CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add flag to disable the web-ui (#10762) (#10751)

Browse Source 
Co-authored-by: eugenio.segala <esegala@deloitte.co.uk>
This commit is contained in:
Yüg
2024-12-10 17:22:34 +00:00
committed by GitHub
parent a05e2afcc2
commit a86ad841f1
5 changed files with 46 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/server/README.md
View File

@@ -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) |

30
examples/server/server.cpp
View File

@@ -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

18
examples/server/tests/unit/test_basic.py
View File

@@ -1,4 +1,5 @@
import pytest
import requests
from utils import *
server = ServerPreset.tinyllama2()
@@ -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
examples/server/tests/utils.py
View File

@@ -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
@@ -158,6 +159,8 @@ class ServerProcess:
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)}")