embedding : show full embedding for single prompt (#6342)

* embedding : show full embedding for single prompt

To support the use case of creating an embedding for a given prompt, the entire embedding and not just the first part needed to be printed.

Also, show cosine similarity matrix only if there is more than one prompt, as the cosine similarity matrix for a single prompt is always `1.00`.

* Update examples/embedding/embedding.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
howlger 2024-03-27 12:15:44 +01:00 committed by GitHub
parent e82f9e2b83
commit 1e13987fba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -178,17 +178,18 @@ int main(int argc, char ** argv) {
float * out = emb + p * n_embd;
batch_decode(ctx, batch, out, s, n_embd);
// print the first part of the embeddings
// 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 < std::min(16, n_embd); i++) {
for (int i = 0; i < (n_prompts > 1 ? std::min(16, n_embd) : n_embd); i++) {
fprintf(stdout, "%9.6f ", emb[j * n_embd + i]);
}
fprintf(stdout, "\n");
}
// print cosine similarity matrix
if (n_prompts > 1) {
fprintf(stdout, "\n");
printf("cosine similarity matrix:\n\n");
for (int i = 0; i < n_prompts; i++) {
@ -198,6 +199,7 @@ int main(int argc, char ** argv) {
}
fprintf(stdout, "\n");
}
}
// clean up
llama_print_timings(ctx);