@tangle-network/agent-knowledge 5.0.4 → 6.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +17 -0
- package/README.md +2 -2
- package/dist/benchmarks/index.d.ts +2 -53
- package/dist/benchmarks/index.js +2 -49
- package/dist/benchmarks-CmW6iORW.js +2718 -0
- package/dist/benchmarks-CmW6iORW.js.map +1 -0
- package/dist/cli.d.ts +1 -1
- package/dist/cli.js +180 -274
- package/dist/cli.js.map +1 -1
- package/dist/ids-DRqPZ42_.js +15 -0
- package/dist/ids-DRqPZ42_.js.map +1 -0
- package/dist/index-CGBctbit.d.ts +857 -0
- package/dist/index-CGBctbit.d.ts.map +1 -0
- package/dist/index-CIW3G4s_.d.ts +680 -0
- package/dist/index-CIW3G4s_.d.ts.map +1 -0
- package/dist/index.d.ts +1671 -1876
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +5836 -6530
- package/dist/index.js.map +1 -1
- package/dist/inspect-D5iarJc2.js +1864 -0
- package/dist/inspect-D5iarJc2.js.map +1 -0
- package/dist/memory/index.d.ts +3 -8
- package/dist/memory/index.js +3 -81
- package/dist/memory-C6KPRhoU.js +4494 -0
- package/dist/memory-C6KPRhoU.js.map +1 -0
- package/dist/search-CP0QtBJZ.js +113 -0
- package/dist/search-CP0QtBJZ.js.map +1 -0
- package/dist/sources/index.d.ts +212 -205
- package/dist/sources/index.d.ts.map +1 -0
- package/dist/sources/index.js +614 -33
- package/dist/sources/index.js.map +1 -1
- package/dist/types-DcCCzreS.d.ts +175 -0
- package/dist/types-DcCCzreS.d.ts.map +1 -0
- package/dist/viz/index.d.ts +23 -22
- package/dist/viz/index.d.ts.map +1 -0
- package/dist/viz/index.js +134 -10
- package/dist/viz/index.js.map +1 -1
- package/docs/results/investment-thesis.md +1 -1
- package/docs/results/research-driving.md +1 -1
- package/docs/{two-agent-research-ab.md → verified-research-ab.md} +2 -2
- package/package.json +22 -11
- package/dist/benchmarks/index.js.map +0 -1
- package/dist/chunk-4PNXQ2NT.js +0 -147
- package/dist/chunk-4PNXQ2NT.js.map +0 -1
- package/dist/chunk-AKYJG2MR.js +0 -2183
- package/dist/chunk-AKYJG2MR.js.map +0 -1
- package/dist/chunk-DQ3PDMDP.js +0 -115
- package/dist/chunk-DQ3PDMDP.js.map +0 -1
- package/dist/chunk-EYIA5PLQ.js +0 -3153
- package/dist/chunk-EYIA5PLQ.js.map +0 -1
- package/dist/chunk-LMR53POQ.js +0 -5437
- package/dist/chunk-LMR53POQ.js.map +0 -1
- package/dist/chunk-MYFM6LKH.js +0 -551
- package/dist/chunk-MYFM6LKH.js.map +0 -1
- package/dist/chunk-YMKHCTS2.js +0 -19
- package/dist/chunk-YMKHCTS2.js.map +0 -1
- package/dist/index-Cf7txrYP.d.ts +0 -790
- package/dist/memory/index.js.map +0 -1
- package/dist/types-6x0OpfW6.d.ts +0 -173
- package/dist/types-BY-xLVw-.d.ts +0 -622
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,22 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 6.1.0
|
|
4
|
+
|
|
5
|
+
### Changed
|
|
6
|
+
|
|
7
|
+
- Updated `@tangle-network/agent-eval` to `0.130.1`, `@tangle-network/agent-interface` to `0.35.0`, Mem0 to `3.1.2`, and the maintained build toolchain.
|
|
8
|
+
- Replaced tsup with tsdown so declaration builds support TypeScript 7.
|
|
9
|
+
- Added package export validation with publint and Are the Types Wrong to every release.
