mirror of
https://github.com/supermemoryai/supermemory.git
synced 2026-05-17 12:20:04 +00:00
75 lines
1.7 KiB
Text
75 lines
1.7 KiB
Text
---
|
|
title: "Extend Benchmark"
|
|
description: "Add a custom benchmark dataset to MemoryBench"
|
|
sidebarTitle: "Extend Benchmark"
|
|
---
|
|
|
|
## Benchmark Interface
|
|
|
|
```typescript
|
|
interface Benchmark {
|
|
name: string
|
|
load(config?: BenchmarkConfig): Promise<void>
|
|
getQuestions(filter?: QuestionFilter): UnifiedQuestion[]
|
|
getHaystackSessions(questionId: string): UnifiedSession[]
|
|
getGroundTruth(questionId: string): string
|
|
getQuestionTypes(): QuestionTypeRegistry
|
|
}
|
|
```
|
|
|
|
---
|
|
|
|
## Adding a Custom Benchmark
|
|
|
|
### 1. Create the Benchmark
|
|
|
|
```typescript
|
|
// src/benchmarks/mybenchmark/index.ts
|
|
import type { Benchmark, UnifiedQuestion, UnifiedSession } from "../../types"
|
|
|
|
export class MyBenchmark implements Benchmark {
|
|
name = "mybenchmark"
|
|
private questions: UnifiedQuestion[] = []
|
|
private sessions: Map<string, UnifiedSession[]> = new Map()
|
|
|
|
async load() {
|
|
const data = await this.loadDataset()
|
|
this.processData(data)
|
|
}
|
|
|
|
getQuestions(filter?: QuestionFilter) {
|
|
let result = [...this.questions]
|
|
if (filter?.limit) result = result.slice(0, filter.limit)
|
|
return result
|
|
}
|
|
|
|
getHaystackSessions(questionId: string) {
|
|
return this.sessions.get(questionId) || []
|
|
}
|
|
|
|
getGroundTruth(questionId: string) {
|
|
return this.questions.find(q => q.questionId === questionId)?.groundTruth || ""
|
|
}
|
|
|
|
getQuestionTypes() {
|
|
return {
|
|
"type1": { id: "type1", description: "Type 1 questions" },
|
|
"type2": { id: "type2", description: "Type 2 questions" },
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
### 2. Register the Benchmark
|
|
|
|
```typescript
|
|
// src/benchmarks/index.ts
|
|
import { MyBenchmark } from "./mybenchmark"
|
|
|
|
export const benchmarks = {
|
|
locomo: LoComoBenchmark,
|
|
longmemeval: LongMemEvalBenchmark,
|
|
convomem: ConvoMemBenchmark,
|
|
mybenchmark: MyBenchmark, // Add here
|
|
}
|
|
```
|