llama.cpp/examples/server/utils.hpp

#pragma once

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

#ifndef NDEBUG
// crash the server in debug mode, otherwise send an http 500 error
#define CPPHTTPLIB_NO_EXCEPTIONS 1
#endif
// increase max payload length to allow use of larger context size
#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
#include "httplib.h"

// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
#include "json.hpp"

#include <random>
#include <sstream>
#include <string>
#include <vector>
#include <memory>

#define DEFAULT_OAICOMPAT_MODEL "gpt-3.5-turbo-0613"

using json = nlohmann::ordered_json;

#define SLT_INF(slot, fmt, ...) LOG_INF("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
#define SLT_WRN(slot, fmt, ...) LOG_WRN("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
#define SLT_ERR(slot, fmt, ...) LOG_ERR("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
#define SLT_DBG(slot, fmt, ...) LOG_DBG("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)

#define SRV_INF(fmt, ...) LOG_INF("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define SRV_WRN(fmt, ...) LOG_WRN("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define SRV_ERR(fmt, ...) LOG_ERR("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define SRV_DBG(fmt, ...) LOG_DBG("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)

#define QUE_INF(fmt, ...) LOG_INF("que  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_WRN(fmt, ...) LOG_WRN("que  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_ERR(fmt, ...) LOG_ERR("que  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_DBG(fmt, ...) LOG_DBG("que  %12.*s: " fmt, 12, __func__, __VA_ARGS__)

template <typename T>
static T json_value(const json & body, const std::string & key, const T & default_value) {
    // Fallback null to default value
    if (body.contains(key) && !body.at(key).is_null()) {
        try {
            return body.at(key);
        } catch (NLOHMANN_JSON_NAMESPACE::detail::type_error const &) {
            LOG_WRN("Wrong type supplied for parameter '%s'. Expected '%s', using default value\n", key.c_str(), json(default_value).type_name());
            return default_value;
        }
    } else {
        return default_value;
    }
}

//
// tokenizer and input processing utils
//

static bool json_is_array_of_numbers(const json & data) {
    if (data.is_array()) {
        for (const auto & e : data) {
            if (!e.is_number_integer()) {
                return false;
            }
        }
        return true;
    }
    return false;
}

// is array having BOTH numbers & strings?
static bool json_is_array_of_mixed_numbers_strings(const json & data) {
    bool seen_string = false;
    bool seen_number = false;
    if (data.is_array()) {
        for (const auto & e : data) {
            seen_string |= e.is_string();
            seen_number |= e.is_number_integer();
            if (seen_number && seen_string) {
                return true;
            }
        }
    }
    return false;
}

/**
 * this handles 2 cases:
 * - only string, example: "string"
 * - mixed string and tokens, example: [12, 34, "string", 56, 78]
 */
static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {
    // If `add_bos` is true, we only add BOS, when json_prompt is a string,
    // or the first element of the json_prompt array is a string.
    llama_tokens prompt_tokens;

    if (json_prompt.is_array()) {
        bool first = true;
        for (const auto & p : json_prompt) {
            if (p.is_string()) {
                auto s = p.template get<std::string>();

                llama_tokens p;
                if (first) {
                    p = common_tokenize(ctx, s, add_special, parse_special);
                    first = false;
                } else {
                    p = common_tokenize(ctx, s, false, parse_special);
                }

                prompt_tokens.insert(prompt_tokens.end(), p.begin(), p.end());
            } else {
                if (first) {
                    first = false;
                }

                prompt_tokens.push_back(p.template get<llama_token>());
            }
        }
    } else {
        auto s = json_prompt.template get<std::string>();
        prompt_tokens = common_tokenize(ctx, s, add_special, parse_special);
    }

