fix code formating

group of parameters // embedding
print usage for embedding parameters

common/common.cpp

@@ -1573,6 +1573,11 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
     options.push_back({ "bench",       "-ntg n0,n1,...",                "number of text generation tokens" });
     options.push_back({ "bench",       "-npl n0,n1,...",                "number of parallel prompts" });
 
+    options.push_back({ "embedding" });
+    options.push_back({ "embedding",   "       --embd-normalize",       "normalisation for embendings (default: %d) (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)", params.embd_normalize });
+    options.push_back({ "embedding",   "       --embd-output-format",   "empty = default, \"array\" = [[],[]...], \"json\" = openai style, \"json+\" = same \"json\" + cosine similarity matrix" });
+    options.push_back({ "embedding",   "       --embd-separator",       "separator of embendings (default \\n) for example \"<#sep#>\"" });
+
     options.push_back({ "server" });
     options.push_back({ "server",      "       --host HOST",            "ip address to listen (default: %s)", params.hostname.c_str() });
     options.push_back({ "server",      "       --port PORT",            "port to listen (default: %d)", params.port });

common/common.h

@@ -152,10 +152,6 @@ struct gpt_params {
     bool prompt_cache_all  = false; // save user input and generations to prompt cache
     bool prompt_cache_ro   = false; // open the prompt cache read-only and do not update it
 
-    bool embedding         = false; // get only sentence embedding
-    int32_t embd_normalize = 2;     // normalisation for embendings (-1=none, 0=max absolute, 1=taxicab, 2=euclidean, >2=p-norm)
-    std::string embd_out   = "";    // empty = default, "array" = [] or [[],[]...], "json" = openai style, "json+" = same "json" + cosine similarity matrix
-    std::string embd_sep   = "\n";  // separator of embendings
     bool escape            = true;  // escape "\n", "\r", "\t", "\'", "\"", and "\\"
     bool multiline_input   = false; // reverse the usage of `\`
     bool simple_io         = false; // improves compatibility with subprocesses and limited consoles
@@ -182,6 +178,12 @@ struct gpt_params {
     std::string mmproj = "";        // path to multimodal projector
     std::vector<std::string> image; // path to image file(s)
 
+    // embedding
+    bool embedding         = false; // get only sentence embedding
+    int32_t embd_normalize = 2;     // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)
+    std::string embd_out   = "";    // empty = default, "array" = [[],[]...], "json" = openai style, "json+" = same "json" + cosine similarity matrix
+    std::string embd_sep   = "\n";  // separator of embendings
+
     // server params
     int32_t port           = 8080;         // server listens on this network port
     int32_t timeout_read   = 600;          // http read timeout in seconds

examples/embedding/embedding.cpp

@@ -184,17 +184,18 @@ int main(int argc, char ** argv) {
     float * out = emb + p * n_embd;
     batch_decode(ctx, batch, out, s, n_embd, params.embd_normalize);
 
-    if (params.embd_out=="") {
+    if (params.embd_out.empty()) {
         // print the first part of the embeddings or for a single prompt, the full embedding
         fprintf(stdout, "\n");
         for (int j = 0; j < n_prompts; j++) {
             fprintf(stdout, "embedding %d: ", j);
             for (int i = 0; i < (n_prompts > 1 ? std::min(16, n_embd) : n_embd); i++) {
-                if (params.embd_normalize==0)
+                if (params.embd_normalize == 0) {
                     fprintf(stdout, "%6.0f ", emb[j * n_embd + i]);
-                else
+                } else {
                     fprintf(stdout, "%9.6f ", emb[j * n_embd + i]);
                 }
+            }
             fprintf(stdout, "\n");
         }