Method send_embedding

smallthinker/tools/server/server.cpp:2542–2583

    }

    void send_embedding(const server_slot & slot, const llama_batch & batch) {
        auto res = std::make_unique<server_task_result_embd>();
        res->id        = slot.id_task;
        res->index     = slot.index;
        res->n_tokens  = slot.n_prompt_tokens;
        res->oaicompat = slot.params.oaicompat;

        const int n_embd = llama_model_n_embd(model);

        std::vector<float> embd_res(n_embd, 0.0f);

        for (int i = 0; i < batch.n_tokens; ++i) {
            if (!batch.logits[i] || batch.seq_id[i][0] != slot.id) {
                continue;
            }

            const float * embd = llama_get_embeddings_seq(ctx, batch.seq_id[i][0]);
            if (embd == NULL) {
                embd = llama_get_embeddings_ith(ctx, i);
            }

            if (embd == NULL) {
                SLT_ERR(slot, "failed to get embeddings, token = %d, seq_id = %d\n", batch.token[i], batch.seq_id[i][0]);

                res->embedding.push_back(std::vector<float>(n_embd, 0.0f));
                continue;
            }

            // normalize only when there is pooling
            // TODO: configurable
            if (llama_pooling_type(slot.ctx) != LLAMA_POOLING_TYPE_NONE) {
                common_embd_normalize(embd, embd_res.data(), n_embd, 2);
                res->embedding.push_back(embd_res);
            } else {
                res->embedding.push_back({ embd, embd + n_embd });
            }
        }

        SLT_DBG(slot, "%s", "sending embeddings\n");

        queue_results.send(std::move(res));
    }

    void send_rerank(const server_slot & slot, const llama_batch & batch) {
        auto res = std::make_unique<server_task_result_rerank>();