    return prompt_tokens;
}

/**
 * break the input "prompt" object into multiple prompt if needed, then tokenize them
 * this supports these cases:
 * - "prompt": "string"
 * - "prompt": [12, 34, 56]
 * - "prompt": [12, 34, "string", 56, 78]
 * and multiple prompts (multi-tasks):
 * - "prompt": ["string1", "string2"]
 * - "prompt": ["string1", [12, 34, 56]]
 * - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]]
 */
static std::vector<llama_tokens> tokenize_input_prompts(llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {
    std::vector<llama_tokens> result;
    if (json_prompt.is_string() || json_is_array_of_mixed_numbers_strings(json_prompt)) {
        // string or mixed
        result.push_back(tokenize_mixed(ctx, json_prompt, add_special, parse_special));
    } else if (json_is_array_of_numbers(json_prompt)) {
        // array of tokens
        result.push_back(json_prompt.get<llama_tokens>());
    } else if (json_prompt.is_array()) {
        // array of prompts
        result.reserve(json_prompt.size());
        for (const auto & p : json_prompt) {
            if (p.is_string() || json_is_array_of_mixed_numbers_strings(p)) {
                result.push_back(tokenize_mixed(ctx, p, add_special, parse_special));
            } else if (json_is_array_of_numbers(p)) {
                // array of tokens
                result.push_back(p.get<llama_tokens>());
            } else {
                throw std::runtime_error("element of \"prompt\" must be a string, an list of tokens, or a list of mixed strings & tokens");
            }
        }
    } else {
        throw std::runtime_error("\"prompt\" must be a string, an list of tokens, a list of mixed strings & tokens, or a list of prompts");
    }
    if (result.empty()) {
        throw std::runtime_error("\"prompt\" must not be empty");
    }
    return result;
}

//
// template utils
//

// format rerank task: [BOS]query[EOS][SEP]doc[EOS]
static llama_tokens format_rerank(const struct llama_model * model, const llama_tokens & query, const llama_tokens & doc) {
    llama_tokens result;
    result.reserve(doc.size() + query.size() + 4);
    result.push_back(llama_token_bos(model));
    result.insert(result.end(), query.begin(), query.end());
    result.push_back(llama_token_eos(model));
    result.push_back(llama_token_sep(model));
    result.insert(result.end(), doc.begin(), doc.end());
    result.push_back(llama_token_eos(model));
    return result;
}

// format infill task
static llama_tokens format_infill(
        const llama_context * ctx,
        const json & input_prefix,
        const json & input_suffix,
        const json & input_extra,
        const int n_batch,
        const int n_predict,
        const int n_ctx,
        const bool spm_infill,
        const llama_tokens & tokens_prompt
    ) {
    // TODO: optimize this block by reducing memory allocations and movement

    // use FIM repo-level pattern:
    // ref: https://arxiv.org/pdf/2409.12186
    //
    // [FIM_REP]myproject
    // [FIM_SEP]filename0
    // extra chunk 0
    // [FIM_SEP]filename1
    // extra chunk 1
    // ...
    // [FIM_SEP]filename
    // [FIM_PRE]prefix[FIM_SUF]suffix[FIM_MID]prompt
    //
    llama_tokens extra_tokens;
    extra_tokens.reserve(n_ctx);

    auto model = llama_get_model(ctx);
    auto tokens_prefix = tokenize_mixed(ctx, input_prefix, false, false);
    auto tokens_suffix = tokenize_mixed(ctx, input_suffix, false, false);

    if (llama_token_fim_rep(model) != LLAMA_TOKEN_NULL) {
        // TODO: make project name an input
        static const auto k_fim_repo = common_tokenize(ctx, "myproject\n", false, false);

        extra_tokens.push_back(llama_token_fim_rep(model));
        extra_tokens.insert(extra_tokens.end(), k_fim_repo.begin(), k_fim_repo.end());
    }
    for (const auto & chunk : input_extra) {
        // { "text": string, "filename": string }
        const std::string text     = json_value(chunk, "text",     std::string());
        const std::string filename = json_value(chunk, "filename", std::string("tmp"));

        if (llama_token_fim_sep(model) != LLAMA_TOKEN_NULL) {
            const auto k_fim_file = common_tokenize(ctx, filename + "\n", false, false);

            extra_tokens.insert(extra_tokens.end(), llama_token_fim_sep(model));
            extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end());
        } else {
            // chunk separator in binary form to avoid confusing the AI
            static const char k_chunk_prefix_str[] = {0x0a, 0x0a, 0x2d, 0x2d, 0x2d, 0x20, 0x73, 0x6e, 0x69, 0x70, 0x70, 0x65, 0x74, 0x20, 0x2d, 0x2d, 0x2d, 0x0a, 0x0a, 0x00};
            static const auto k_chunk_prefix_tokens = common_tokenize(ctx, k_chunk_prefix_str, false, false);

            extra_tokens.insert(extra_tokens.end(), k_chunk_prefix_tokens.begin(), k_chunk_prefix_tokens.end());
        }

        const auto chunk_tokens = common_tokenize(ctx, text, false, false);
        extra_tokens.insert(extra_tokens.end(), chunk_tokens.begin(), chunk_tokens.end());
    }

    if (llama_token_fim_sep(model) != LLAMA_TOKEN_NULL) {
        // TODO: current filename
        static const auto k_fim_file = common_tokenize(ctx, "filename\n", false, false);

        extra_tokens.insert(extra_tokens.end(), llama_token_fim_sep(model));
        extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end());
    }

