Method send_embedding

examples/server/server.cpp:1219–1248

    }

    void send_embedding(llama_client_slot &slot)
    {
        std::lock_guard<std::mutex> lock(mutex_results);
        task_result res;
        res.id = slot.task_id;
        res.error = false;
        res.stop = true;

        const int n_embd = llama_n_embd(model);
        if (!params.embedding)
        {
            LOG_WARNING("embedding disabled", {
                                                  {"params.embedding", params.embedding},
                                              });
            res.result_json = json
            {
                {"embedding", std::vector<float>(n_embd, 0.0f)},
            };
        }
        else
        {
            const float *data = llama_get_embeddings(ctx);
            std::vector<float> embedding(data, data + n_embd);
            res.result_json = json
            {
                {"embedding", embedding },
            };
        }
        queue_results.push_back(res);
    }

    int request_completion(json data, bool infill, bool embedding)
    {