@fllf/agent-sdk 0.1.2 → 0.1.3
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 +169 -0
- package/README.md +824 -198
- package/dist/agent/Agent.d.ts +16 -5
- package/dist/agent/Agent.d.ts.map +1 -1
- package/dist/agent/Agent.js +283 -2
- package/dist/agent/Agent.js.map +1 -1
- package/dist/agent/index.d.ts +1 -1
- package/dist/agent/index.d.ts.map +1 -1
- package/dist/agent/types.d.ts +27 -3
- package/dist/agent/types.d.ts.map +1 -1
- package/dist/config/config.d.ts +22 -3
- package/dist/config/config.d.ts.map +1 -1
- package/dist/config/config.js +194 -47
- package/dist/config/config.js.map +1 -1
- package/dist/config/index.d.ts +1 -1
- package/dist/config/index.d.ts.map +1 -1
- package/dist/errors.d.ts +74 -0
- package/dist/errors.d.ts.map +1 -0
- package/dist/errors.js +186 -0
- package/dist/errors.js.map +1 -0
- package/dist/executors/base-executor.d.ts +14 -0
- package/dist/executors/base-executor.d.ts.map +1 -0
- package/dist/executors/base-executor.js +31 -0
- package/dist/executors/base-executor.js.map +1 -0
- package/dist/executors/base.d.ts +36 -5
- package/dist/executors/base.d.ts.map +1 -1
- package/dist/executors/chat-request-builder.d.ts +10 -0
- package/dist/executors/chat-request-builder.d.ts.map +1 -0
- package/dist/executors/chat-request-builder.js +96 -0
- package/dist/executors/chat-request-builder.js.map +1 -0
- package/dist/executors/index.d.ts +4 -1
- package/dist/executors/index.d.ts.map +1 -1
- package/dist/executors/index.js +6 -1
- package/dist/executors/index.js.map +1 -1
- package/dist/executors/rag-executor.js +1 -1
- package/dist/executors/rag-executor.js.map +1 -1
- package/dist/executors/simple-chat-executor.d.ts +4 -2
- package/dist/executors/simple-chat-executor.d.ts.map +1 -1
- package/dist/executors/simple-chat-executor.js +59 -57
- package/dist/executors/simple-chat-executor.js.map +1 -1
- package/dist/executors/tool-calling-executor.d.ts +20 -2
- package/dist/executors/tool-calling-executor.d.ts.map +1 -1
- package/dist/executors/tool-calling-executor.js +189 -91
- package/dist/executors/tool-calling-executor.js.map +1 -1
- package/dist/history/base.d.ts +55 -2
- package/dist/history/base.d.ts.map +1 -1
- package/dist/history/base.js +49 -0
- package/dist/history/base.js.map +1 -1
- package/dist/history/compression.d.ts +49 -0
- package/dist/history/compression.d.ts.map +1 -0
- package/dist/history/compression.js +53 -0
- package/dist/history/compression.js.map +1 -0
- package/dist/history/context-window.d.ts +33 -0
- package/dist/history/context-window.d.ts.map +1 -0
- package/dist/history/context-window.js +68 -0
- package/dist/history/context-window.js.map +1 -0
- package/dist/history/in-memory.d.ts +6 -4
- package/dist/history/in-memory.d.ts.map +1 -1
- package/dist/history/in-memory.js +25 -39
- package/dist/history/in-memory.js.map +1 -1
- package/dist/history/index.d.ts +9 -2
- package/dist/history/index.d.ts.map +1 -1
- package/dist/history/index.js +18 -1
- package/dist/history/index.js.map +1 -1
- package/dist/history/postgres/index.d.ts +4 -0
- package/dist/history/postgres/index.d.ts.map +1 -0
- package/dist/history/postgres/index.js +20 -0
- package/dist/history/postgres/index.js.map +1 -0
- package/dist/history/postgres/postgres-message-history-store.d.ts +35 -0
- package/dist/history/postgres/postgres-message-history-store.d.ts.map +1 -0
- package/dist/history/postgres/postgres-message-history-store.js +195 -0
- package/dist/history/postgres/postgres-message-history-store.js.map +1 -0
- package/dist/history/postgres/schema.d.ts +18 -0
- package/dist/history/postgres/schema.d.ts.map +1 -0
- package/dist/history/postgres/schema.js +46 -0
- package/dist/history/postgres/schema.js.map +1 -0
- package/dist/history/postgres/sql.d.ts +29 -0
- package/dist/history/postgres/sql.d.ts.map +1 -0
- package/dist/history/postgres/sql.js +102 -0
- package/dist/history/postgres/sql.js.map +1 -0
- package/dist/history/postgres/types.d.ts +20 -0
- package/dist/history/postgres/types.d.ts.map +1 -0
- package/dist/history/postgres/types.js +3 -0
- package/dist/history/postgres/types.js.map +1 -0
- package/dist/history/tool-pairing.d.ts +11 -0
- package/dist/history/tool-pairing.d.ts.map +1 -0
- package/dist/history/tool-pairing.js +52 -0
- package/dist/history/tool-pairing.js.map +1 -0
- package/dist/index.d.ts +2 -0
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +2 -0
- package/dist/index.js.map +1 -1
- package/dist/llm/LLM.d.ts +1 -0
- package/dist/llm/LLM.d.ts.map +1 -1
- package/dist/llm/LLM.js +136 -26
- package/dist/llm/LLM.js.map +1 -1
- package/dist/llm/errors.d.ts +11 -1
- package/dist/llm/errors.d.ts.map +1 -1
- package/dist/llm/errors.js +50 -1
- package/dist/llm/errors.js.map +1 -1
- package/dist/llm/factory.d.ts +14 -2
- package/dist/llm/factory.d.ts.map +1 -1
- package/dist/llm/factory.js +48 -9
- package/dist/llm/factory.js.map +1 -1
- package/dist/llm/index.d.ts +8 -3
- package/dist/llm/index.d.ts.map +1 -1
- package/dist/llm/index.js +10 -1
- package/dist/llm/index.js.map +1 -1
- package/dist/llm/providers/anthropic.d.ts +14 -0
- package/dist/llm/providers/anthropic.d.ts.map +1 -0
- package/dist/llm/providers/anthropic.js +336 -0
- package/dist/llm/providers/anthropic.js.map +1 -0
- package/dist/llm/providers/openai-compatible.d.ts +7 -0
- package/dist/llm/providers/openai-compatible.d.ts.map +1 -1
- package/dist/llm/providers/openai-compatible.js +151 -47
- package/dist/llm/providers/openai-compatible.js.map +1 -1
- package/dist/llm/stream-accumulator.d.ts +17 -0
- package/dist/llm/stream-accumulator.d.ts.map +1 -0
- package/dist/llm/stream-accumulator.js +83 -0
