Skip to content

feat: add getters for prompt token count and total tokens count in LLMs #777

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chmjkb wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat: add getters for prompt token count and total tokens count in LLMs #777

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
abd721c
feat: add getTotalTokenCount, getPromptTokenCount
chmjkb Feb 3, 2026
8fa97f4
fix: add docs, expose method from cpp
chmjkb Feb 3, 2026
bbc536a
chore: remove console.logs
chmjkb Feb 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs/docs/03-hooks/01-natural-language-processing/useLLM.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,8 @@ For more information on loading resources, take a look at [loading models](../..
| `deleteMessage` | `(index: number) => void` | Deletes all messages starting with message on `index` position. After deletion `messageHistory` will be updated. |
| `messageHistory` | `Message[]` | History containing all messages in conversation. This field is updated after model responds to `sendMessage`. |
| `getGeneratedTokenCount` | `() => number` | Returns the number of tokens generated in the last response. |
| `getPromptTokenCount` | `() => number` | Returns the number of tokens in the prompt (input tokens) for the current session. |
| `getTotalTokenCount` | `() => number` | Returns the total number of tokens processed (sum of prompt tokens and generated tokens). |

<details>
<summary>Type definitions</summary>
Expand Down Expand Up @@ -110,6 +112,8 @@ interface LLMType {
generationConfig?: GenerationConfig;
}) => void;
getGeneratedTokenCount: () => number;
getPromptTokenCount: () => number;
getTotalTokenCount: () => number;
generate: (messages: Message[], tools?: LLMTool[]) => Promise<string>;
sendMessage: (message: string) => Promise<string>;
deleteMessage: (index: number) => void;
Expand Down
2 changes: 2 additions & 0 deletions docs/docs/04-typescript-api/01-natural-language-processing/LLMModule.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,8 @@ llm.delete();
| `delete` | `() => void` | Method to delete the model from memory. Note you cannot delete model while it's generating. You need to interrupt it first and make sure model stopped generation. |
| `interrupt` | `() => void` | Interrupts model generation. It may return one more token after interrupt. |
| `getGeneratedTokenCount` | `() => number` | Returns the number of tokens generated in the last response. |
| `getPromptTokenCount` | `() => number` | Returns the number of tokens in the prompt (input tokens) for the current session. |
| `getTotalTokenCount` | `() => number` | Returns the total number of tokens processed (sum of prompt tokens and generated tokens). |

<details>
<summary>Type definitions</summary>
Expand Down
5 changes: 5 additions & 0 deletions packages/react-native-executorch/common/rnexecutorch/host_objects/ModelHostObject.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,11 @@ template <typename Model> class ModelHostObject : public JsiHostObject {
synchronousHostFunction<&Model::getGeneratedTokenCount>,
"getGeneratedTokenCount"));

addFunctions(JSI_EXPORT_FUNCTION(
ModelHostObject<Model>,
synchronousHostFunction<&Model::getPromptTokenCount>,
"getPromptTokenCount"));

addFunctions(
JSI_EXPORT_FUNCTION(ModelHostObject<Model>,
synchronousHostFunction<&Model::setCountInterval>,
Expand Down
7 changes: 7 additions & 0 deletions packages/react-native-executorch/common/rnexecutorch/models/llm/LLM.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,13 @@ size_t LLM::getGeneratedTokenCount() const noexcept {
return runner->stats_.num_generated_tokens;
}

size_t LLM::getPromptTokenCount() const noexcept {
if (!runner || !runner->is_loaded()) {
return 0;
}
return runner->stats_.num_prompt_tokens;
}

size_t LLM::getMemoryLowerBound() const noexcept {
return memorySizeLowerBound;
}
Expand Down
1 change: 1 addition & 0 deletions packages/react-native-executorch/common/rnexecutorch/models/llm/LLM.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ class LLM : public BaseModel {
void interrupt();
void unload() noexcept;
size_t getGeneratedTokenCount() const noexcept;
size_t getPromptTokenCount() const noexcept;
size_t getMemoryLowerBound() const noexcept;
void setCountInterval(size_t countInterval);
void setTemperature(float temperature);
Expand Down
14 changes: 14 additions & 0 deletions packages/react-native-executorch/src/controllers/LLMController.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,20 @@ export class LLMController {
return this.nativeModule.getGeneratedTokenCount();
}

public getPromptTokenCount(): number {
if (!this.nativeModule) {
throw new RnExecutorchError(
RnExecutorchErrorCode.ModuleNotLoaded,
"Cannot get prompt token count for a model that's not loaded."
);
}
return this.nativeModule.getPromptTokenCount();
}

public getTotalTokenCount(): number {
return this.getGeneratedTokenCount() + this.getPromptTokenCount();
}

public async generate(
messages: Message[],
tools?: LLMTool[]
Expand Down
12 changes: 12 additions & 0 deletions packages/react-native-executorch/src/hooks/natural_language_processing/useLLM.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,6 +130,16 @@ export const useLLM = ({
[controllerInstance]
);

const getPromptTokenCount = useCallback(
() => controllerInstance.getPromptTokenCount(),
[controllerInstance]
);

const getTotalTokenCount = useCallback(
() => controllerInstance.getTotalTokenCount(),
[controllerInstance]
);

return {
messageHistory,
response,
Expand All @@ -139,6 +149,8 @@ export const useLLM = ({
downloadProgress,
error,
getGeneratedTokenCount: getGeneratedTokenCount,
getPromptTokenCount: getPromptTokenCount,
getTotalTokenCount: getTotalTokenCount,
configure: configure,
generate: generate,
sendMessage: sendMessage,
Expand Down
8 changes: 8 additions & 0 deletions packages/react-native-executorch/src/modules/natural_language_processing/LLMModule.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,14 @@ export class LLMModule {
return this.controller.getGeneratedTokenCount();
}

getPromptTokensCount() {
return this.controller.getPromptTokenCount();
}

getTotalTokensCount() {
return this.controller.getTotalTokenCount();
}

delete() {
this.controller.delete();
}
Expand Down
2 changes: 2 additions & 0 deletions packages/react-native-executorch/src/types/llm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@ export interface LLMType {
generationConfig?: GenerationConfig;
}) => void;
getGeneratedTokenCount: () => number;
getTotalTokenCount: () => number;
getPromptTokenCount: () => number;
generate: (messages: Message[], tools?: LLMTool[]) => Promise<string>;
sendMessage: (message: string) => Promise<string>;
deleteMessage: (index: number) => void;
Expand Down
Loading