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

28
docs/backend/function_calling.ipynb
View File

@@ -31,17 +31,19 @@
"source": [
"from openai import OpenAI\n",
"import json\n",
"from sglang.utils import (\n",
" execute_shell_command,\n",
" wait_for_server,\n",
" terminate_process,\n",
" print_highlight,\n",
")\n",
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
"from sglang.test.test_utils import is_in_ci\n",
"\n",
"server_process = execute_shell_command(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --tool-call-parser llama3 --port 30333 --host 0.0.0.0\" # llama3\n",
"if is_in_ci():\n",
" from patch import launch_server_cmd\n",
"else:\n",
" from sglang.utils import launch_server_cmd\n",
"\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --tool-call-parser llama3 --host 0.0.0.0\" # llama3\n",
")\n",
"wait_for_server(\"http://localhost:30333\")"
"wait_for_server(f\"http://localhost:{port}\")"
]
},
{
@@ -141,7 +143,7 @@
"outputs": [],
"source": [
"# Initialize OpenAI-like client\n",
"client = OpenAI(api_key=\"None\", base_url=\"http://0.0.0.0:30333/v1\")\n",
"client = OpenAI(api_key=\"None\", base_url=f\"http://0.0.0.0:{port}/v1\")\n",
"model_name = client.models.list().data[0].id"
]
},
@@ -377,13 +379,13 @@
" tools=tools,\n",
")\n",
"\n",
"gen_url = \"http://localhost:30333/generate\"\n",
"gen_url = f\"http://localhost:{port}/generate\"\n",
"gen_data = {\"text\": input, \"sampling_params\": {\"skip_special_tokens\": False}}\n",
"gen_response = requests.post(gen_url, json=gen_data).json()[\"text\"]\n",
"print(gen_response)\n",
"\n",
"# parse the response\n",
"parse_url = \"http://localhost:30333/function_call\"\n",
"parse_url = f\"http://localhost:{port}/function_call\"\n",
"\n",
"function_call_input = {\n",
" \"text\": gen_response,\n",
@@ -403,7 +405,7 @@
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)"
"terminate_process(server_process, port)"
]
},
{