- package/dist/llm/stream-accumulator.js.map +1 -0
- package/dist/llm/tool-arguments.d.ts +6 -0
- package/dist/llm/tool-arguments.d.ts.map +1 -0
- package/dist/llm/tool-arguments.js +20 -0
- package/dist/llm/tool-arguments.js.map +1 -0
- package/dist/llm/types.d.ts +76 -4
- package/dist/llm/types.d.ts.map +1 -1
- package/dist/messages/content.d.ts +36 -0
- package/dist/messages/content.d.ts.map +1 -0
- package/dist/messages/content.js +70 -0
- package/dist/messages/content.js.map +1 -0
- package/dist/messages/index.d.ts +4 -2
- package/dist/messages/index.d.ts.map +1 -1
- package/dist/messages/index.js +10 -1
- package/dist/messages/index.js.map +1 -1
- package/dist/messages/message.d.ts +11 -9
- package/dist/messages/message.d.ts.map +1 -1
- package/dist/messages/message.js +69 -4
- package/dist/messages/message.js.map +1 -1
- package/dist/messages/types.d.ts +12 -0
- package/dist/messages/types.d.ts.map +1 -1
- package/dist/observability/collecting-observer.d.ts +8 -0
- package/dist/observability/collecting-observer.d.ts.map +1 -0
- package/dist/observability/collecting-observer.js +15 -0
- package/dist/observability/collecting-observer.js.map +1 -0
- package/dist/observability/index.d.ts +1 -0
- package/dist/observability/index.d.ts.map +1 -1
- package/dist/observability/index.js +3 -1
- package/dist/observability/index.js.map +1 -1
- package/dist/observability/observer.d.ts.map +1 -1
- package/dist/observability/observer.js +14 -1
- package/dist/observability/observer.js.map +1 -1
- package/dist/observability/types.d.ts +16 -1
- package/dist/observability/types.d.ts.map +1 -1
- package/dist/rag/chunking/auto-chunker.d.ts +7 -0
- package/dist/rag/chunking/auto-chunker.d.ts.map +1 -1
- package/dist/rag/chunking/auto-chunker.js +13 -0
- package/dist/rag/chunking/auto-chunker.js.map +1 -1
- package/dist/rag/chunking/chunker.d.ts.map +1 -1
- package/dist/rag/chunking/chunker.js +29 -5
- package/dist/rag/chunking/chunker.js.map +1 -1
- package/dist/rag/chunking/index.d.ts +2 -0
- package/dist/rag/chunking/index.d.ts.map +1 -1
- package/dist/rag/chunking/index.js +2 -0
- package/dist/rag/chunking/index.js.map +1 -1
- package/dist/rag/chunking/markdown-chunker.d.ts.map +1 -1
- package/dist/rag/chunking/markdown-chunker.js.map +1 -1
- package/dist/rag/chunking/qa-pair-chunker.d.ts +23 -0
- package/dist/rag/chunking/qa-pair-chunker.d.ts.map +1 -0
- package/dist/rag/chunking/qa-pair-chunker.js +162 -0
- package/dist/rag/chunking/qa-pair-chunker.js.map +1 -0
- package/dist/rag/chunking/semantic-chunker.d.ts +19 -0
- package/dist/rag/chunking/semantic-chunker.d.ts.map +1 -0
- package/dist/rag/chunking/semantic-chunker.js +291 -0
- package/dist/rag/chunking/semantic-chunker.js.map +1 -0
- package/dist/rag/embeddings/embedder.d.ts.map +1 -1
- package/dist/rag/embeddings/embedder.js +6 -0
- package/dist/rag/embeddings/embedder.js.map +1 -1
- package/dist/rag/generation/context-builder.d.ts +7 -0
- package/dist/rag/generation/context-builder.d.ts.map +1 -1
- package/dist/rag/generation/context-builder.js +4 -1
- package/dist/rag/generation/context-builder.js.map +1 -1
- package/dist/rag/ingestion/metadata.d.ts +6 -1
- package/dist/rag/ingestion/metadata.d.ts.map +1 -1
- package/dist/rag/ingestion/metadata.js +6 -2
- package/dist/rag/ingestion/metadata.js.map +1 -1
- package/dist/rag/pipeline.d.ts.map +1 -1
- package/dist/rag/pipeline.js +34 -11
- package/dist/rag/pipeline.js.map +1 -1
- package/dist/rag/retrieval/index.d.ts +1 -0
- package/dist/rag/retrieval/index.d.ts.map +1 -1
- package/dist/rag/retrieval/index.js +1 -0
- package/dist/rag/retrieval/index.js.map +1 -1
- package/dist/rag/retrieval/parent-child-expanding-retriever.d.ts +31 -0
- package/dist/rag/retrieval/parent-child-expanding-retriever.d.ts.map +1 -0
- package/dist/rag/retrieval/parent-child-expanding-retriever.js +194 -0
- package/dist/rag/retrieval/parent-child-expanding-retriever.js.map +1 -0
- package/dist/rag/stores/in-memory-keyword-store.d.ts.map +1 -1
- package/dist/rag/stores/in-memory-keyword-store.js +3 -8
- package/dist/rag/stores/in-memory-keyword-store.js.map +1 -1
- package/dist/rag/stores/keyword-tokenizer.d.ts +4 -0
- package/dist/rag/stores/keyword-tokenizer.d.ts.map +1 -0
- package/dist/rag/stores/keyword-tokenizer.js +113 -0
- package/dist/rag/stores/keyword-tokenizer.js.map +1 -0
- package/dist/rag/stores/postgres/pg-vector-store.d.ts.map +1 -1
- package/dist/rag/stores/postgres/pg-vector-store.js +21 -8
- package/dist/rag/stores/postgres/pg-vector-store.js.map +1 -1
- package/dist/rag/stores/postgres/postgres-document-store.d.ts.map +1 -1
- package/dist/rag/stores/postgres/postgres-document-store.js +26 -13
- package/dist/rag/stores/postgres/postgres-document-store.js.map +1 -1
- package/dist/rag/stores/postgres/postgres-keyword-store.d.ts.map +1 -1
- package/dist/rag/stores/postgres/postgres-keyword-store.js +43 -43
- package/dist/rag/stores/postgres/postgres-keyword-store.js.map +1 -1
- package/dist/rag/stores/postgres/sql.d.ts +22 -0
- package/dist/rag/stores/postgres/sql.d.ts.map +1 -1
- package/dist/rag/stores/postgres/sql.js +42 -0
- package/dist/rag/stores/postgres/sql.js.map +1 -1
- package/dist/rag/stores/types.d.ts +5 -0
- package/dist/rag/stores/types.d.ts.map +1 -1
- package/dist/rag/types.d.ts +6 -0
- package/dist/rag/types.d.ts.map +1 -1
- package/dist/testing/agent.d.ts +11 -0
- package/dist/testing/agent.d.ts.map +1 -0
- package/dist/testing/agent.js +45 -0
- package/dist/testing/agent.js.map +1 -0
- package/dist/testing/history-contract.d.ts +12 -0
- package/dist/testing/history-contract.d.ts.map +1 -0
