Skip to content

server: add flag to disable the web ui #10751

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 10, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions common/arg.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1711,6 +1711,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.public_path = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_STATIC_PATH"));
add_opt(common_arg(
{"--no-webui"},
string_format("Disable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
[](common_params & params) {
params.webui = false;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_WEBUI"));
add_opt(common_arg(
{"--embedding", "--embeddings"},
string_format("restrict to only support embedding use case; use only with dedicated embedding models (default: %s)", params.embedding ? "enabled" : "disabled"),
Expand Down
1 change: 1 addition & 0 deletions examples/server/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,7 @@ The project is under active development, and we are [looking for feedback and co
| `--host HOST` | ip address to listen (default: 127.0.0.1)<br/>(env: LLAMA_ARG_HOST) |
| `--port PORT` | port to listen (default: 8080)<br/>(env: LLAMA_ARG_PORT) |
| `--path PATH` | path to serve static files from (default: )<br/>(env: LLAMA_ARG_STATIC_PATH) |
| `--no-webui` | disable the Web UI<br/>(env: LLAMA_ARG_NO_WEBUI) |
| `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
| `--reranking, --rerank` | enable reranking endpoint on server (default: disabled)<br/>(env: LLAMA_ARG_RERANKING) |
| `--api-key KEY` | API key to use for authentication (default: none)<br/>(env: LLAMA_API_KEY) |
Expand Down
30 changes: 17 additions & 13 deletions examples/server/server.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -3815,20 +3815,24 @@ int main(int argc, char ** argv) {
// Router
//

// register static assets routes
if (!params.public_path.empty()) {
// Set the base directory for serving static files
bool is_found = svr->set_mount_point("/", params.public_path);
if (!is_found) {
LOG_ERR("%s: static assets path not found: %s\n", __func__, params.public_path.c_str());
return 1;
}
if (!params.webui) {
LOG_INF("Web UI is disabled\n");
} else {
// using embedded static index.html
svr->Get("/", [](const httplib::Request &, httplib::Response & res) {
res.set_content(reinterpret_cast<const char*>(index_html), index_html_len, "text/html; charset=utf-8");
return false;
});
// register static assets routes
if (!params.public_path.empty()) {
// Set the base directory for serving static files
bool is_found = svr->set_mount_point("/", params.public_path);
if (!is_found) {
LOG_ERR("%s: static assets path not found: %s\n", __func__, params.public_path.c_str());
return 1;
}
} else {
// using embedded static index.html
svr->Get("/", [](const httplib::Request &, httplib::Response & res) {
res.set_content(reinterpret_cast<const char*>(index_html), index_html_len, "text/html; charset=utf-8");
return false;
});
}
}

// register API routes
Expand Down
18 changes: 18 additions & 0 deletions examples/server/tests/unit/test_basic.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import pytest
import requests
from utils import *

server = ServerPreset.tinyllama2()
Expand Down Expand Up @@ -76,3 +77,20 @@ def test_load_split_model():
})
assert res.status_code == 200
assert match_regex("(little|girl)+", res.body["content"])


def test_no_webui():
global server
# default: webui enabled
server.start()
url = f"http://{server.server_host}:{server.server_port}"
res = requests.get(url)
assert res.status_code == 200
assert "<html>" in res.text
server.stop()

# with --no-webui
server.no_webui = True
server.start()
res = requests.get(url)
assert res.status_code == 404
3 changes: 3 additions & 0 deletions examples/server/tests/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,7 @@ class ServerProcess:
disable_ctx_shift: int | None = False
draft_min: int | None = None
draft_max: int | None = None
no_webui: bool | None = None

# session variables
process: subprocess.Popen | None = None
Expand Down Expand Up @@ -158,6 +159,8 @@ def start(self, timeout_seconds: int = 10) -> None:
server_args.extend(["--draft-max", self.draft_max])
if self.draft_min:
server_args.extend(["--draft-min", self.draft_min])
if self.no_webui:
server_args.append("--no-webui")

args = [str(arg) for arg in [server_path, *server_args]]
print(f"bench: starting server with: {' '.join(args)}")
Expand Down
Loading