Skip to content

Handling correctly negative values in /v3/tokenize endpoint #4324

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
przepeck wants to merge 2 commits into
base: main
Choose a base branch
from
+44 −4
Open

Handling correctly negative values in /v3/tokenize endpoint #4324

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e1e8e23
handling negative values
przepeck Jun 25, 2026
b80f8a0
adding handlig zero
przepeck Jun 26, 2026
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
38 changes: 37 additions & 1 deletion src/test/tokenize_parser_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,7 @@ TEST(TokenizeDeserialization, invalidTokenizeMaxLengthType) {
auto status = ovms::TokenizeParser::parseTokenizeRequest(d, request);
ASSERT_NE(status, absl::OkStatus());
auto error = status.message();
ASSERT_EQ(error, "max_length should be integer");
ASSERT_EQ(error, "max_length should be unsigned integer");
}

TEST(TokenizeDeserialization, invalidTokenizePadToMaxLengthType) {
Expand Down Expand Up @@ -228,3 +228,39 @@ TEST(TokenizeDeserialization, invalidTokenizePaddingSideValue) {
auto error = status.message();
ASSERT_EQ(error, "padding_side should be either left or right");
}

TEST(TokenizeDeserialization, invalidTokenizeMaxLengthNegative) {
std::string requestBody = R"(
{
"model": "embeddings",
"text": ["one", "two", "three"],
"max_length": -10
}
)";
rapidjson::Document d;
rapidjson::ParseResult ok = d.Parse(requestBody.c_str());
ovms::TokenizeRequest request;
ASSERT_EQ(ok.Code(), 0);
auto status = ovms::TokenizeParser::parseTokenizeRequest(d, request);
ASSERT_NE(status, absl::OkStatus());
auto error = status.message();
ASSERT_EQ(error, "max_length should be unsigned integer");
}

TEST(TokenizeDeserialization, invalidTokenizeMaxLengthZero) {
std::string requestBody = R"(
{
"model": "embeddings",
"text": ["one", "two", "three"],
"max_length": 0
}
)";
rapidjson::Document d;
rapidjson::ParseResult ok = d.Parse(requestBody.c_str());
ovms::TokenizeRequest request;
ASSERT_EQ(ok.Code(), 0);
auto status = ovms::TokenizeParser::parseTokenizeRequest(d, request);
ASSERT_NE(status, absl::OkStatus());
auto error = status.message();
ASSERT_EQ(error, "max_length should be greater than 0");
}
10 changes: 7 additions & 3 deletions src/tokenize/tokenize_parser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,13 +81,17 @@ std::variant<TokenizeRequest, std::string> TokenizeParser::validateTokenizeReque

auto it = parsedJson.FindMember("max_length");
if (it != parsedJson.MemberEnd()) {
if (it->value.IsInt()) {
size_t max_length = it->value.GetInt();
if (it->value.IsUint()) {

@dtrawins dtrawins Jun 25, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is zero allowed?

@przepeck przepeck Jun 26, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, I will add additional condition for 0

size_t max_length = it->value.GetUint();
if (max_length == 0) {
return "max_length should be greater than 0";
}

request.parameters["max_length"] = max_length;
// Keep OVMS tokenize API contract: max_length implies truncation.
request.parameters["truncation"] = true;
Comment on lines +84 to 92
} else {
return "max_length should be integer";
return "max_length should be unsigned integer";
}
}
it = parsedJson.FindMember("pad_to_max_length");
Expand Down