ClickHouse/programs/library-bridge/CatBoostLibraryAPI.h
Robert Schulze 60f9f6855d
feat: implement catboost in library-bridge
This commit moves the catboost model evaluation out of the server
process into the library-bridge binary. This serves two goals: On the
one hand, crashes / memory corruptions of the catboost library no longer
affect the server. On the other hand, we can forbid loading dynamic
libraries in the server (catboost was the last consumer of this
functionality), thus improving security.

SQL syntax:

  SELECT
    catboostEvaluate('/path/to/model.bin', FEAT_1, ..., FEAT_N) > 0 AS prediction,
    ACTION AS target
  FROM amazon_train
  LIMIT 10

Required configuration:

  <catboost_lib_path>/path/to/libcatboostmodel.so</catboost_lib_path>

*** Implementation Details ***

The internal protocol between the server and the library-bridge is
simple:

- HTTP GET on path "/extdict_ping":
  A ping, used during the handshake to check if the library-bridge runs.

- HTTP POST on path "extdict_request"
  (1) Send a "catboost_GetTreeCount" request from the server to the
      bridge, containing a library path (e.g /home/user/libcatboost.so) and
      a model path (e.g. /home/user/model.bin). Rirst, this unloads the
      catboost library handler associated to the model path (if it was
      loaded), then loads the catboost library handler associated to the
      model path, then executes GetTreeCount() on the library handler and
      finally sends the result back to the server. Step (1) is called once
      by the server from FunctionCatBoostEvaluate::getReturnTypeImpl(). The
      library path handler is unloaded in the beginning because it contains
      state which may no longer be valid if the user runs
      catboost("/path/to/model.bin", ...) more than once and if "model.bin"
      was updated in between.
  (2) Send "catboost_Evaluate" from the server to the bridge, containing
      the model path and the features to run the interference on. Step (2)
      is called multiple times (once per chunk) by the server from function
      FunctionCatBoostEvaluate::executeImpl(). The library handler for the
      given model path is expected to be already loaded by Step (1).

Fixes 
2022-09-08 09:01:32 +00:00

50 lines
2.4 KiB
C++

#pragma once
#include <cstdint>
#include <cstddef>
// Function pointer typedefs and names of libcatboost.so functions used by ClickHouse
struct CatBoostLibraryAPI
{
using ModelCalcerHandle = void;
using ModelCalcerCreateFunc = ModelCalcerHandle * (*)();
static constexpr const char * ModelCalcerCreateName = "ModelCalcerCreate";
using ModelCalcerDeleteFunc = void (*)(ModelCalcerHandle *);
static constexpr const char * ModelCalcerDeleteName = "ModelCalcerDelete";
using GetErrorStringFunc = const char * (*)();
static constexpr const char * GetErrorStringName = "GetErrorString";
using LoadFullModelFromFileFunc = bool (*)(ModelCalcerHandle *, const char *);
static constexpr const char * LoadFullModelFromFileName = "LoadFullModelFromFile";
using CalcModelPredictionFlatFunc = bool (*)(ModelCalcerHandle *, size_t, const float **, size_t, double *, size_t);
static constexpr const char * CalcModelPredictionFlatName = "CalcModelPredictionFlat";
using CalcModelPredictionFunc = bool (*)(ModelCalcerHandle *, size_t, const float **, size_t, const char ***, size_t, double *, size_t);
static constexpr const char * CalcModelPredictionName = "CalcModelPrediction";
using CalcModelPredictionWithHashedCatFeaturesFunc = bool (*)(ModelCalcerHandle *, size_t, const float **, size_t, const int **, size_t, double *, size_t);
static constexpr const char * CalcModelPredictionWithHashedCatFeaturesName = "CalcModelPredictionWithHashedCatFeatures";
using GetStringCatFeatureHashFunc = int (*)(const char *, size_t);
static constexpr const char * GetStringCatFeatureHashName = "GetStringCatFeatureHash";
using GetIntegerCatFeatureHashFunc = int (*)(uint64_t);
static constexpr const char * GetIntegerCatFeatureHashName = "GetIntegerCatFeatureHash";
using GetFloatFeaturesCountFunc = size_t (*)(ModelCalcerHandle *);
static constexpr const char * GetFloatFeaturesCountName = "GetFloatFeaturesCount";
using GetCatFeaturesCountFunc = size_t (*)(ModelCalcerHandle *);
static constexpr const char * GetCatFeaturesCountName = "GetCatFeaturesCount";
using GetTreeCountFunc = size_t (*)(ModelCalcerHandle *);
static constexpr const char * GetTreeCountName = "GetTreeCount";
using GetDimensionsCountFunc = size_t (*)(ModelCalcerHandle *);
static constexpr const char * GetDimensionsCountName = "GetDimensionsCount";
};