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

feat(oai refactor): Replace openai_api with entrypoints/openai (#7351)

Browse Source 
Co-authored-by: Jin Pan <jpan236@wisc.edu>
This commit is contained in:
Chang Su
2025-06-21 13:21:06 -07:00
committed by GitHub
parent 02bf31ef29
commit 72676cd6c0
43 changed files with 674 additions and 4555 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/backend/openai_api_embeddings.ipynb
View File

@@ -64,11 +64,14 @@
"text = \"Once upon a time\"\n",
"\n",
"curl_text = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -H \"Content-Type: application/json\" \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
"\n",
"text_embedding = json.loads(subprocess.check_output(curl_text, shell=True))[\"data\"][0][\n",
" \"embedding\"\n",
"]\n",
"result = subprocess.check_output(curl_text, shell=True)\n",
"\n",
"print(result)\n",
"\n",
"text_embedding = json.loads(result)[\"data\"][0][\"embedding\"]\n",
"\n",
"print_highlight(f\"Text embedding (first 10): {text_embedding[:10]}\")"
]
@@ -152,6 +155,7 @@
"input_ids = tokenizer.encode(text)\n",
"\n",
"curl_ids = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -H \"Content-Type: application/json\" \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
"\n",
"input_ids_embedding = json.loads(subprocess.check_output(curl_ids, shell=True))[\"data\"][\n",