EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[CI] Improve Docs CI Efficiency (#3587)

Browse Source 
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
This commit is contained in:
Shi Shuai
2025-02-15 03:57:00 +00:00
committed by GitHub
parent 862dd76c76
commit 7443197a63
19 changed files with 366 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docs/backend/openai_api_embeddings.ipynb
View File

@@ -29,21 +29,23 @@
"metadata": {},
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
" wait_for_server,\n",
" terminate_process,\n",
" print_highlight,\n",
")\n",
"from sglang.test.test_utils import is_in_ci\n",
"\n",
"embedding_process = execute_shell_command(\n",
"if is_in_ci():\n",
" from patch import launch_server_cmd\n",
"else:\n",
" from sglang.utils import launch_server_cmd\n",
"\n",
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
"\n",
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
" --port 30000 --host 0.0.0.0 --is-embedding\n",
" --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30000\")"
"wait_for_server(f\"http://localhost:{port}\")"
]
},
{
@@ -63,7 +65,7 @@
"\n",
"text = \"Once upon a time\"\n",
"\n",
"curl_text = f\"\"\"curl -s http://localhost:30000/v1/embeddings \\\n",
"curl_text = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -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",
@@ -91,7 +93,7 @@
"text = \"Once upon a time\"\n",
"\n",
"response = requests.post(\n",
" \"http://localhost:30000/v1/embeddings\",\n",
" f\"http://localhost:{port}/v1/embeddings\",\n",
" json={\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": text},\n",
")\n",
"\n",
@@ -115,7 +117,7 @@
"source": [
"import openai\n",
"\n",
"client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"# Text embedding example\n",
"response = client.embeddings.create(\n",
@@ -151,7 +153,7 @@
"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:30000/v1/embeddings \\\n",
"curl_ids = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\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",
@@ -167,7 +169,7 @@
"metadata": {},
"outputs": [],
"source": [
"terminate_process(embedding_process)"
"terminate_process(embedding_process, port)"
]
}
],