Skip to content

server: Add ability to mount server at prefix #14544

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.

Sign up for GitHub

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 4 commits into from
Jul 8, 2025
Merged

server: Add ability to mount server at prefix #14544

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4d02004
Add server_prefix
oluwandabira Jul 5, 2025
7b05916
Correct server path env
oluwandabira Jul 5, 2025
5607d97
Rename cli flag to --api-prefix
oluwandabira Jul 6, 2025
84285aa
Change all to api_prefix
oluwandabira Jul 7, 2025
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
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2734,6 +2734,13 @@ 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(
{"--prefix"}, "PREFIX",
string_format("prefix path the server serves from, without the trailing slash (default: %s)", params.server_prefix.c_str()),
[](common_params & params, const std::string & value) {
params.server_prefix = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SERVER_PATH"));
add_opt(common_arg(
{"--no-webui"},
string_format("Disable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
Expand Down
1 change: 1 addition & 0 deletions common/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,6 +370,7 @@ struct common_params {

std::string hostname = "127.0.0.1";
std::string public_path = ""; // NOLINT
std::string server_prefix = ""; // NOLINT
std::string chat_template = ""; // NOLINT
bool use_jinja = false; // NOLINT
bool enable_chat_template = true;
Expand Down
64 changes: 33 additions & 31 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4800,20 +4800,22 @@ int main(int argc, char ** argv) {
// Router
//

const char* server_prefix = params.server_prefix.c_str();

if (!params.webui) {
LOG_INF("Web UI is disabled\n");
} else {
// 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);
bool is_found = svr->set_mount_point(string_format("%s/", server_prefix), 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 & req, httplib::Response & res) {
svr->Get(string_format("%s/", server_prefix), [](const httplib::Request & req, httplib::Response & res) {
if (req.get_header_value("Accept-Encoding").find("gzip") == std::string::npos) {
res.set_content("Error: gzip is not supported by this browser", "text/plain");
} else {
Expand All @@ -4829,37 +4831,37 @@ int main(int argc, char ** argv) {
}

// register API routes
svr->Get ("/health", handle_health); // public endpoint (no API key check)
svr->Get ("/metrics", handle_metrics);
svr->Get ("/props", handle_props);
svr->Post("/props", handle_props_change);
svr->Post("/api/show", handle_api_show);
svr->Get ("/models", handle_models); // public endpoint (no API key check)
svr->Get ("/v1/models", handle_models); // public endpoint (no API key check)
svr->Get ("/api/tags", handle_models); // ollama specific endpoint. public endpoint (no API key check)
svr->Post("/completion", handle_completions); // legacy
svr->Post("/completions", handle_completions);
svr->Post("/v1/completions", handle_completions_oai);
svr->Post("/chat/completions", handle_chat_completions);
svr->Post("/v1/chat/completions", handle_chat_completions);
svr->Post("/api/chat", handle_chat_completions); // ollama specific endpoint
svr->Post("/infill", handle_infill);
svr->Post("/embedding", handle_embeddings); // legacy
svr->Post("/embeddings", handle_embeddings);
svr->Post("/v1/embeddings", handle_embeddings_oai);
svr->Post("/rerank", handle_rerank);
svr->Post("/reranking", handle_rerank);
svr->Post("/v1/rerank", handle_rerank);
svr->Post("/v1/reranking", handle_rerank);
svr->Post("/tokenize", handle_tokenize);
svr->Post("/detokenize", handle_detokenize);
svr->Post("/apply-template", handle_apply_template);
svr->Get (string_format("%s/health", server_prefix), handle_health); // public endpoint (no API key check)
svr->Get (string_format("%s/metrics", server_prefix), handle_metrics);
svr->Get (string_format("%s/props", server_prefix), handle_props);
svr->Post(string_format("%s/props", server_prefix), handle_props_change);
svr->Post(string_format("%s/api/show", server_prefix), handle_api_show);
svr->Get (string_format("%s/models", server_prefix), handle_models); // public endpoint (no API key check)
svr->Get (string_format("%s/v1/models", server_prefix), handle_models); // public endpoint (no API key check)
svr->Get (string_format("%s/api/tags", server_prefix), handle_models); // ollama specific endpoint. public endpoint (no API key check)
svr->Post(string_format("%s/completion", server_prefix), handle_completions); // legacy
svr->Post(string_format("%s/completions", server_prefix), handle_completions);
svr->Post(string_format("%s/v1/completions", server_prefix), handle_completions_oai);
svr->Post(string_format("%s/chat/completions", server_prefix), handle_chat_completions);
svr->Post(string_format("%s/v1/chat/completions", server_prefix), handle_chat_completions);
svr->Post(string_format("%s/api/chat", server_prefix), handle_chat_completions); // ollama specific endpoint
svr->Post(string_format("%s/infill", server_prefix), handle_infill);
svr->Post(string_format("%s/embedding", server_prefix), handle_embeddings); // legacy
svr->Post(string_format("%s/embeddings", server_prefix), handle_embeddings);
svr->Post(string_format("%s/v1/embeddings", server_prefix), handle_embeddings_oai);
svr->Post(string_format("%s/rerank", server_prefix), handle_rerank);
svr->Post(string_format("%s/reranking", server_prefix), handle_rerank);
svr->Post(string_format("%s/v1/rerank", server_prefix), handle_rerank);
svr->Post(string_format("%s/v1/reranking", server_prefix), handle_rerank);
svr->Post(string_format("%s/tokenize", server_prefix), handle_tokenize);
svr->Post(string_format("%s/detokenize", server_prefix), handle_detokenize);
svr->Post(string_format("%s/apply-template", server_prefix), handle_apply_template);
// LoRA adapters hotswap
svr->Get ("/lora-adapters", handle_lora_adapters_list);
svr->Post("/lora-adapters", handle_lora_adapters_apply);
svr->Get (string_format("%s/lora-adapters", server_prefix), handle_lora_adapters_list);
svr->Post(string_format("%s/lora-adapters", server_prefix), handle_lora_adapters_apply);
// Save & load slots
svr->Get ("/slots", handle_slots);
svr->Post("/slots/:id_slot", handle_slots_action);
svr->Get (string_format("%s/slots", server_prefix), handle_slots);
svr->Post(string_format("%s/slots/:id_slot", server_prefix), handle_slots_action);

//
// Start the server
Expand Down
Loading