|
|
10
|
+
- Split Mem0 hosted and OSS client contracts, compile them against Mem0 3.1.2, and exercise the OSS SQLite lifecycle locally.
|
|
11
|
+
- Updated GitHub Actions to their current stable releases.
|
|
12
|
+
|
|
13
|
+
## 6.0.0
|
|
14
|
+
|
|
15
|
+
### Breaking Changes
|
|
16
|
+
|
|
17
|
+
- Renamed the verified research entry point to `runVerifiedResearchLoop` and removed the old two-agent function, option, result, round, and module names.
|
|
18
|
+
- Updated `@tangle-network/agent-eval` to `0.129.0` and `@tangle-network/agent-interface` to `0.34.0`.
|
|
19
|
+
|
|
3
20
|
## 5.0.4
|
|
4
21
|
|
|
5
22
|
### Changed
|
package/README.md
CHANGED
|
@@ -9,7 +9,7 @@ Supply application callbacks for those decisions, or use `@tangle-network/agent-
|
|
|
9
9
|
## Install
|
|
10
10
|
|
|
11
11
|
```bash
|
|
12
|
-
pnpm add @tangle-network/agent-knowledge @tangle-network/agent-eval@0.
|
|
12
|
+
pnpm add @tangle-network/agent-knowledge @tangle-network/agent-eval@0.130.1
|
|
13
13
|
```
|
|
14
14
|
|
|
15
15
|
Requires Node.js 20.19 or later.
|
|
@@ -270,7 +270,7 @@ Those choices stay in the application or in `@tangle-network/agent-runtime`.
|
|
|
270
270
|
## More detail
|
|
271
271
|
|
|
272
272
|
- [Architecture and data model](docs/architecture.md)
|
|
273
|
-
- [
|
|
273
|
+
- [Verified research comparison](docs/verified-research-ab.md)
|
|
274
274
|
- [Changelog](CHANGELOG.md)
|
|
275
275
|
|
|
276
276
|
## License
|
|
@@ -1,53 +1,2 @@
|
|
|
1
|
-
import {
|
|
2
|
-
export {
|
|
3
|
-
import { CampaignResult, JudgeConfig } from '@tangle-network/agent-eval/campaign';
|
|
4
|
-
import '../types-6x0OpfW6.js';
|
|
5
|
-
import '@tangle-network/agent-interface';
|
|
6
|
-
|
|
7
|
-
declare function createNoopMemoryBenchmarkAdapter(id?: string): AgentMemoryAdapter;
|
|
8
|
-
declare function createInMemoryBenchmarkAdapter(options?: {
|
|
9
|
-
id?: string;
|
|
10
|
-
}): AgentMemoryAdapter;
|
|
11
|
-
|
|
12
|
-
declare const INDUSTRY_RAG_BENCHMARKS: readonly (KnowledgeBenchmarkSpec & {
|
|
13
|
-
taskKind: 'retrieval' | KnowledgeAnswerBenchmarkTaskKind;
|
|
14
|
-
})[];
|
|
15
|
-
declare const INDUSTRY_MEMORY_BENCHMARKS: readonly (KnowledgeBenchmarkSpec & {
|
|
16
|
-
taskKind: KnowledgeMemoryBenchmarkTaskKind;
|
|
17
|
-
})[];
|
|
18
|
-
declare function buildIndustryRagBenchmarkSmokeCases(specs?: readonly (KnowledgeBenchmarkSpec & {
|
|
19
|
-
taskKind: 'retrieval' | KnowledgeAnswerBenchmarkTaskKind;
|
|
20
|
-
})[]): KnowledgeBenchmarkCase[];
|
|
21
|
-
declare function respondToIndustryRagBenchmarkSmokeCase(input: {
|
|
22
|
-
case: KnowledgeBenchmarkCase;
|
|
23
|
-
}): KnowledgeBenchmarkArtifact;
|
|
24
|
-
declare function buildIndustryMemoryBenchmarkSmokeCases(specs?: readonly (KnowledgeBenchmarkSpec & {
|
|