- package/dist/testing/history-contract.js +111 -0
- package/dist/testing/history-contract.js.map +1 -0
- package/dist/testing/index.d.ts +11 -0
- package/dist/testing/index.d.ts.map +1 -0
- package/dist/testing/index.js +16 -0
- package/dist/testing/index.js.map +1 -0
- package/dist/testing/models.d.ts +34 -0
- package/dist/testing/models.d.ts.map +1 -0
- package/dist/testing/models.js +74 -0
- package/dist/testing/models.js.map +1 -0
- package/dist/testing/tool-schema.d.ts +6 -0
- package/dist/testing/tool-schema.d.ts.map +1 -0
- package/dist/testing/tool-schema.js +29 -0
- package/dist/testing/tool-schema.js.map +1 -0
- package/dist/testing/tools.d.ts +21 -0
- package/dist/testing/tools.d.ts.map +1 -0
- package/dist/testing/tools.js +43 -0
- package/dist/testing/tools.js.map +1 -0
- package/dist/tools/base.d.ts +38 -7
- package/dist/tools/base.d.ts.map +1 -1
- package/dist/tools/base.js +238 -11
- package/dist/tools/base.js.map +1 -1
- package/dist/tools/builtin/advancedSearchTool.d.ts.map +1 -1
- package/dist/tools/builtin/advancedSearchTool.js +30 -4
- package/dist/tools/builtin/advancedSearchTool.js.map +1 -1
- package/dist/tools/builtin/ragSearchTool.d.ts +6 -3
- package/dist/tools/builtin/ragSearchTool.d.ts.map +1 -1
- package/dist/tools/builtin/ragSearchTool.js +8 -6
- package/dist/tools/builtin/ragSearchTool.js.map +1 -1
- package/dist/tools/executor.d.ts +30 -2
- package/dist/tools/executor.d.ts.map +1 -1
- package/dist/tools/executor.js +83 -15
- package/dist/tools/executor.js.map +1 -1
- package/dist/tools/index.d.ts +3 -1
- package/dist/tools/index.d.ts.map +1 -1
- package/dist/tools/registry.d.ts +15 -3
- package/dist/tools/registry.d.ts.map +1 -1
- package/dist/tools/registry.js +21 -2
- package/dist/tools/registry.js.map +1 -1
- package/package.json +58 -4
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/rag/retrieval/index.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;AAAA,0CAAwB;AACxB,oDAAkC;AAClC,2CAAyB;AACzB,qDAAmC;AACnC,6DAA2C;AAC3C,6CAA2B;AAC3B,qDAAmC"}
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/rag/retrieval/index.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;AAAA,0CAAwB;AACxB,oDAAkC;AAClC,2CAAyB;AACzB,qDAAmC;AACnC,6DAA2C;AAC3C,qEAAmD;AACnD,6CAA2B;AAC3B,qDAAmC"}
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
import type { RetrievedChunk, RetrieveOptions } from '../types';
|
|
2
|
+
import type { DocumentStore } from '../stores';
|
|
3
|
+
import type { Retriever } from './types';
|
|
4
|
+
export type ParentChildExpansionStrategy = 'parent' | 'neighbors' | 'parent_or_neighbors';
|
|
5
|
+
export interface ParentChildExpandingRetrieverOptions {
|
|
6
|
+
retriever: Retriever;
|
|
7
|
+
documentStore: DocumentStore;
|
|
8
|
+
strategy?: ParentChildExpansionStrategy;
|
|
9
|
+
neighborWindow?: number;
|
|
10
|
+
includeOriginalChunks?: boolean;
|
|
11
|
+
maxExpandedChunkCharacters?: number;
|
|
12
|
+
}
|
|
13
|
+
/**
|
|
14
|
+
* Expands child chunk hits into larger context chunks after retrieval.
|
|
15
|
+
* This keeps child chunks useful for recall while letting generation receive
|
|
16
|
+
* parent or neighboring context without changing the underlying retriever.
|
|
17
|
+
*/
|
|
18
|
+
export declare class ParentChildExpandingRetriever implements Retriever {
|
|
19
|
+
private readonly retriever;
|
|
20
|
+
private readonly documentStore;
|
|
21
|
+
private readonly strategy;
|
|
22
|
+
private readonly neighborWindow;
|
|
23
|
+
private readonly includeOriginalChunks;
|
|
24
|
+
private readonly maxExpandedChunkCharacters;
|
|
25
|
+
constructor(options: ParentChildExpandingRetrieverOptions);
|
|
26
|
+
retrieve(query: string, options?: RetrieveOptions): Promise<RetrievedChunk[]>;
|
|
27
|
+
private expandItem;
|
|
28
|
+
private createParentExpansion;
|
|
29
|
+
private createNeighborExpansions;
|
|
30
|
+
}
|
|
31
|
+
//# sourceMappingURL=parent-child-expanding-retriever.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"parent-child-expanding-retriever.d.ts","sourceRoot":"","sources":["../../../src/rag/retrieval/parent-child-expanding-retriever.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAER,cAAc,EACd,eAAe,EAClB,MAAM,UAAU,CAAC;AAClB,OAAO,KAAK,EACR,aAAa,EAEhB,MAAM,WAAW,CAAC;AAKnB,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,SAAS,CAAC;AAMzC,MAAM,MAAM,4BAA4B,GAAG,QAAQ,GAAG,WAAW,GAAG,qBAAqB,CAAC;AAE1F,MAAM,WAAW,oCAAoC;IACjD,SAAS,EAAE,SAAS,CAAC;IACrB,aAAa,EAAE,aAAa,CAAC;IAC7B,QAAQ,CAAC,EAAE,4BAA4B,CAAC;IACxC,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,qBAAqB,CAAC,EAAE,OAAO,CAAC;IAChC,0BAA0B,CAAC,EAAE,MAAM,CAAC;CACvC;AAMD;;;;GAIG;AACH,qBAAa,6BAA8B,YAAW,SAAS;IAC3D,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAY;IACtC,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAgB;IAC9C,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAA+B;IACxD,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAS;IACxC,OAAO,CAAC,QAAQ,CAAC,qBAAqB,CAAU;IAChD,OAAO,CAAC,QAAQ,CAAC,0BAA0B,CAAqB;gBAEpD,OAAO,EAAE,oCAAoC;IAWnD,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;YAsCrE,UAAU;IAyBxB,OAAO,CAAC,qBAAqB;IA2B7B,OAAO,CAAC,wBAAwB;CAwBnC"}
|
|
@@ -0,0 +1,194 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
|
+
exports.ParentChildExpandingRetriever = void 0;
|
|
4
|
+
const utils_1 = require("../stores/utils");
|
|
5
|
+
const utils_2 = require("./utils");
|
|
6
|
+
/**
|
|
7
|
+
* Expands child chunk hits into larger context chunks after retrieval.
|
|
8
|
+
* This keeps child chunks useful for recall while letting generation receive
|
|
9
|
+
* parent or neighboring context without changing the underlying retriever.
