FLASK_PORT=<port>`."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'model_name': 'all-mpnet-base-v2', 'model_path': 'all-mpnet-base-v2', 'client_name': 'huggingfaceembedding'}\n"
]
}
],
"source": [
"from manifest import Manifest\n",
"\n",
"# Local hosted GPT Neo 125M\n",
"manifest = Manifest(\n",
" client_name=\"huggingfaceembedding\",\n",
" client_connection=\"http://127.0.0.1:6000\",\n",
" cache_name=\"sqlite\",\n",
" cache_connection=\"my_sqlite_manifest.sqlite\"\n",
")\n",
"print(manifest.client_pool.get_next_client().get_model_params())"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(768,)\n",
"(768,) (768,)\n"
]
}
],
"source": [
"emb = manifest.run(\"Is this an embedding?\")\n",
"print(emb.shape)\n",
"\n",
"emb = manifest.run([\"Is this an embedding?\", \"Bananas!!!\"])\n",
"print(emb[0].shape, emb[1].shape)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "manifest",
"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": "3.10.4"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "fddffe4ac3b9f00470127629076101c1b5f38ecb1e7358b567d19305425e9491"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|