25
|
-
taskKind: KnowledgeMemoryBenchmarkTaskKind;
|
|
26
|
-
})[]): KnowledgeMemoryBenchmarkCase[];
|
|
27
|
-
declare function respondToIndustryMemoryBenchmarkSmokeCase(input: {
|
|
28
|
-
case: KnowledgeMemoryBenchmarkCase;
|
|
29
|
-
}): KnowledgeBenchmarkArtifact;
|
|
30
|
-
declare function buildFirstPartyMemoryLifecycleBenchmarkCases(): KnowledgeMemoryBenchmarkCase[];
|
|
31
|
-
|
|
32
|
-
declare function runMemoryAdapterBenchmark(options: RunMemoryAdapterBenchmarkOptions): Promise<RunMemoryAdapterBenchmarkResult>;
|
|
33
|
-
|
|
34
|
-
declare function summarizeKnowledgeBenchmarkCampaign<TArtifact>(input: {
|
|
35
|
-
scenarios: readonly KnowledgeBenchmarkScenario[];
|
|
36
|
-
campaign: CampaignResult<TArtifact, KnowledgeBenchmarkScenario>;
|
|
37
|
-
}): KnowledgeBenchmarkReport;
|
|
38
|
-
|
|
39
|
-
declare function parseKnowledgeBenchmarkJsonl<T = unknown>(text: string): T[];
|
|
40
|
-
declare function parseKnowledgeBenchmarkQrels(text: string): KnowledgeRetrievalBenchmarkQrel[];
|
|
41
|
-
declare function buildRetrievalBenchmarkCasesFromQrels(options: BuildRetrievalBenchmarkCasesFromQrelsOptions): KnowledgeRetrievalBenchmarkCase[];
|
|
42
|
-
|
|
43
|
-
declare function scoreKnowledgeBenchmarkArtifact<TArtifact>(testCase: KnowledgeBenchmarkCase, artifact: TArtifact): KnowledgeBenchmarkEvaluation;
|
|
44
|
-
declare function scoreMemoryBenchmarkArtifact<TArtifact>(testCase: KnowledgeMemoryBenchmarkCase, artifact: TArtifact): KnowledgeBenchmarkEvaluation;
|
|
45
|
-
|
|
46
|
-
declare function runKnowledgeBenchmarkSuite<TArtifact = KnowledgeBenchmarkArtifact>(options: RunKnowledgeBenchmarkSuiteOptions<TArtifact>): Promise<RunKnowledgeBenchmarkSuiteResult<TArtifact>>;
|
|
47
|
-
declare function renderKnowledgeBenchmarkReportMarkdown(report: KnowledgeBenchmarkReport): string;
|
|
48
|
-
declare function buildKnowledgeBenchmarkScenarios(cases: readonly KnowledgeBenchmarkCase[], splits?: readonly KnowledgeBenchmarkSplit[]): KnowledgeBenchmarkScenario[];
|
|
49
|
-
declare function knowledgeBenchmarkJudge<TArtifact = KnowledgeBenchmarkArtifact>(): JudgeConfig<TArtifact, KnowledgeBenchmarkScenario>;
|
|
50
|
-
|
|
51
|
-
declare function isKnowledgeMemoryBenchmarkCase(testCase: KnowledgeBenchmarkCase): testCase is KnowledgeMemoryBenchmarkCase;
|
|
52
|
-
|
|
53
|
-
export { BuildRetrievalBenchmarkCasesFromQrelsOptions, INDUSTRY_MEMORY_BENCHMARKS, INDUSTRY_RAG_BENCHMARKS, KnowledgeAnswerBenchmarkTaskKind, KnowledgeBenchmarkArtifact, KnowledgeBenchmarkCase, KnowledgeBenchmarkEvaluation, KnowledgeBenchmarkReport, KnowledgeBenchmarkScenario, KnowledgeBenchmarkSpec, KnowledgeBenchmarkSplit, KnowledgeMemoryBenchmarkCase, KnowledgeMemoryBenchmarkTaskKind, KnowledgeRetrievalBenchmarkCase, KnowledgeRetrievalBenchmarkQrel