|
|
10
|
+
*/
|
|
11
|
+
class ParentChildExpandingRetriever {
|
|
12
|
+
retriever;
|
|
13
|
+
documentStore;
|
|
14
|
+
strategy;
|
|
15
|
+
neighborWindow;
|
|
16
|
+
includeOriginalChunks;
|
|
17
|
+
maxExpandedChunkCharacters;
|
|
18
|
+
constructor(options) {
|
|
19
|
+
this.retriever = options.retriever;
|
|
20
|
+
this.documentStore = options.documentStore;
|
|
21
|
+
this.strategy = options.strategy ?? 'parent';
|
|
22
|
+
this.neighborWindow = normalizeNonNegativeInteger(options.neighborWindow, 0);
|
|
23
|
+
this.includeOriginalChunks = options.includeOriginalChunks ?? false;
|
|
24
|
+
this.maxExpandedChunkCharacters = normalizeOptionalPositiveInteger(options.maxExpandedChunkCharacters);
|
|
25
|
+
}
|
|
26
|
+
async retrieve(query, options) {
|
|
27
|
+
const recalled = await this.retriever.retrieve(query, options);
|
|
28
|
+
if (recalled.length === 0) {
|
|
29
|
+
return [];
|
|
30
|
+
}
|
|
31
|
+
const cache = createDocumentChunkCache(this.documentStore);
|
|
32
|
+
const searchOptions = (0, utils_2.toSearchOptions)(options);
|
|
33
|
+
const expanded = [];
|
|
34
|
+
const expandedByChunkId = new Map();
|
|
35
|
+
for (const item of recalled) {
|
|
36
|
+
if (this.includeOriginalChunks) {
|
|
37
|
+
appendOrMergeRetrievedChunk(expanded, expandedByChunkId, (0, utils_2.cloneRetrievedChunk)(item));
|
|
38
|
+
}
|
|
39
|
+
const expandedItems = await this.expandItem(item, cache, searchOptions);
|
|
40
|
+
if (expandedItems.length === 0) {
|
|
41
|
+
appendOrMergeRetrievedChunk(expanded, expandedByChunkId, (0, utils_2.cloneRetrievedChunk)(item));
|
|
42
|
+
continue;
|
|
43
|
+
}
|
|
44
|
+
for (const expandedItem of expandedItems) {
|
|
45
|
+
appendOrMergeRetrievedChunk(expanded, expandedByChunkId, expandedItem);
|
|
46
|
+
}
|
|
47
|
+
}
|
|
48
|
+
return expanded;
|
|
49
|
+
}
|
|
50
|
+
async expandItem(item, cache, searchOptions) {
|
|
51
|
+
const chunks = await cache.get(item.chunk.documentId);
|
|
52
|
+
if (this.strategy === 'parent') {
|
|
53
|
+
const parent = this.createParentExpansion(item, chunks, searchOptions);
|
|
54
|
+
return parent === undefined ? [] : [parent];
|
|
55
|
+
}
|
|
56
|
+
if (this.strategy === 'neighbors') {
|
|
57
|
+
return this.createNeighborExpansions(item, chunks, searchOptions);
|
|
58
|
+
}
|
|
59
|
+
const parent = this.createParentExpansion(item, chunks, searchOptions);
|
|
60
|
+
if (parent !== undefined) {
|
|
61
|
+
return [parent];
|
|
62
|
+
}
|
|
63
|
+
return this.createNeighborExpansions(item, chunks, searchOptions);
|
|
64
|
+
}
|
|
65
|
+
createParentExpansion(item, chunks, searchOptions) {
|
|
66
|
+
const parentId = item.chunk.parentId;
|
|
67
|
+
if (parentId === undefined) {
|
|
68
|
+
return undefined;
|
|
69
|
+
}
|
|
70
|
+
const parent = chunks.find((chunk) => chunk.id === parentId);
|
|
71
|
+
if (parent === undefined) {
|
|
72
|
+
return undefined;
|
|
73
|
+
}
|
|
74
|
+
if (!(0, utils_1.matchesSearchOptions)(parent, searchOptions)) {
|
|
75
|
+
return undefined;
|
|
76
|
+
}
|
|
77
|
+
if (this.maxExpandedChunkCharacters !== undefined
|
|
78
|
+
&& parent.content.length > this.maxExpandedChunkCharacters) {
|
|
79
|
+
return undefined;
|
|
80
|
+
}
|
|
81
|
+
return createExpandedRetrievedChunk(parent, item, 'parent');
|
|
82
|
+
}
|
|
83
|
+
createNeighborExpansions(item, chunks, searchOptions) {
|
|
84
|
+
const candidates = getNeighborCandidates(item.chunk, chunks)
|
|
85
|
+
.filter((chunk) => (0, utils_1.matchesSearchOptions)(chunk, searchOptions))
|
|
86
|
+
.sort((left, right) => left.metadata.chunkIndex - right.metadata.chunkIndex);
|
|
87
|
+
const centerIndex = candidates.findIndex((chunk) => chunk.id === item.chunk.id);
|
|
88
|
+
if (centerIndex < 0) {
|
|
89
|
+
return [];
|
|
90
|
+
}
|
|
91
|
+
const start = Math.max(0, centerIndex - this.neighborWindow);
|
|
92
|
+
const end = Math.min(candidates.length, centerIndex + this.neighborWindow + 1);
|
|
93
|
+
return candidates
|
|
94
|
+
.slice(start, end)
|
|
95
|
+
.map((chunk) => (chunk.id === item.chunk.id
|
|
96
|
+
? createExpandedRetrievedChunk(chunk, item, 'self')
|
|
97
|
+
: createExpandedRetrievedChunk(chunk, item, 'neighbor')));
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
exports.ParentChildExpandingRetriever = ParentChildExpandingRetriever;
|
|
101
|
+
function createDocumentChunkCache(documentStore) {
|
|
102
|
+
const chunksByDocumentId = new Map();
|
|
103
|
+
return {
|
|
104
|
+
async get(documentId) {
|
|
105
|
+
let chunks = chunksByDocumentId.get(documentId);
|
|
106
|
+
if (chunks === undefined) {
|
|
107
|
+
chunks = documentStore.getChunksByDocument(documentId);
|
|
108
|
+
chunksByDocumentId.set(documentId, chunks);
|
|
109
|
+
}
|
|
110
|
+
return await chunks;
|
|
111
|
+
},
|
|
112
|
+
};
|
|
113
|
+
}
|
|
114
|
+
function getNeighborCandidates(hit, chunks) {
|
|
115
|
+
if (hit.parentId !== undefined) {
|
|
116
|
+
return chunks.filter((chunk) => chunk.id === hit.id || chunk.parentId === hit.parentId);
|
|
117
|
+
}
|
|
118
|
+
return chunks.filter((chunk) => chunk.parentId === undefined);
|
|
119
|
+
}
|
|
120
|
+
function createExpandedRetrievedChunk(chunk, original, expansion) {
|
|
121
|
+
const item = {
|
|
122
|
+
chunk: (0, utils_1.cloneChunk)(chunk),
|
|
123
|
+
score: original.score,
|
|
124
|
+
source: original.source,
|
|
125
|
+
metadata: createExpansionMetadata(original, expansion),
