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 loading html page while model is loading (#9468)

Browse Source 
* Adding loading page for '/' server requests

* set content when model is loading

* removed loading html file

* updated cmakelist

* updated makefile

* cleaned up whitespace

* cleanup for PR removed error

* updated server test to handle 503 HTML

* updated server test to handle 503 HTML

* ca†ch 503 before parsing json

* revert test

* account for both api and web browser requests

* precommit corrections

* eol fix

* revert changes to pre-commit

* removed print statement

* made loading message more descriptive

* also support .html files

---------

Co-authored-by: VJHack <flymyplane21@gmail.com>
Co-authored-by: Vinesh Janarthanan <36610342+VJHack@users.noreply.github.com>
This commit is contained in:
Xuan Son Nguyen
2024-09-13 14:23:11 +02:00
committed by GitHub
parent 0abc6a2c25
commit feff4aa846
4 changed files with 23 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/server/CMakeLists.txt
View File

@@ -30,6 +30,7 @@ set(PUBLIC_ASSETS
system-prompts.js
prompt-formats.js
json-schema-to-grammar.mjs
loading.html
)
foreach(asset ${PUBLIC_ASSETS})

12
examples/server/public/loading.html Normal file
View File

@@ -0,0 +1,12 @@
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="refresh" content="5">
</head>
<body>
<div id="loading">
The model is loading. Please wait.<br/>
The user interface will appear soon.
</div>
</body>
</html>

11
examples/server/server.cpp
View File

@@ -28,6 +28,7 @@
#include "system-prompts.js.hpp"
#include "prompt-formats.js.hpp"
#include "json-schema-to-grammar.mjs.hpp"
#include "loading.html.hpp"
#include <atomic>
#include <chrono>
@@ -2592,10 +2593,16 @@ int main(int argc, char ** argv) {
return false;
};
auto middleware_server_state = [&res_error, &state](const httplib::Request &, httplib::Response & res) {
auto middleware_server_state = [&res_error, &state](const httplib::Request & req, httplib::Response & res) {
server_state current_state = state.load();
if (current_state == SERVER_STATE_LOADING_MODEL) {
res_error(res, format_error_response("Loading model", ERROR_TYPE_UNAVAILABLE));
auto tmp = string_split(req.path, '.');
if (req.path == "/" || tmp.back() == "html") {
res.set_content(reinterpret_cast<const char*>(loading_html), loading_html_len, "text/html; charset=utf-8");
res.status = 503;
} else {
res_error(res, format_error_response("Loading model", ERROR_TYPE_UNAVAILABLE));
}
return false;
}
return true;