Sentence embeddings from C

// Sentence embeddings with the Kwker Runtime from C: load a sentence-transformers model folder (weights and tokenizer),
// embed a few texts and print how similar each one is to the first. No Python, no PyTorch.
//
//   rt_embed <model folder> <text> <text> [<text> ...]
//
// The embeddings use the folder's own pooling and normalization, as sentence-transformers does.
//
// Build: cc rt_embed.c -I<kwker include dir> -L<lib dir> -lkwker_rt -lm -o rt_embed
#include <math.h>
#include <stdio.h>
#include <stdlib.h>

#include "kwker_rt.h"

int main(int argc, char** argv) {
    if (argc < 4) {
        fprintf(stderr, "usage: %s <model folder> <text> <text> [<text> ...]\n", argv[0]);
        return 2;
    }
    const char* dir = argv[1];
    const int64_t n = argc - 2;

    kwker_rt_tokenizer* tok = NULL;
    kwker_rt_encoder* enc = NULL;
    if (kwker_rt_tokenizer_load(dir, &tok) != 0) {
        fprintf(stderr, "tokenizer: %s\n", kwker_rt_tokenizer_error());
        return 1;
    }
    if (kwker_rt_encoder_load(dir, "float32", &enc) != 0) {
        fprintf(stderr, "encoder: %s\n", kwker_rt_last_error());
        return 1;
    }
    const int64_t hidden = kwker_rt_encoder_hidden(enc);

    // Token ids for every text, with the model's start and end tokens; rows padded to the longest one.
    int64_t* lens = malloc(sizeof(int64_t) * n);
    int64_t longest = 0;
    for (int64_t i = 0; i < n; i++) {
        kwker_rt_tokenizer_encode(tok, argv[2 + i], -1, 1, NULL, 0, &lens[i]);
        if (lens[i] > longest) longest = lens[i];
    }
    int64_t* ids = calloc((size_t)(n * longest), sizeof(int64_t));
    for (int64_t i = 0; i < n; i++) kwker_rt_tokenizer_encode(tok, argv[2 + i], -1, 1, ids + i * longest, longest, &lens[i]);

    // One call embeds them all: n rows of hidden floats.
    float* emb = malloc(sizeof(float) * (size_t)(n * hidden));
    if (kwker_rt_encoder_embed(enc, n, longest, ids, lens, emb, 0) != 0) {
        fprintf(stderr, "embed: %s\n", kwker_rt_last_error());
        return 1;
    }

    // Cosine similarity of each text to the first.
    for (int64_t i = 1; i < n; i++) {
        double dot = 0, a = 0, b = 0;
        for (int64_t j = 0; j < hidden; j++) {
            dot += (double)emb[j] * emb[i * hidden + j];
            a += (double)emb[j] * emb[j];
            b += (double)emb[i * hidden + j] * emb[i * hidden + j];
        }
        printf("%.4f  %s\n", dot / sqrt(a * b), argv[2 + i]);
    }

    kwker_rt_encoder_free(enc);
    kwker_rt_tokenizer_free(tok);
    free(emb);
    free(ids);
    free(lens);
    return 0;
}

cc rt_embed.c -I<include dir> -L<library dir> -lkwker_rt -lm -Wl,-rpath,<library dir> -o rt_embed
./rt_embed ~/models/all-MiniLM-L6-v2 "How do I bake bread?" "A recipe for sourdough loaves" "The stock market fell today"

0.5845  A recipe for sourdough loaves
0.0645  The stock market fell today