    // for now pick FIM context to fit in a batch (ratio prefix:suffix = 3:1, TODO: configurable?)
    const int n_prefix_take = std::min<int>(tokens_prefix.size(),                3*(n_batch/4));
    const int n_suffix_take = std::min<int>(tokens_suffix.size(), std::max<int>(0, (n_batch/4) - (2 + tokens_prompt.size())));

    SRV_DBG("n_prefix_take = %d, n_suffix_take = %d, total = %d\n", n_prefix_take, n_suffix_take, (n_prefix_take + n_suffix_take));

    // fill the rest of the context with extra chunks
    const int n_extra_take = std::min<int>(std::max<int>(0, n_ctx - (n_batch) - 2*n_predict), extra_tokens.size());

    tokens_prefix.erase(tokens_prefix.begin(), tokens_prefix.begin() + tokens_prefix.size() - n_prefix_take);
    tokens_suffix.resize(n_suffix_take);

    tokens_prefix.insert(tokens_prefix.begin(), llama_token_fim_pre(model));
    tokens_prefix.insert(tokens_prefix.end(),   tokens_prompt.begin(), tokens_prompt.end());
    tokens_suffix.insert(tokens_suffix.begin(), llama_token_fim_suf(model));

    auto embd_inp = spm_infill ? tokens_suffix : tokens_prefix;
    auto embd_end = spm_infill ? tokens_prefix : tokens_suffix;

    if (llama_add_bos_token(model)) {
        embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
    }

    SRV_DBG("extra: n_ctx = %d, n_extra_take = %d, n_extra = %d\n", n_ctx, n_extra_take, (int) extra_tokens.size());

    // put the extra context before the FIM prefix
    embd_inp.insert(embd_inp.begin(), extra_tokens.end() - n_extra_take, extra_tokens.end());

    embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
    embd_inp.push_back(llama_token_fim_mid(model));

    return embd_inp;
}

// Format given chat. If tmpl is empty, we take the template from model metadata
inline std::string format_chat(const struct llama_model * model, const std::string & tmpl, const std::vector<json> & messages) {
    std::vector<common_chat_msg> chat;

    for (size_t i = 0; i < messages.size(); ++i) {
        const auto & curr_msg = messages[i];

        std::string role = json_value(curr_msg, "role", std::string(""));

        std::string content;
        if (curr_msg.contains("content")) {
            if (curr_msg["content"].is_string()) {
                content = curr_msg["content"].get<std::string>();
            } else if (curr_msg["content"].is_array()) {
                for (const auto & part : curr_msg["content"]) {
                    if (part.contains("text")) {
                        content += "\n" + part["text"].get<std::string>();
                    }
                }
            } else {
                throw std::runtime_error("Invalid 'content' type (ref: https://github.com/ggerganov/llama.cpp/issues/8367)");
            }
        } else {
            throw std::runtime_error("Missing 'content' (ref: https://github.com/ggerganov/llama.cpp/issues/8367)");
        }

        chat.push_back({role, content});
    }

    const auto formatted_chat = common_chat_apply_template(model, tmpl, chat, true);
    LOG_DBG("formatted_chat: '%s'\n", formatted_chat.c_str());

    return formatted_chat;
}

static std::string llama_get_chat_template(const struct llama_model * model) {
    std::string template_key = "tokenizer.chat_template";
    // call with NULL buffer to get the total size of the string
    int32_t res = llama_model_meta_val_str(model, template_key.c_str(), NULL, 0);
    if (res < 2) {
        return "";
    } else {
        std::vector<char> model_template(res, 0);
        llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), model_template.size());
        return std::string(model_template.data(), model_template.size() - 1);
    }
}

//
// base64 utils (TODO: move to common in the future)
//

static const std::string base64_chars =
             "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
             "abcdefghijklmnopqrstuvwxyz"
             "0123456789+/";

static inline bool is_base64(uint8_t c) {
    return (isalnum(c) || (c == '+') || (c == '/'));
}

static inline std::vector<uint8_t> base64_decode(const std::string & encoded_string) {
    int i = 0;
    int j = 0;
    int in_ = 0;

    int in_len = encoded_string.size();

    uint8_t char_array_4[4];
    uint8_t char_array_3[3];

    std::vector<uint8_t> ret;

    while (in_len-- && (encoded_string[in_] != '=') && is_base64(encoded_string[in_])) {
        char_array_4[i++] = encoded_string[in_]; in_++;
        if (i == 4) {
            for (i = 0; i < 4; i++) {
                char_array_4[i] = base64_chars.find(char_array_4[i]);
            }