, RunKnowledgeBenchmarkSuiteOptions, RunKnowledgeBenchmarkSuiteResult, RunMemoryAdapterBenchmarkOptions, RunMemoryAdapterBenchmarkResult, buildFirstPartyMemoryLifecycleBenchmarkCases, buildIndustryMemoryBenchmarkSmokeCases, buildIndustryRagBenchmarkSmokeCases, buildKnowledgeBenchmarkScenarios, buildRetrievalBenchmarkCasesFromQrels, createInMemoryBenchmarkAdapter, createNoopMemoryBenchmarkAdapter, isKnowledgeMemoryBenchmarkCase, knowledgeBenchmarkJudge, parseKnowledgeBenchmarkJsonl, parseKnowledgeBenchmarkQrels, renderKnowledgeBenchmarkReportMarkdown, respondToIndustryMemoryBenchmarkSmokeCase, respondToIndustryRagBenchmarkSmokeCase, runKnowledgeBenchmarkSuite, runMemoryAdapterBenchmark, scoreKnowledgeBenchmarkArtifact, scoreMemoryBenchmarkArtifact, summarizeKnowledgeBenchmarkCampaign };
|
|
1
|
+
import { A as KnowledgeBenchmarkResponder, B as KnowledgeMemoryEvent, C as KnowledgeBenchmarkArtifact, Ct as createInMemoryBenchmarkAdapter, D as KnowledgeBenchmarkEvaluation, E as KnowledgeBenchmarkDistribution, F as KnowledgeBenchmarkSplit, G as MemoryAdapterBenchmarkCandidate, H as KnowledgeRetrievalBenchmarkCase, I as KnowledgeBenchmarkTaskKind, J as RunKnowledgeBenchmarkSuiteResult, K as MemoryAdapterBenchmarkRankingRow, L as KnowledgeClaimMatcher, M as KnowledgeBenchmarkSliceSummary, N as KnowledgeBenchmarkSource, O as KnowledgeBenchmarkFamily, P as KnowledgeBenchmarkSpec, R as KnowledgeMemoryBenchmarkCase, S as KnowledgeAnswerBenchmarkTaskKind, T as KnowledgeBenchmarkCaseBase, U as KnowledgeRetrievalBenchmarkQrel, V as KnowledgeMemoryFactMatcher, W as KnowledgeRetrievalBenchmarkQuery, X as RunMemoryAdapterBenchmarkResult, Y as RunMemoryAdapterBenchmarkOptions, _ as buildIndustryRagBenchmarkSmokeCases, a as runKnowledgeBenchmarkSuite, b as BuildRetrievalBenchmarkCasesFromQrelsOptions, c as buildRetrievalBenchmarkCasesFromQrels, d as summarizeKnowledgeBenchmarkCampaign, f as runMemoryAdapterBenchmark, g as buildIndustryMemoryBenchmarkSmokeCases, h as buildFirstPartyMemoryLifecycleBenchmarkCases, i as renderKnowledgeBenchmarkReportMarkdown, j as KnowledgeBenchmarkScenario, k as KnowledgeBenchmarkReport, l as parseKnowledgeBenchmarkJsonl, m as INDUSTRY_RAG_BENCHMARKS, n as buildKnowledgeBenchmarkScenarios, o as scoreKnowledgeBenchmarkArtifact, p as INDUSTRY_MEMORY_BENCHMARKS, q as RunKnowledgeBenchmarkSuiteOptions, r as knowledgeBenchmarkJudge, s as scoreMemoryBenchmarkArtifact, t as isKnowledgeMemoryBenchmarkCase, u as parseKnowledgeBenchmarkQrels, v as respondToIndustryMemoryBenchmarkSmokeCase, w as KnowledgeBenchmarkCase, wt as createNoopMemoryBenchmarkAdapter, x as KnowledgeAnswerBenchmarkCase, y as respondToIndustryRagBenchmarkSmokeCase, z as KnowledgeMemoryBenchmarkTaskKind } from "../index-CIW3G4s_.js";
|
|
2
|
+
