Cortex (Inference)

The current UE plugin exposes both local node-backed cortex helpers and remote API-backed cortex helpers.

Local Cortex

Local inference is driven by Cortex/CortexThunks.h and currently loads a model from a file path.

1
#include "RuntimeStore.h"
2
#include "CLI/CliOperations.h"
3
4
auto Store = createSDKStore();
5
6
FCortexStatus Local = SDKOps::InitCortex(
7
    Store,
8
    TEXT("smollm2-135m"));
9
10
FCortexResponse Response =
11
    SDKOps::CompleteCortex(Store, TEXT("Write one short sentence."));

Important points:

• InitCortex takes a model ID (e.g. smollm2-135m) which maps to a HuggingFace GGUF URL — the SDK downloads it automatically on first use to {ProjectSavedDir}/ForbocAI/models/
• You can also pass a direct file path to a .gguf model
• Local completion uses the currently initialized llama.cpp context (Metal GPU on Mac)
• GenerateEmbedding is also available through SDKOps::GenerateEmbedding(...) — the embedding model (all-MiniLM-L6-v2) is also downloaded automatically on first use

Remote Cortex

1
#include "RuntimeStore.h"
2
#include "CLI/CliOperations.h"
3
#include "RuntimeConfig.h"
4
5
auto Store = createSDKStore();
6
SDKConfig::SetApiConfig(TEXT("https://api.forboc.ai"), ApiKey);
7
8
TArray<FCortexModelInfo> Models = SDKOps::ListCortexModels(Store);
9
FCortexStatus Remote = SDKOps::InitRemoteCortex(Store, TEXT("api-integrated"));
10
FCortexResponse RemoteResp =
11
    SDKOps::CompleteRemoteCortex(Store, Remote.Id, TEXT("Summarize this."));

Protocol Requirement

rtk::processNPC(...) with rtk::LocalProtocolRuntime() uses local cortex for ExecuteInference instructions. Remote fallback is intentionally disabled in that path.

If local cortex is not initialized and the API requests inference, processNPC(...) fails fast.

Key Types

• FCortexStatus
• FCortexConfig
• FCortexResponse
• FCortexModelInfo

FCortexConfig also supports optional stop sequences and a JSON schema payload for remote completion requests.