Skip to content

server : implement /api/version endpoint for ollama compatibility (#15167 ) #15177

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

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+20 −2
Open

server : implement /api/version endpoint for ollama compatibility (#15167 ) #15177

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
84bcf50
adding a fake ollama version endpoint
albert-polak Aug 8, 2025
5589224
apply suggestions from comments
albert-polak Aug 11, 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
22 changes: 20 additions & 2 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3810,7 +3810,8 @@ int main(int argc, char ** argv) {
"/health",
"/models",
"/v1/models",
"/api/tags"
"/api/tags",
"/api/version"
};

// If API key is not set, skip validation
Expand Down Expand Up @@ -3849,7 +3850,7 @@ int main(int argc, char ** argv) {
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 if (req.path == "/models" || req.path == "/v1/models" || req.path == "/api/tags") {
} else if (req.path == "/models" || req.path == "/v1/models" || req.path == "/api/tags" || req.path == "/api/version") {
// allow the models endpoint to be accessed during loading
return true;
} else {
Expand Down Expand Up @@ -4545,6 +4546,22 @@ int main(int argc, char ** argv) {
res_ok(res, models);
};

const auto handle_version = [&ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) {
json version;
char* version_override = std::getenv("LLAMA_API_VERSION_OVERRIDE");
if (version_override) {
version = {
{"version", std::string(version_override)}
};
} else {
version = {
{"version", std::to_string(LLAMA_BUILD_NUMBER)}
};
}

res_ok(res, version);
};

const auto handle_tokenize = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) {
const json body = json::parse(req.body);

Expand Down Expand Up @@ -4883,6 +4900,7 @@ int main(int argc, char ** argv) {
svr->Get (params.api_prefix + "/models", handle_models); // public endpoint (no API key check)
svr->Get (params.api_prefix + "/v1/models", handle_models); // public endpoint (no API key check)
svr->Get (params.api_prefix + "/api/tags", handle_models); // ollama specific endpoint. public endpoint (no API key check)
svr->Get (params.api_prefix + "/api/version", handle_version); // public endpoint (no API key check)
svr->Post(params.api_prefix + "/completion", handle_completions); // legacy
svr->Post(params.api_prefix + "/completions", handle_completions);
svr->Post(params.api_prefix + "/v1/completions", handle_completions_oai);
Expand Down