export { type BuildRetrievalBenchmarkCasesFromQrelsOptions, INDUSTRY_MEMORY_BENCHMARKS, INDUSTRY_RAG_BENCHMARKS, type KnowledgeAnswerBenchmarkCase, type KnowledgeAnswerBenchmarkTaskKind, type KnowledgeBenchmarkArtifact, type KnowledgeBenchmarkCase, type KnowledgeBenchmarkCaseBase, type KnowledgeBenchmarkDistribution, type KnowledgeBenchmarkEvaluation, type KnowledgeBenchmarkFamily, type KnowledgeBenchmarkReport, type KnowledgeBenchmarkResponder, type KnowledgeBenchmarkScenario, type KnowledgeBenchmarkSliceSummary, type KnowledgeBenchmarkSource, type KnowledgeBenchmarkSpec, type KnowledgeBenchmarkSplit, type KnowledgeBenchmarkTaskKind, type KnowledgeClaimMatcher, type KnowledgeMemoryBenchmarkCase, type KnowledgeMemoryBenchmarkTaskKind, type KnowledgeMemoryEvent, type KnowledgeMemoryFactMatcher, type KnowledgeRetrievalBenchmarkCase, type KnowledgeRetrievalBenchmarkQrel, type KnowledgeRetrievalBenchmarkQuery, type MemoryAdapterBenchmarkCandidate, type MemoryAdapterBenchmarkRankingRow, type RunKnowledgeBenchmarkSuiteOptions, type RunKnowledgeBenchmarkSuiteResult, type RunMemoryAdapterBenchmarkOptions, type RunMemoryAdapterBenchmarkResult, buildFirstPartyMemoryLifecycleBenchmarkCases, buildIndustryMemoryBenchmarkSmokeCases, buildIndustryRagBenchmarkSmokeCases, buildKnowledgeBenchmarkScenarios, buildRetrievalBenchmarkCasesFromQrels, createInMemoryBenchmarkAdapter, createNoopMemoryBenchmarkAdapter, isKnowledgeMemoryBenchmarkCase, knowledgeBenchmarkJudge, parseKnowledgeBenchmarkJsonl, parseKnowledgeBenchmarkQrels, renderKnowledgeBenchmarkReportMarkdown, respondToIndustryMemoryBenchmarkSmokeCase, respondToIndustryRagBenchmarkSmokeCase, runKnowledgeBenchmarkSuite, runMemoryAdapterBenchmark, scoreKnowledgeBenchmarkArtifact, scoreMemoryBenchmarkArtifact, summarizeKnowledgeBenchmarkCampaign };
|
package/dist/benchmarks/index.js
CHANGED
|
@@ -1,49 +1,2 @@
|
|
|
1
|
-
import {
|
|
2
|
-
|
|
3
|
-
INDUSTRY_RAG_BENCHMARKS,
|
|
4
|
-
buildFirstPartyMemoryLifecycleBenchmarkCases,
|
|
5
|
-
buildIndustryMemoryBenchmarkSmokeCases,
|
|
6
|
-
buildIndustryRagBenchmarkSmokeCases,
|
|
7
|
-
buildKnowledgeBenchmarkScenarios,
|
|
8
|
-
buildRetrievalBenchmarkCasesFromQrels,
|
|
9
|
-
createInMemoryBenchmarkAdapter,
|
|
10
|
-
createNoopMemoryBenchmarkAdapter,
|
|
11
|
-
isKnowledgeMemoryBenchmarkCase,
|
|
12
|
-
knowledgeBenchmarkJudge,
|
|
13
|
-
parseKnowledgeBenchmarkJsonl,
|
|
14
|
-
parseKnowledgeBenchmarkQrels,
|
|
15
|
-
renderKnowledgeBenchmarkReportMarkdown,
|
|
16
|
-
respondToIndustryMemoryBenchmarkSmokeCase,
|
|
17
|
-
respondToIndustryRagBenchmarkSmokeCase,
|
|
18
|
-
runKnowledgeBenchmarkSuite,
|
|
19
|
-
runMemoryAdapterBenchmark,
|
|
20
|
-
scoreKnowledgeBenchmarkArtifact,
|
|
21
|
-
scoreMemoryBenchmarkArtifact,
|
|
22
|
-