            char_array_3[0] = ((char_array_4[0]      ) << 2) + ((char_array_4[1] & 0x30) >> 4);
            char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
            char_array_3[2] = ((char_array_4[2] & 0x3) << 6) +   char_array_4[3];

            for (i = 0; (i < 3); i++) {
                ret.push_back(char_array_3[i]);
            }

            i = 0;
        }
    }

    if (i) {
        for (j = i; j < 4; j++) {
            char_array_4[j] = 0;
        }

        for (j = 0; j < 4; j++) {
            char_array_4[j] = base64_chars.find(char_array_4[j]);
        }

        char_array_3[0] = ((char_array_4[0]      ) << 2) + ((char_array_4[1] & 0x30) >> 4);
        char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
        char_array_3[2] = ((char_array_4[2] & 0x3) << 6) +   char_array_4[3];

        for (j = 0; j < i - 1; j++) {
            ret.push_back(char_array_3[j]);
        }
    }

    return ret;
}

//
// random string / id
//

static std::string random_string() {
    static const std::string str("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

    std::random_device rd;
    std::mt19937 generator(rd());

    std::string result(32, ' ');

    for (int i = 0; i < 32; ++i) {
        result[i] = str[generator() % str.size()];
    }

    return result;
}

static std::string gen_chatcmplid() {
    return "chatcmpl-" + random_string();
}

//
// other common utils
//

static bool ends_with(const std::string & str, const std::string & suffix) {
    return str.size() >= suffix.size() && 0 == str.compare(str.size() - suffix.size(), suffix.size(), suffix);
}

static size_t find_partial_stop_string(const std::string &stop, const std::string &text) {
    if (!text.empty() && !stop.empty()) {
        const char text_last_char = text.back();
        for (int64_t char_index = stop.size() - 1; char_index >= 0; char_index--) {
            if (stop[char_index] == text_last_char) {
                const std::string current_partial = stop.substr(0, char_index + 1);
                if (ends_with(text, current_partial)) {
                    return text.size() - char_index - 1;
                }
            }
        }
    }

    return std::string::npos;
}

// TODO: reuse llama_detokenize
template <class Iter>
static std::string tokens_to_str(llama_context * ctx, Iter begin, Iter end) {
    std::string ret;
    for (; begin != end; ++begin) {
        ret += common_token_to_piece(ctx, *begin);
    }

    return ret;
}

// format incomplete utf-8 multibyte character for output
static std::string tokens_to_output_formatted_string(const llama_context * ctx, const llama_token token) {
    std::string out = token == -1 ? "" : common_token_to_piece(ctx, token);

    // if the size is 1 and first bit is 1, meaning it's a partial character
    //   (size > 1 meaning it's already a known token)
    if (out.size() == 1 && (out[0] & 0x80) == 0x80) {
        std::stringstream ss;
        ss << std::hex << (out[0] & 0xff);
        std::string res(ss.str());
        out = "byte: \\x" + res;
    }

    return out;
}

static bool server_sent_event(httplib::DataSink & sink, const char * event, const json & data) {
    const std::string str =
        std::string(event) + ": " +
        data.dump(-1, ' ', false, json::error_handler_t::replace) +
        "\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row).

    LOG_DBG("data stream, to_send: %s", str.c_str());

    return sink.write(str.c_str(), str.size());
}

//
// OAI utils
//

static json oaicompat_completion_params_parse(
    const struct llama_model * model,
    const json & body, /* openai api json semantics */
    const std::string & chat_template) {
    json llama_params;

    // Apply chat template to the list of messages
    llama_params["prompt"] = format_chat(model, chat_template, body.at("messages"));

    // Handle "stop" field
    if (body.contains("stop") && body.at("stop").is_string()) {
        llama_params["stop"] = json::array({body.at("stop").get<std::string>()});
    } else {
        llama_params["stop"] = json_value(body, "stop", json::array());
    }

    // Handle "response_format" field
    if (body.contains("response_format")) {
        json response_format      = json_value(body, "response_format", json::object());
        std::string response_type = json_value(response_format, "type", std::string());
        if (response_type == "json_object") {
            llama_params["json_schema"] = json_value(response_format, "schema", json::object());
        } else if (response_type == "json_schema") {
            json json_schema = json_value(response_format, "json_schema", json::object());
            llama_params["json_schema"] = json_value(json_schema, "schema", json::object());
        } else if (!response_type.empty() && response_type != "text") {
            throw std::runtime_error("response_format type must be one of \"text\" or \"json_object\", but got: " + response_type);
        }
    }

