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

Docs: Only use X-Grammar in structed output (#2991)

Browse Source
This commit is contained in:
Chayenne
2025-01-19 20:22:47 -08:00
committed by GitHub
parent cd493b5afc
commit 0ffcfdf474
2 changed files with 22 additions and 202 deletions
Download Patch File Download Diff File Expand all files Collapse all files

131
docs/backend/openai_api_completions.ipynb
View File

@@ -41,10 +41,10 @@
")\n",
"\n",
"server_process = execute_shell_command(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0\"\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30020 --host 0.0.0.0\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30000\")"
"wait_for_server(\"http://localhost:30020\")"
]
},
{
@@ -68,7 +68,7 @@
"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=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
@@ -214,125 +214,8 @@
"metadata": {},
"source": [
"## Structured Outputs (JSON, Regex, EBNF)\n",
"You can specify a JSON schema, [regular expression](https://en.wikipedia.org/wiki/Regular_expression) or [EBNF](https://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_form) to constrain the model output. The model output will be guaranteed to follow the given constraints. Only one constraint parameter (`json_schema`, `regex`, or `ebnf`) can be specified for a request.\n",
"\n",
"SGLang supports two grammar backends:\n",
"\n",
"- [Outlines](https://github.com/dottxt-ai/outlines) (default): Supports JSON schema and regular expression constraints.\n",
"- [XGrammar](https://github.com/mlc-ai/xgrammar): Supports JSON schema, regular expression, and EBNF constraints.\n",
" - XGrammar currently uses the [GGML BNF format](https://github.com/ggerganov/llama.cpp/blob/master/grammars/README.md)\n",
"\n",
"Initialize the XGrammar backend using `--grammar-backend xgrammar` flag\n",
"```bash\n",
"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
"--port 30000 --host 0.0.0.0 --grammar-backend [xgrammar|outlines] # xgrammar or outlines (default: outlines)\n",
"```\n",
"\n",
"### JSON"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"json_schema = json.dumps(\n",
" {\n",
" \"type\": \"object\",\n",
" \"properties\": {\n",
" \"name\": {\"type\": \"string\", \"pattern\": \"^[\\\\w]+$\"},\n",
" \"population\": {\"type\": \"integer\"},\n",
" },\n",
" \"required\": [\"name\", \"population\"],\n",
" }\n",
")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": \"Give me the information of the capital of France in the JSON format.\",\n",
" },\n",
" ],\n",
" temperature=0,\n",
" max_tokens=128,\n",
" response_format={\n",
" \"type\": \"json_schema\",\n",
" \"json_schema\": {\"name\": \"foo\", \"schema\": json.loads(json_schema)},\n",
" },\n",
")\n",
"\n",
"print_highlight(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Regular expression (use default \"outlines\" backend)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": \"What is the capital of France?\"},\n",
" ],\n",
" temperature=0,\n",
" max_tokens=128,\n",
" extra_body={\"regex\": \"(Paris|London)\"},\n",
")\n",
"\n",
"print_highlight(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### EBNF (use \"xgrammar\" backend)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# terminate the existing server(that's using default outlines backend) for this demo\n",
"terminate_process(server_process)\n",
"\n",
"# start new server with xgrammar backend\n",
"server_process = execute_shell_command(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0 --grammar-backend xgrammar\"\n",
")\n",
"wait_for_server(\"http://localhost:30000\")\n",
"\n",
"# EBNF example\n",
"ebnf_grammar = r\"\"\"\n",
" root ::= \"Hello\" | \"Hi\" | \"Hey\"\n",
" \"\"\"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": \"You are a helpful EBNF test bot.\"},\n",
" {\"role\": \"user\", \"content\": \"Say a greeting.\"},\n",
" ],\n",
" temperature=0,\n",
" max_tokens=32,\n",
" extra_body={\"ebnf\": ebnf_grammar},\n",
")\n",
"\n",
"print_highlight(response.choices[0].message.content)"
"For OpenAI compatible structed outputs API, refer to [Structured Outputs](https://docs.sglang.ai/backend/structured_outputs.html#OpenAI-Compatible-API) for more details.\n"
]
},
{
@@ -362,7 +245,7 @@
"import time\n",
"from openai import OpenAI\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"\n",
"requests = [\n",
" {\n",
@@ -465,7 +348,7 @@
"import time\n",
"from openai import OpenAI\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"\n",
"requests = []\n",
"for i in range(100):\n",
@@ -542,7 +425,7 @@
"from openai import OpenAI\n",
"import os\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"\n",
"requests = []\n",
"for i in range(500):\n",