llama.cpp/examples/embedding/embedding.cpp

#include "common.h"
#include "llama.h"

#include <cassert>
#include <cinttypes>
#include <cmath>
#include <cstdio>
#include <cstring>
#include <fstream>
#include <string>
#include <vector>

int main(int argc, char ** argv) {
    gpt_params params;
    params.model = "models/llama-7B/ggml-model.bin";

    if (gpt_params_parse(argc, argv, params) == false) {
        return 1;
    }

    params.embedding = true;

    if (params.n_ctx > 2048) {
        fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
                "expect poor results\n", __func__, params.n_ctx);
    }

    if (params.seed <= 0) {
        params.seed = time(NULL);
    }

    fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);

    std::mt19937 rng(params.seed);
    if (params.random_prompt) {
        params.prompt = gpt_random_prompt(rng);
    }

    llama_context * ctx;

    // load the model
    {
        auto lparams = llama_context_default_params();

        lparams.n_ctx      = params.n_ctx;
        lparams.n_parts    = params.n_parts;
        lparams.seed       = params.seed;
        lparams.f16_kv     = params.memory_f16;
        lparams.logits_all = params.perplexity;
        lparams.use_mlock  = params.use_mlock;
        lparams.embedding  = params.embedding;

        ctx = llama_init_from_file(params.model.c_str(), lparams);

        if (ctx == NULL) {
            fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
            return 1;
        }
    }

    // print system information
    {
        fprintf(stderr, "\n");
        fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
    }

    int n_past = 0;

    // Add a space in front of the first character to match OG llama tokenizer behavior
    params.prompt.insert(0, 1, ' ');

    // tokenize the prompt
    auto embd_inp = ::llama_tokenize(ctx, params.prompt, true);

    // determine newline token
    auto llama_token_newline = ::llama_tokenize(ctx, "\n", false);

    if (params.verbose_prompt) {
        fprintf(stderr, "\n");
        fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
        fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
        for (int i = 0; i < (int) embd_inp.size(); i++) {
            fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
        }
        fprintf(stderr, "\n");
    }

    if (params.embedding){
        if (embd_inp.size() > 0) {
            if (llama_eval(ctx, embd_inp.data(), embd_inp.size(), n_past, params.n_threads)) {
                fprintf(stderr, "%s : failed to eval\n", __func__);
                return 1;
            }
        }

        const auto embeddings = llama_get_embeddings(ctx);

        // TODO: print / use the embeddings
    }

    llama_print_timings(ctx);
    llama_free(ctx);

    return 0;
}