    // Handle "n" field
    int n_choices = json_value(body, "n", 1);
    if (n_choices != 1) {
        throw std::runtime_error("Only one completion choice is allowed");
    }

    // Handle "logprobs" field
    // TODO: The response format of this option is not yet OAI-compatible, but seems like no one really using it; We may need to fix it in the future
    if (json_value(body, "logprobs", false)) {
        llama_params["n_probs"] = json_value(body, "top_logprobs", 20);
    } else if (body.contains("top_logprobs") && !body.at("top_logprobs").is_null()) {
        throw std::runtime_error("top_logprobs requires logprobs to be set to true");
    }

    // Params supported by OAI but unsupported by llama.cpp
    static const std::vector<std::string> unsupported_params { "tools", "tool_choice" };
    for (const auto & param : unsupported_params) {
        if (body.contains(param)) {
            throw std::runtime_error("Unsupported param: " + param);
        }
    }

    // Copy remaining properties to llama_params
    // This allows user to use llama.cpp-specific params like "mirostat", ... via OAI endpoint.
    // See "launch_slot_with_task()" for a complete list of params supported by llama.cpp
    for (const auto & item : body.items()) {
        // Exception: if "n_predict" is present, we overwrite the value specified earlier by "max_tokens"
        if (!llama_params.contains(item.key()) || item.key() == "n_predict") {
            llama_params[item.key()] = item.value();
        }
    }

    return llama_params;
}

static json format_embeddings_response_oaicompat(const json & request, const json & embeddings) {
    json data = json::array();
    int i = 0;
    for (const auto & elem : embeddings) {
        data.push_back(json{
            {"embedding", json_value(elem, "embedding", json::array())},
            {"index",     i++},
            {"object",    "embedding"}
        });
    }

    json res = json {
        {"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))},
        {"object", "list"},
        {"usage", json { // TODO: fill
            {"prompt_tokens", 0},
            {"total_tokens", 0}
        }},
        {"data", data}
    };

    return res;
}

static json format_response_rerank(const json & request, const json & ranks) {
    json data = json::array();
    int i = 0;
    for (const auto & rank : ranks) {
        data.push_back(json{
            {"index",    i++},
            {"relevance_score", json_value(rank, "score", 0.0)},
        });
    }

    json res = json {
        {"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))},
        {"object", "list"},
        {"usage", json { // TODO: fill
            {"prompt_tokens", 0},
            {"total_tokens", 0}
        }},
        {"results", data}
    };

    return res;
}

static bool is_valid_utf8(const std::string & str) {
    const unsigned char* bytes = reinterpret_cast<const unsigned char*>(str.data());
    const unsigned char* end = bytes + str.length();

    while (bytes < end) {
        if (*bytes <= 0x7F) {
            // 1-byte sequence (0xxxxxxx)
            bytes++;
        } else if ((*bytes & 0xE0) == 0xC0) {
            // 2-byte sequence (110xxxxx 10xxxxxx)
            if (end - bytes < 2 || (bytes[1] & 0xC0) != 0x80)
                return false;
            bytes += 2;
        } else if ((*bytes & 0xF0) == 0xE0) {
            // 3-byte sequence (1110xxxx 10xxxxxx 10xxxxxx)
            if (end - bytes < 3 || (bytes[1] & 0xC0) != 0x80 || (bytes[2] & 0xC0) != 0x80)
                return false;
            bytes += 3;
        } else if ((*bytes & 0xF8) == 0xF0) {
            // 4-byte sequence (11110xxx 10xxxxxx 10xxxxxx 10xxxxxx)
            if (end - bytes < 4 || (bytes[1] & 0xC0) != 0x80 ||
                (bytes[2] & 0xC0) != 0x80 || (bytes[3] & 0xC0) != 0x80)
                return false;
            bytes += 4;
        } else {
            // Invalid UTF-8 lead byte
            return false;
        }
    }

    return true;
}

static json format_tokenizer_response(const json & tokens) {
    return json {
        {"tokens", tokens}
    };
}

static json format_detokenized_response(const std::string & content) {
    return json {
        {"content", content}
    };
}

static json format_logit_bias(const std::vector<llama_logit_bias> & logit_bias) {
    json data = json::array();
    for (const auto & lb : logit_bias) {
        data.push_back(json{
            {"bias", lb.bias},
            {"token", lb.token},
        });
    }
    return data;
}

static std::string safe_json_to_str(json data) {
    return data.dump(-1, ' ', false, json::error_handler_t::replace);
}