|
|
126
|
+
};
|
|
127
|
+
return item;
|
|
128
|
+
}
|
|
129
|
+
function createExpansionMetadata(original, expansion) {
|
|
130
|
+
const metadata = {
|
|
131
|
+
...(original.metadata ?? {}),
|
|
132
|
+
expansion,
|
|
133
|
+
expandedFromChunkIds: [original.chunk.id],
|
|
134
|
+
};
|
|
135
|
+
assignIfDefined(metadata, 'expandedFromParentId', original.chunk.parentId);
|
|
136
|
+
return metadata;
|
|
137
|
+
}
|
|
138
|
+
function appendOrMergeRetrievedChunk(chunks, chunksById, item) {
|
|
139
|
+
const existing = chunksById.get(item.chunk.id);
|
|
140
|
+
if (existing === undefined) {
|
|
141
|
+
chunks.push(item);
|
|
142
|
+
chunksById.set(item.chunk.id, item);
|
|
143
|
+
return;
|
|
144
|
+
}
|
|
145
|
+
existing.score = Math.max(existing.score, item.score);
|
|
146
|
+
const metadata = mergeRetrievedMetadata(existing.metadata, item.metadata);
|
|
147
|
+
if (metadata === undefined) {
|
|
148
|
+
delete existing.metadata;
|
|
149
|
+
}
|
|
150
|
+
else {
|
|
151
|
+
existing.metadata = metadata;
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
function mergeRetrievedMetadata(left, right) {
|
|
155
|
+
if (left === undefined && right === undefined) {
|
|
156
|
+
return undefined;
|
|
157
|
+
}
|
|
158
|
+
const metadata = {
|
|
159
|
+
...(left ?? {}),
|
|
160
|
+
...(right ?? {}),
|
|
161
|
+
};
|
|
162
|
+
const expandedFromChunkIds = [
|
|
163
|
+
...readStringArray(left?.expandedFromChunkIds),
|
|
164
|
+
...readStringArray(right?.expandedFromChunkIds),
|
|
165
|
+
];
|
|
166
|
+
if (expandedFromChunkIds.length > 0) {
|
|
167
|
+
metadata.expandedFromChunkIds = [...new Set(expandedFromChunkIds)];
|
|
168
|
+
}
|
|
169
|
+
return metadata;
|
|
170
|
+
}
|
|
171
|
+
function readStringArray(value) {
|
|
172
|
+
if (!Array.isArray(value)) {
|
|
173
|
+
return [];
|
|
174
|
+
}
|
|
175
|
+
return value.filter((item) => typeof item === 'string');
|
|
176
|
+
}
|
|
177
|
+
function normalizeNonNegativeInteger(value, fallback) {
|
|
178
|
+
if (value === undefined || !Number.isFinite(value) || value < 0) {
|
|
179
|
+
return fallback;
|
|
180
|
+
}
|
|
181
|
+
return Math.floor(value);
|
|
182
|
+
}
|
|
183
|
+
function normalizeOptionalPositiveInteger(value) {
|
|
184
|
+
if (value === undefined || !Number.isFinite(value) || value <= 0) {
|
|
185
|
+
return undefined;
|
|
186
|
+
}
|
|
187
|
+
return Math.floor(value);
|
|
188
|
+
}
|
|
189
|
+
function assignIfDefined(target, key, value) {
|
|
190
|
+
if (value !== undefined) {
|
|
191
|
+
target[key] = value;
|
|
192
|
+
}
|
|
193
|
+
}
|
|
194
|
+
//# sourceMappingURL=parent-child-expanding-retriever.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"parent-child-expanding-retriever.js","sourceRoot":"","sources":["../../../src/rag/retrieval/parent-child-expanding-retriever.ts"],"names":[],"mappings":";;;AASA,2CAGyB;AAEzB,mCAGiB;AAiBjB;;;;GAIG;AACH,MAAa,6BAA6B;IACrB,SAAS,CAAY;IACrB,aAAa,CAAgB;IAC7B,QAAQ,CAA+B;IACvC,cAAc,CAAS;IACvB,qBAAqB,CAAU;IAC/B,0BAA0B,CAAqB;IAEhE,YAAY,OAA6C;QACrD,IAAI,CAAC,SAAS,GAAG,OAAO,CAAC,SAAS,CAAC;QACnC,IAAI,CAAC,aAAa,GAAG,OAAO,CAAC,aAAa,CAAC;QAC3C,IAAI,CAAC,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,QAAQ,CAAC;QAC7C,IAAI,CAAC,cAAc,GAAG,2BAA2B,CAAC,OAAO,CAAC,cAAc,EAAE,CAAC,CAAC,CAAC;QAC7E,IAAI,CAAC,qBAAqB,GAAG,OAAO,CAAC,qBAAqB,IAAI,KAAK,CAAC;QACpE,IAAI,CAAC,0BAA0B,GAAG,gCAAgC,CAC9D,OAAO,CAAC,0BAA0B,CACrC,CAAC;IACN,CAAC;IAED,KAAK,CAAC,QAAQ,CAAC,KAAa,EAAE,OAAyB;QACnD,MAAM,QAAQ,GAAG,MAAM,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;QAC/D,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACxB,OAAO,EAAE,CAAC;QACd,CAAC;QAED,MAAM,KAAK,GAAG,wBAAwB,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC;QAC3D,MAAM,aAAa,GAAG,IAAA,uBAAe,EAAC,OAAO,CAAC,CAAC;QAC/C,MAAM,QAAQ,GAAqB,EAAE,CAAC;QACtC,MAAM,iBAAiB,GAAG,IAAI,GAAG,EAA0B,CAAC;QAE5D,KAAK,MAAM,IAAI,IAAI,QAAQ,EAAE,CAAC;YAC1B,IAAI,IAAI,CAAC,qBAAqB,EAAE,CAAC;gBAC7B,2BAA2B,CACvB,QAAQ,EACR,iBAAiB,EACjB,IAAA,2BAAmB,EAAC,IAAI,CAAC,CAC5B,CAAC;YACN,CAAC;YAED,MAAM,aAAa,GAAG,MAAM,IAAI,CAAC,UAAU,CAAC,IAAI,EAAE,KAAK,EAAE,aAAa,CAAC,CAAC;YACxE,IAAI,aAAa,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBAC7B,2BAA2B,CACvB,QAAQ,EACR,iBAAiB,EACjB,IAAA,2BAAmB,EAAC,IAAI,CAAC,CAC5B,CAAC;gBACF,SAAS;YACb,CAAC;YAED,KAAK,MAAM,YAAY,IAAI,aAAa,EAAE,CAAC;gBACvC,2BAA2B,CAAC,QAAQ,EAAE,iBAAiB,EAAE,YAAY,CAAC,CAAC;YAC3E,CAAC;QACL,CAAC;QAED,OAAO,QAAQ,CAAC;IACpB,CAAC;IAEO,KAAK,CAAC,UAAU,CACpB,IAAoB,EACpB,KAAyB,EACzB,aAA4B;QAE5B,MAAM,MAAM,GAAG,MAAM,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;QAEtD,IAAI,IAAI,CAAC,QAAQ,KAAK,QAAQ,EAAE,CAAC;YAC7B,MAAM,MAAM,GAAG,IAAI,CAAC,qBAAqB,CAAC,IAAI,EAAE,MAAM,EAAE,aAAa,CAAC,CAAC;YAEvE,OAAO,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;QAChD,CAAC;QAED,IAAI,IAAI,CAAC,QAAQ,KAAK,WAAW,EAAE,CAAC;YAChC,OAAO,IAAI,CAAC,wBAAwB,CAAC,IAAI,EAAE,MAAM,EAAE,aAAa,CAAC,CAAC;QACtE,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,CAAC,qBAAqB,CAAC,IAAI,EAAE,MAAM,EAAE,aAAa,CAAC,CAAC;QACvE,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;YACvB,OAAO,CAAC,MAAM,CAAC,CAAC;QACpB,CAAC;QAED,OAAO,IAAI,CAAC,wBAAwB,CAAC,IAAI,EAAE,MAAM,EAAE,aAAa,CAAC,CAAC;IACtE,CAAC;IAEO,qBAAqB,CACzB,IAAoB,EACpB,MAAe,EACf,aAA4B;QAE5B,MAAM,QAAQ,GAAG,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC;QACrC,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;YACzB,OAAO,SAAS,CAAC;QACrB,CAAC;QAED,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,QAAQ,CAAC,CAAC;QAC7D,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;YACvB,OAAO,SAAS,CAAC;QACrB,CAAC;QACD,IAAI,CAAC,IAAA,4BAAoB,EAAC,MAAM,EAAE,aAAa,CAAC,EAAE,CAAC;YAC/C,OAAO,SAAS,CAAC;QACrB,CAAC;QACD,IACI,IAAI,CAAC,0BAA0B,KAAK,SAAS;eAC1C,MAAM,CAAC,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC,0BAA0B,EAC5D,CAAC;YACC,OAAO,SAAS,CAAC;QACrB,CAAC;QAED,OAAO,4BAA4B,CAAC,MAAM,EAAE,IAAI,EAAE,QAAQ,CAAC,CAAC;IAChE,CAAC;IAEO,wBAAwB,CAC5B,IAAoB,EACpB,MAAe,EACf,aAA4B;QAE5B,MAAM,UAAU,GAAG,qBAAqB,CAAC,IAAI,CAAC,KAAK,EAAE,MAAM,CAAC;aACvD,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,IAAA,4BAAoB,EAAC,KAAK,EAAE,aAAa,CAAC,CAAC;aAC7D,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,UAAU,GAAG,KAAK,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;QACjF,MAAM,WAAW,GAAG,UAAU,CAAC,SAAS,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;QAChF,IAAI,WAAW,GAAG,CAAC,EAAE,CAAC;YAClB,OAAO,EAAE,CAAC;QACd,CAAC;QAED,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,GAAG,IAAI,CAAC,cAAc,CAAC,CAAC;QAC7D,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,MAAM,EAAE,WAAW,GAAG,IAAI,CAAC,cAAc,GAAG,CAAC,CAAC,CAAC;QAE/E,OAAO,UAAU;aACZ,KAAK,CAAC,KAAK,EAAE,GAAG,CAAC;aACjB,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CACZ,KAAK,CAAC,EAAE,KAAK,IAAI,CAAC,KAAK,CAAC,EAAE;YACtB,CAAC,CAAC,4BAA4B,CAAC,KAAK,EAAE,IAAI,EAAE,MAAM,CAAC;YACnD,CAAC,CAAC,4BAA4B,CAAC,KAAK,EAAE,IAAI,EAAE,UAAU,CAAC,CAC9D,CAAC,CAAC;IACX,CAAC;CACJ;AArID,sEAqIC;AAED,SAAS,wBAAwB,CAAC,aAA4B;IAC1D,MAAM,kBAAkB,GAAG,IAAI,GAAG,EAA4B,CAAC;IAE/D,OAAO;QACH,KAAK,CAAC,GAAG,CAAC,UAAkB;YACxB,IAAI,MAAM,GAAG,kBAAkB,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;YAChD,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;gBACvB,MAAM,GAAG,aAAa,CAAC,mBAAmB,CAAC,UAAU,CAAC,CAAC;gBACvD,kBAAkB,CAAC,GAAG,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC;YAC/C,CAAC;YAED,OAAO,MAAM,MAAM,CAAC;QACxB,CAAC;KACJ,CAAC;AACN,CAAC;AAED,SAAS,qBAAqB,CAAC,GAAU,EAAE,MAAe;IACtD,IAAI,GAAG,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;QAC7B,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,GAAG,CAAC,EAAE,IAAI,KAAK,CAAC,QAAQ,KAAK,GAAG,CAAC,QAAQ,CAAC,CAAC;IAC5F,CAAC;IAED,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC;AAClE,CAAC;AAED,SAAS,4BAA4B,CACjC,KAAY,EACZ,QAAwB,EACxB,SAAyC;IAEzC,MAAM,IAAI,GAAmB;QACzB,KAAK,EAAE,IAAA,kBAAU,EAAC,KAAK,CAAC;QACxB,KAAK,EAAE,QAAQ,CAAC,KAAK;QACrB,MAAM,EAAE,QAAQ,CAAC,MAAM;QACvB,QAAQ,EAAE,uBAAuB,CAAC,QAAQ,EAAE,SAAS,CAAC;KACzD,CAAC;IAEF,OAAO,IAAI,CAAC;AAChB,CAAC;AAED,SAAS,uBAAuB,CAC5B,QAAwB,EACxB,SAAyC;IAEzC,MAAM,QAAQ,GAA4B;QACtC,GAAG,CAAC,QAAQ,CAAC,QAAQ,IAAI,EAAE,CAAC;QAC5B,SAAS;QACT,oBAAoB,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;KAC5C,CAAC;IAEF,eAAe,CAAC,QAAQ,EAAE,sBAAsB,EAAE,QAAQ,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;IAE3E,OAAO,QAAQ,CAAC;AACpB,CAAC;AAED,SAAS,2BAA2B,CAChC,MAAwB,EACxB,UAAuC,EACvC,IAAoB;IAEpB,MAAM,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAC/C,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;QACzB,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAClB,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,EAAE,IAAI,CAAC,CAAC;QACpC,OAAO;IACX,CAAC;IAED,QAAQ,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;IACtD,MAAM,QAAQ,GAAG,sBAAsB,CAAC,QAAQ,CAAC,QAAQ,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAC;IAC1E,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;QACzB,OAAO,QAAQ,CAAC,QAAQ,CAAC;IAC7B,CAAC;SAAM,CAAC;QACJ,QAAQ,CAAC,QAAQ,GAAG,QAAQ,CAAC;IACjC,CAAC;AACL,CAAC;AAED,SAAS,sBAAsB,CAC3B,IAAyC,EACzC,KAA0C;IAE1C,IAAI,IAAI,KAAK,SAAS,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;QAC5C,OAAO,SAAS,CAAC;IACrB,CAAC;IAED,MAAM,QAAQ,GAA4B;QACtC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC;QACf,GAAG,CAAC,KAAK,IAAI,EAAE,CAAC;KACnB,CAAC;IACF,MAAM,oBAAoB,GAAG;QACzB,GAAG,eAAe,CAAC,IAAI,EAAE,oBAAoB,CAAC;QAC9C,GAAG,eAAe,CAAC,KAAK,EAAE,oBAAoB,CAAC;KAClD,CAAC;IAEF,IAAI,oBAAoB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAClC,QAAQ,CAAC,oBAAoB,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,oBAAoB,CAAC,CAAC,CAAC;IACvE,CAAC;IAED,OAAO,QAAQ,CAAC;AACpB,CAAC;AAED,SAAS,eAAe,CAAC,KAAc;IACnC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACxB,OAAO,EAAE,CAAC;IACd,CAAC;IAED,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAkB,EAAE,CAAC,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC;AAC5E,CAAC;AAED,SAAS,2BAA2B,CAAC,KAAyB,EAAE,QAAgB;IAC5E,IAAI,KAAK,KAAK,SAAS,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;QAC9D,OAAO,QAAQ,CAAC;IACpB,CAAC;IAED,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;AAC7B,CAAC;AAED,SAAS,gCAAgC,CAAC,KAAyB;IAC/D,IAAI,KAAK,KAAK,SAAS,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,CAAC,EAAE,CAAC;QAC/D,OAAO,SAAS,CAAC;IACrB,CAAC;IAED,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;AAC7B,CAAC;AAED,SAAS,eAAe,CACpB,MAAS,EACT,GAAM,EACN,KAAuB;IAEvB,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;QACtB,MAAM,CAAC,GAAG,CAAC,GAAG,KAAK,CAAC;IACxB,CAAC;AACL,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"in-memory-keyword-store.d.ts","sourceRoot":"","sources":["../../../src/rag/stores/in-memory-keyword-store.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,KAAK,EACR,YAAY,EACZ,cAAc,EACd,aAAa,EAChB,MAAM,SAAS,CAAC;
|
|
1
|
+
