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

Fix docs (#1890)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-11-02 13:26:32 -07:00
committed by GitHub
parent 5a5f18432f
commit be7986e005
7 changed files with 34 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/backend/openai_api_embeddings.ipynb
View File

@@ -24,7 +24,7 @@
"\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\n",
" --port 30000 --host 0.0.0.0 --is-embedding\n",
"```\n",
"\n",
"Remember to add `--is-embedding` to the command."
@@ -53,11 +53,11 @@
"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\n",
" --port 30000 --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30010\")"
"wait_for_server(\"http://localhost:30000\")"
]
},
{
@@ -84,7 +84,7 @@
"\n",
"text = \"Once upon a time\"\n",
"\n",
"curl_text = f\"\"\"curl -s http://localhost:30010/v1/embeddings \\\n",
"curl_text = f\"\"\"curl -s http://localhost:30000/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",
@@ -112,7 +112,7 @@
"text = \"Once upon a time\"\n",
"\n",
"response = requests.post(\n",
" \"http://localhost:30010/v1/embeddings\",\n",
" \"http://localhost:30000/v1/embeddings\",\n",
" json={\n",
" \"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
" \"input\": text\n",
@@ -146,7 +146,7 @@
"source": [
"import openai\n",
"\n",
"client = openai.Client(base_url=\"http://127.0.0.1:30010/v1\", api_key=\"None\")\n",
"client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
"\n",
"# Text embedding example\n",
"response = client.embeddings.create(\n",
@@ -189,7 +189,7 @@
"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:30010/v1/embeddings \\\n",
"curl_ids = f\"\"\"curl -s http://localhost:30000/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",