Add openAI compatible API (#1810)
Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>
This commit is contained in:
Chayenne
@@ -4,19 +4,32 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Embedding Model"
|
||||
"# Embedding Model\n",
|
||||
"\n",
|
||||
"SGLang supports embedding models in the same way as completion models. Here are some example models:\n",
|
||||
"\n",
|
||||
"- [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct)\n",
|
||||
"- [Alibaba-NLP/gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Launch A Server"
|
||||
"## Launch A Server\n",
|
||||
"\n",
|
||||
"The following code is equivalent to running this in the shell:\n",
|
||||
"```bash\n",
|
||||
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
|
||||
" --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Remember to add `--is-embedding` to the command."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -28,14 +41,14 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Equivalent to running this in the shell:\n",
|
||||
"# python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
|
||||
"from sglang.utils import execute_shell_command, wait_for_server, terminate_process\n",
|
||||
"\n",
|
||||
"embedding_process = execute_shell_command(\"\"\"\n",
|
||||
"embedding_process = execute_shell_command(\n",
|
||||
" \"\"\"\n",
|
||||
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
|
||||
" --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
|
||||
"\"\"\")\n",
|
||||
"\"\"\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"wait_for_server(\"http://localhost:30010\")\n",
|
||||
"\n",
|
||||
@@ -51,25 +64,32 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[0.0083160400390625, 0.0006804466247558594, -0.00809478759765625, -0.0006995201110839844, 0.0143890380859375, -0.0090179443359375, 0.01238250732421875, 0.00209808349609375, 0.0062103271484375, -0.003047943115234375]\n"
|
||||
"Text embedding (first 10): [0.0083160400390625, 0.0006804466247558594, -0.00809478759765625, -0.0006995201110839844, 0.0143890380859375, -0.0090179443359375, 0.01238250732421875, 0.00209808349609375, 0.0062103271484375, -0.003047943115234375]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Get the first 10 elements of the embedding\n",
|
||||
"import subprocess, json\n",
|
||||
"\n",
|
||||
"! curl -s http://localhost:30010/v1/embeddings \\\n",
|
||||
"text = \"Once upon a time\"\n",
|
||||
"\n",
|
||||
"curl_text = f\"\"\"curl -s http://localhost:30010/v1/embeddings \\\n",
|
||||
" -H \"Content-Type: application/json\" \\\n",
|
||||
" -H \"Authorization: Bearer None\" \\\n",
|
||||
" -d '{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": \"Once upon a time\"}' \\\n",
|
||||
" | python3 -c \"import sys, json; print(json.load(sys.stdin)['data'][0]['embedding'][:10])\""
|
||||
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
|
||||
"\n",
|
||||
"text_embedding = json.loads(subprocess.check_output(curl_text, shell=True))[\"data\"][0][\n",
|
||||
" \"embedding\"\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"print(f\"Text embedding (first 10): {text_embedding[:10]}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -81,37 +101,79 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[0.00603485107421875, -0.0190582275390625, -0.01273345947265625, 0.01552581787109375, 0.0066680908203125, -0.0135955810546875, 0.01131439208984375, 0.0013713836669921875, -0.0089874267578125, 0.021759033203125]\n"
|
||||
"Text embedding (first 10): [0.00829315185546875, 0.0007004737854003906, -0.00809478759765625, -0.0006799697875976562, 0.01438140869140625, -0.00897979736328125, 0.0123748779296875, 0.0020923614501953125, 0.006195068359375, -0.0030498504638671875]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import openai\n",
|
||||
"\n",
|
||||
"client = openai.Client(\n",
|
||||
" base_url=\"http://127.0.0.1:30010/v1\", api_key=\"None\"\n",
|
||||
")\n",
|
||||
"client = openai.Client(base_url=\"http://127.0.0.1:30010/v1\", api_key=\"None\")\n",
|
||||
"\n",
|
||||
"# Text embedding example\n",
|
||||
"response = client.embeddings.create(\n",
|
||||
" model=\"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
|
||||
" input=\"How are you today\",\n",
|
||||
" input=text,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"embedding = response.data[0].embedding[:10]\n",
|
||||
"print(embedding)"
|
||||
"print(f\"Text embedding (first 10): {embedding}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using Input IDs\n",
|
||||
"\n",
|
||||
"SGLang also supports `input_ids` as input to get the embedding."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Input IDs embedding (first 10): [0.00829315185546875, 0.0007004737854003906, -0.00809478759765625, -0.0006799697875976562, 0.01438140869140625, -0.00897979736328125, 0.0123748779296875, 0.0020923614501953125, 0.006195068359375, -0.0030498504638671875]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"import os\n",
|
||||
"from transformers import AutoTokenizer\n",
|
||||
"\n",
|
||||
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
|
||||
"\n",
|
||||
"tokenizer = AutoTokenizer.from_pretrained(\"Alibaba-NLP/gte-Qwen2-7B-instruct\")\n",
|
||||
"input_ids = tokenizer.encode(text)\n",
|
||||
"\n",
|
||||
"curl_ids = f\"\"\"curl -s http://localhost:30010/v1/embeddings \\\n",
|
||||
" -H \"Content-Type: application/json\" \\\n",
|
||||
" -H \"Authorization: Bearer None\" \\\n",
|
||||
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
|
||||
"\n",
|
||||
"input_ids_embedding = json.loads(subprocess.check_output(curl_ids, shell=True))[\"data\"][\n",
|
||||
" 0\n",
|
||||
"][\"embedding\"]\n",
|
||||
"\n",
|
||||
"print(f\"Input IDs embedding (first 10): {input_ids_embedding[:10]}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
||||
Reference in New Issue
Block a user