summarizeKnowledgeBenchmarkCampaign
|
|
23
|
-
} from "../chunk-EYIA5PLQ.js";
|
|
24
|
-
import "../chunk-DQ3PDMDP.js";
|
|
25
|
-
import "../chunk-YMKHCTS2.js";
|
|
26
|
-
export {
|
|
27
|
-
INDUSTRY_MEMORY_BENCHMARKS,
|
|
28
|
-
INDUSTRY_RAG_BENCHMARKS,
|
|
29
|
-
buildFirstPartyMemoryLifecycleBenchmarkCases,
|
|
30
|
-
buildIndustryMemoryBenchmarkSmokeCases,
|
|
31
|
-
buildIndustryRagBenchmarkSmokeCases,
|
|
32
|
-
buildKnowledgeBenchmarkScenarios,
|
|
33
|
-
buildRetrievalBenchmarkCasesFromQrels,
|
|
34
|
-
createInMemoryBenchmarkAdapter,
|
|
35
|
-
createNoopMemoryBenchmarkAdapter,
|
|
36
|
-
isKnowledgeMemoryBenchmarkCase,
|
|
37
|
-
knowledgeBenchmarkJudge,
|
|
38
|
-
parseKnowledgeBenchmarkJsonl,
|
|
39
|
-
parseKnowledgeBenchmarkQrels,
|
|
40
|
-
renderKnowledgeBenchmarkReportMarkdown,
|
|
41
|
-
respondToIndustryMemoryBenchmarkSmokeCase,
|
|
42
|
-
respondToIndustryRagBenchmarkSmokeCase,
|
|
43
|
-
runKnowledgeBenchmarkSuite,
|
|
44
|
-
runMemoryAdapterBenchmark,
|
|
45
|
-
scoreKnowledgeBenchmarkArtifact,
|
|
46
|
-
scoreMemoryBenchmarkArtifact,
|
|
47
|
-
summarizeKnowledgeBenchmarkCampaign
|
|
48
|
-
};
|
|
49
|
-
//# sourceMappingURL=index.js.map
|
|
1
|
+
import { A as INDUSTRY_RAG_BENCHMARKS, F as respondToIndustryRagBenchmarkSmokeCase, I as isKnowledgeMemoryBenchmarkCase, L as createInMemoryBenchmarkAdapter, M as buildIndustryMemoryBenchmarkSmokeCases, N as buildIndustryRagBenchmarkSmokeCases, P as respondToIndustryMemoryBenchmarkSmokeCase, R as createNoopMemoryBenchmarkAdapter, a as buildKnowledgeBenchmarkScenarios, c as runKnowledgeBenchmarkSuite, d as summarizeKnowledgeBenchmarkCampaign, i as runMemoryAdapterBenchmark, j as buildFirstPartyMemoryLifecycleBenchmarkCases, k as INDUSTRY_MEMORY_BENCHMARKS, l as scoreKnowledgeBenchmarkArtifact, n as parseKnowledgeBenchmarkJsonl, o as knowledgeBenchmarkJudge, r as parseKnowledgeBenchmarkQrels, s as renderKnowledgeBenchmarkReportMarkdown, t as buildRetrievalBenchmarkCasesFromQrels, u as scoreMemoryBenchmarkArtifact } from "../benchmarks-CmW6iORW.js";
|
|
2
|
+
export { INDUSTRY_MEMORY_BENCHMARKS, INDUSTRY_RAG_BENCHMARKS, buildFirstPartyMemoryLifecycleBenchmarkCases, buildIndustryMemoryBenchmarkSmokeCases, buildIndustryRagBenchmarkSmokeCases, buildKnowledgeBenchmarkScenarios, buildRetrievalBenchmarkCasesFromQrels, createInMemoryBenchmarkAdapter, createNoopMemoryBenchmarkAdapter, isKnowledgeMemoryBenchmarkCase, knowledgeBenchmarkJudge, parseKnowledgeBenchmarkJsonl, parseKnowledgeBenchmarkQrels, renderKnowledgeBenchmarkReportMarkdown, respondToIndustryMemoryBenchmarkSmokeCase, respondToIndustryRagBenchmarkSmokeCase, runKnowledgeBenchmarkSuite, runMemoryAdapterBenchmark, scoreKnowledgeBenchmarkArtifact, scoreMemoryBenchmarkArtifact, summarizeKnowledgeBenchmarkCampaign };
|