{"version":3,"file":"in-memory-keyword-store.d.ts","sourceRoot":"","sources":["../../../src/rag/stores/in-memory-keyword-store.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,KAAK,EACR,YAAY,EACZ,cAAc,EACd,aAAa,EAChB,MAAM,SAAS,CAAC;AAiBjB,qBAAa,oBAAqB,YAAW,YAAY;IACrD,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAwC;IAE1D,MAAM,CAAC,MAAM,EAAE,KAAK,EAAE,GAAG,OAAO,CAAC,IAAI,CAAC;IAWtC,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,aAAkB,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;IAuC7E,gBAAgB,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAQzD,OAAO,CAAC,0BAA0B;CAerC"}
|
|
@@ -2,11 +2,12 @@
|
|
|
2
2
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
3
|
exports.InMemoryKeywordStore = void 0;
|
|
4
4
|
const utils_1 = require("./utils");
|
|
5
|
+
const keyword_tokenizer_1 = require("./keyword-tokenizer");
|
|
5
6
|
class InMemoryKeywordStore {
|
|
6
7
|
entries = new Map();
|
|
7
8
|
async upsert(chunks) {
|
|
8
9
|
for (const chunk of chunks) {
|
|
9
|
-
const terms =
|
|
10
|
+
const terms = (0, keyword_tokenizer_1.tokenizeKeywordText)((0, keyword_tokenizer_1.createKeywordIndexText)(chunk));
|
|
10
11
|
this.entries.set(chunk.id, {
|
|
11
12
|
chunk: (0, utils_1.cloneChunk)(chunk),
|
|
12
13
|
termCounts: countTerms(terms),
|
|
@@ -15,7 +16,7 @@ class InMemoryKeywordStore {
|
|
|
15
16
|
}
|
|
16
17
|
}
|
|
17
18
|
async search(query, options = {}) {
|
|
18
|
-
const queryTerms = [...new Set(
|
|
19
|
+
const queryTerms = [...new Set((0, keyword_tokenizer_1.tokenizeKeywordText)(query))];
|
|
19
20
|
if (queryTerms.length === 0) {
|
|
20
21
|
return [];
|
|
21
22
|
}
|
|
@@ -83,12 +84,6 @@ function scoreEntry(input) {
|
|
|
83
84
|
}
|
|
84
85
|
return score;
|
|
85
86
|
}
|
|
86
|
-
function tokenize(text) {
|
|
87
|
-
return text
|
|
88
|
-
.normalize('NFKC')
|
|
89
|
-
.toLowerCase()
|
|
90
|
-
.match(/[\p{L}\p{N}_-]+/gu) ?? [];
|
|
91
|
-
}
|
|
92
87
|
function countTerms(terms) {
|
|
93
88
|
const counts = new Map();
|
|
94
89
|
for (const term of terms) {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"in-memory-keyword-store.js","sourceRoot":"","sources":["../../../src/rag/stores/in-memory-keyword-store.ts"],"names":[],"mappings":";;;AAMA,mCAIiB;
|
|
1
|
+
{"version":3,"file":"in-memory-keyword-store.js","sourceRoot":"","sources":["../../../src/rag/stores/in-memory-keyword-store.ts"],"names":[],"mappings":";;;AAMA,mCAIiB;AACjB,2DAG6B;AAQ7B,MAAa,oBAAoB;IACZ,OAAO,GAAG,IAAI,GAAG,EAA6B,CAAC;IAEhE,KAAK,CAAC,MAAM,CAAC,MAAe;QACxB,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;YACzB,MAAM,KAAK,GAAG,IAAA,uCAAmB,EAAC,IAAA,0CAAsB,EAAC,KAAK,CAAC,CAAC,CAAC;YACjE,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,EAAE;gBACvB,KAAK,EAAE,IAAA,kBAAU,EAAC,KAAK,CAAC;gBACxB,UAAU,EAAE,UAAU,CAAC,KAAK,CAAC;gBAC7B,MAAM,EAAE,KAAK,CAAC,MAAM;aACvB,CAAC,CAAC;QACP,CAAC;IACL,CAAC;IAED,KAAK,CAAC,MAAM,CAAC,KAAa,EAAE,UAAyB,EAAE;QACnD,MAAM,UAAU,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,IAAA,uCAAmB,EAAC,KAAK,CAAC,CAAC,CAAC,CAAC;QAC5D,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC1B,OAAO,EAAE,CAAC;QACd,CAAC;QAED,MAAM,IAAI,GAAqB,EAAE,CAAC;QAClC,MAAM,iBAAiB,GAAG,IAAI,CAAC,0BAA0B,CAAC,UAAU,CAAC,CAAC;QACtE,MAAM,cAAc,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;QAEtD,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC;YACxC,IAAI,CAAC,IAAA,4BAAoB,EAAC,KAAK,CAAC,KAAK,EAAE,OAAO,CAAC,EAAE,CAAC;gBAC9C,SAAS;YACb,CAAC;YAED,MAAM,KAAK,GAAG,UAAU,CAAC;gBACrB,KAAK;gBACL,UAAU;gBACV,iBAAiB;gBACjB,cAAc;aACjB,CAAC,CAAC;YACH,IAAI,KAAK,IAAI,CAAC,EAAE,CAAC;gBACb,SAAS;YACb,CAAC;YAED,IAAI,CAAC,IAAI,CAAC;gBACN,OAAO,EAAE,KAAK,CAAC,KAAK,CAAC,EAAE;gBACvB,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,UAAU;gBAClC,KAAK;gBACL,QAAQ,EAAE;oBACN,MAAM,EAAE,SAAS;oBACjB,YAAY,EAAE,UAAU,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;iBACxE;aACJ,CAAC,CAAC;QACP,CAAC;QAED,OAAO,IAAA,yBAAiB,EAAC,IAAI,EAAE,OAAO,CAAC,CAAC;IAC5C,CAAC;IAED,KAAK,CAAC,gBAAgB,CAAC,UAAkB;QACrC,KAAK,MAAM,CAAC,OAAO,EAAE,KAAK,CAAC,IAAI,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC;YACpD,IAAI,KAAK,CAAC,KAAK,CAAC,UAAU,KAAK,UAAU,EAAE,CAAC;gBACxC,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;YACjC,CAAC;QACL,CAAC;IACL,CAAC;IAEO,0BAA0B,CAAC,UAAoB;QACnD,MAAM,SAAS,GAAG,IAAI,GAAG,EAAkB,CAAC;QAE5C,KAAK,MAAM,IAAI,IAAI,UAAU,EAAE,CAAC;YAC5B,IAAI,KAAK,GAAG,CAAC,CAAC;YACd,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC;gBACxC,IAAI,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC7B,KAAK,IAAI,CAAC,CAAC;gBACf,CAAC;YACL,CAAC;YACD,SAAS,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;QAC/B,CAAC;QAED,OAAO,SAAS,CAAC;IACrB,CAAC;CACJ;AA5ED,oDA4EC;AASD,SAAS,UAAU,CAAC,KAAsB;IACtC,IAAI,KAAK,GAAG,CAAC,CAAC;IAEd,KAAK,MAAM,IAAI,IAAI,KAAK,CAAC,UAAU,EAAE,CAAC;QAClC,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACxD,IAAI,SAAS,KAAK,CAAC,EAAE,CAAC;YAClB,SAAS;QACb,CAAC;QAED,MAAM,EAAE,GAAG,KAAK,CAAC,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAClD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,cAAc,GAAG,EAAE,GAAG,GAAG,CAAC,GAAG,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC;QACzE,MAAM,YAAY,GAAG,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,CAAC;QAC5E,KAAK,IAAI,YAAY,GAAG,GAAG,CAAC;IAChC,CAAC;IAED,OAAO,KAAK,CAAC;AACjB,CAAC;AAED,SAAS,UAAU,CAAC,KAAe;IAC/B,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IAEzC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACvB,MAAM,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;IAClD,CAAC;IAED,OAAO,MAAM,CAAC;AAClB,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"keyword-tokenizer.d.ts","sourceRoot":"","sources":["../../../src/rag/stores/keyword-tokenizer.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,UAAU,CAAC;AAKtC,wBAAgB,sBAAsB,CAAC,KAAK,EAAE,KAAK,GAAG,MAAM,CAQ3D;AAED,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAS1D"}
