Skip to content

Added files with Diversity Params #669

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
t-sanagrawal wants to merge 2 commits into
base: jegao/FixMakeFile
Choose a base branch
from
Open

Added files with Diversity Params #669

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
a8a9eef
Please enter the commit message for your changes. Lines starting
t-sanagrawal Sep 10, 2025
2ec8745
Fixed files
t-sanagrawal Sep 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
21 changes: 18 additions & 3 deletions apps/build_memory_index.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,10 +24,11 @@ namespace po = boost::program_options;

int main(int argc, char **argv)
{
std::string data_type, dist_fn, data_path, index_path_prefix, label_file, universal_label, label_type;
uint32_t num_threads, R, L, Lf, build_PQ_bytes;
std::string data_type, dist_fn, data_path, index_path_prefix, label_file, universal_label, label_type, seller_file;
uint32_t num_threads, R, L, Lf, build_PQ_bytes, num_diverse_build;
float alpha;
bool use_pq_build, use_opq;
bool diverse_index=false;

po::options_description desc{
program_options_utils::make_program_description("build_memory_index", "Build a memory-based DiskANN index.")};
Expand Down Expand Up @@ -70,6 +71,12 @@ int main(int argc, char **argv)
program_options_utils::FILTERED_LBUILD);
optional_configs.add_options()("label_type", po::value<std::string>(&label_type)->default_value("uint"),
program_options_utils::LABEL_TYPE_DESCRIPTION);
optional_configs.add_options()("seller_file", po::value<std::string>(&seller_file)->default_value(""),
program_options_utils::DIVERSITY_FILE);
optional_configs.add_options()("NumDiverse", po::value<uint32_t>(&num_diverse_build)->default_value(1),
program_options_utils::NUM_DIVERSE);



// Merge required and optional parameters
desc.add(required_configs).add(optional_configs);
Expand Down Expand Up @@ -112,6 +119,9 @@ int main(int argc, char **argv)
return -1;
}

if(seller_file != "")
diverse_index = true;

try
{
diskann::cout << "Starting index build with R: " << R << " Lbuild: " << L << " alpha: " << alpha
Expand All @@ -120,11 +130,16 @@ int main(int argc, char **argv)
size_t data_num, data_dim;
diskann::get_bin_metadata(data_path, data_num, data_dim);

std::cout<<"Num diverse build: " << num_diverse_build << std::endl;

auto index_build_params = diskann::IndexWriteParametersBuilder(L, R)
.with_filter_list_size(Lf)
.with_alpha(alpha)
.with_saturate_graph(false)
.with_num_threads(num_threads)
.with_diverse_index(diverse_index)
.with_seller_file(seller_file)
.with_num_diverse_build(num_diverse_build)
.build();

auto filter_params = diskann::IndexFilterParamsBuilder()
Expand Down Expand Up @@ -161,4 +176,4 @@ int main(int argc, char **argv)
diskann::cerr << "Index build failed." << std::endl;
return -1;
}
}
}
3 changes: 2 additions & 1 deletion apps/build_stitched_index.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -343,8 +343,9 @@ int main(int argc, char **argv)

path labels_file_to_use = final_index_path_prefix + "_label_formatted.txt";
path labels_map_file = final_index_path_prefix + "_labels_map.txt";
uint32_t universal_label_id = 0;

convert_labels_string_to_int(label_data_path, labels_file_to_use, labels_map_file, universal_label);
convert_labels_string_to_int(label_data_path, labels_file_to_use, labels_map_file, universal_label, universal_label_id);

// 2. parse label file and create necessary data structures
std::vector<label_set> point_ids_to_labels;
Expand Down
Loading