|
|
@@ -0,0 +1,113 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
|
+
exports.createKeywordIndexText = createKeywordIndexText;
|
|
4
|
+
exports.tokenizeKeywordText = tokenizeKeywordText;
|
|
5
|
+
const RAW_TOKEN_PATTERN = /[\p{L}\p{N}_-]+/gu;
|
|
6
|
+
const CJK_CHARACTER_PATTERN = /[\u3400-\u4DBF\u4E00-\u9FFF\uF900-\uFAFF]/u;
|
|
7
|
+
function createKeywordIndexText(chunk) {
|
|
8
|
+
return [
|
|
9
|
+
chunk.metadata.title,
|
|
10
|
+
chunk.metadata.headingPath?.join(' '),
|
|
11
|
+
chunk.content,
|
|
12
|
+
]
|
|
13
|
+
.filter((part) => part !== undefined && part.trim().length > 0)
|
|
14
|
+
.join('\n');
|
|
15
|
+
}
|
|
16
|
+
function tokenizeKeywordText(text) {
|
|
17
|
+
const rawTokens = text.normalize('NFKC').match(RAW_TOKEN_PATTERN) ?? [];
|
|
18
|
+
const terms = [];
|
|
19
|
+
for (const rawToken of rawTokens) {
|
|
20
|
+
terms.push(...createTokenTerms(rawToken));
|
|
21
|
+
}
|
|
22
|
+
return terms;
|
|
23
|
+
}
|
|
24
|
+
function createTokenTerms(rawToken) {
|
|
25
|
+
const terms = new Set();
|
|
26
|
+
addTerm(terms, rawToken);
|
|
27
|
+
for (const part of splitMixedToken(rawToken)) {
|
|
28
|
+
addTerm(terms, part.value);
|
|
29
|
+
if (part.kind === 'cjk') {
|
|
30
|
+
addCjkNgrams(terms, part.value);
|
|
31
|
+
}
|
|
32
|
+
else {
|
|
33
|
+
addIdentifierTerms(terms, part.value);
|
|
34
|
+
}
|
|
35
|
+
}
|
|
36
|
+
return [...terms];
|
|
37
|
+
}
|
|
38
|
+
function splitMixedToken(token) {
|
|
39
|
+
const parts = [];
|
|
40
|
+
let current = '';
|
|
41
|
+
let currentKind;
|
|
42
|
+
for (const character of Array.from(token)) {
|
|
43
|
+
const kind = isCjkCharacter(character) ? 'cjk' : 'identifier';
|
|
44
|
+
if (currentKind !== undefined && currentKind !== kind) {
|
|
45
|
+
parts.push({
|
|
46
|
+
value: current,
|
|
47
|
+
kind: currentKind,
|
|
48
|
+
});
|
|
49
|
+
current = '';
|
|
50
|
+
}
|
|
51
|
+
current += character;
|
|
52
|
+
currentKind = kind;
|
|
53
|
+
}
|
|
54
|
+
if (current.length > 0 && currentKind !== undefined) {
|
|
55
|
+
parts.push({
|
|
56
|
+
value: current,
|
|
57
|
+
kind: currentKind,
|
|
58
|
+
});
|
|
59
|
+
}
|
|
60
|
+
return parts;
|
|
61
|
+
}
|
|
62
|
+
function addIdentifierTerms(terms, value) {
|
|
63
|
+
const separatorParts = value
|
|
64
|
+
.split(/[_-]+/u)
|
|
65
|
+
.filter((part) => part.length > 0);
|
|
66
|
+
for (const part of separatorParts) {
|
|
67
|
+
addTerm(terms, part);
|
|
68
|
+
addCaseSplitTerms(terms, part);
|
|
69
|
+
}
|
|
70
|
+
}
|
|
71
|
+
function addCaseSplitTerms(terms, value) {
|
|
72
|
+
const parts = splitIdentifierCase(value);
|
|
73
|
+
if (parts.length <= 1) {
|
|
74
|
+
return;
|
|
75
|
+
}
|
|
76
|
+
for (const part of parts) {
|
|
77
|
+
addTerm(terms, part);
|
|
78
|
+
}
|
|
79
|
+
for (let index = 0; index < parts.length - 1; index += 1) {
|
|
80
|
+
const current = parts[index];
|
|
81
|
+
const next = parts[index + 1];
|
|
82
|
+
if (current !== undefined && next !== undefined && isAcronym(next)) {
|
|
83
|
+
addTerm(terms, `${current}${next}`);
|
|
84
|
+
}
|
|
85
|
+
}
|
|
86
|
+
}
|
|
87
|
+
function splitIdentifierCase(value) {
|
|
88
|
+
return value.match(/[A-Z]?[a-z]+|[A-Z]+(?![a-z])|\d+/g) ?? [value];
|
|
89
|
+
}
|
|
90
|
+
function addCjkNgrams(terms, value) {
|
|
91
|
+
const characters = Array.from(value);
|
|
92
|
+
for (const size of [2, 3]) {
|
|
93
|
+
if (characters.length < size) {
|
|
94
|
+
continue;
|
|
95
|
+
}
|
|
96
|
+
for (let index = 0; index <= characters.length - size; index += 1) {
|
|
97
|
+
addTerm(terms, characters.slice(index, index + size).join(''));
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
}
|
|
101
|
+
function addTerm(terms, value) {
|
|
102
|
+
const normalized = value.toLowerCase().trim();
|
|
103
|
+
if (normalized.length > 0) {
|
|
104
|
+
terms.add(normalized);
|
|
105
|
+
}
|
|
106
|
+
}
|
|
107
|
+
function isCjkCharacter(character) {
|
|
108
|
+
return CJK_CHARACTER_PATTERN.test(character);
|
|
109
|
+
}
|
|
110
|
+
function isAcronym(value) {
|
|
111
|
+
return /^[A-Z0-9]{2,}$/u.test(value);
|
|
112
|
+
}
|
|
113
|
+
//# sourceMappingURL=keyword-tokenizer.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"keyword-tokenizer.js","sourceRoot":"","sources":["../../../src/rag/stores/keyword-tokenizer.ts"],"names":[],"mappings":";;AAKA,wDAQC;AAED,kDASC;AAtBD,MAAM,iBAAiB,GAAG,mBAAmB,CAAC;AAC9C,MAAM,qBAAqB,GAAG,4CAA4C,CAAC;AAE3E,SAAgB,sBAAsB,CAAC,KAAY;IAC/C,OAAO;QACH,KAAK,CAAC,QAAQ,CAAC,KAAK;QACpB,KAAK,CAAC,QAAQ,CAAC,WAAW,EAAE,IAAI,CAAC,GAAG,CAAC;QACrC,KAAK,CAAC,OAAO;KAChB;SACI,MAAM,CAAC,CAAC,IAAI,EAAkB,EAAE,CAAC,IAAI,KAAK,SAAS,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC;SAC9E,IAAI,CAAC,IAAI,CAAC,CAAC;AACpB,CAAC;AAED,SAAgB,mBAAmB,CAAC,IAAY;IAC5C,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,KAAK,CAAC,iBAAiB,CAAC,IAAI,EAAE,CAAC;IACxE,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;QAC/B,KAAK,CAAC,IAAI,CAAC,GAAG,gBAAgB,CAAC,QAAQ,CAAC,CAAC,CAAC;IAC9C,CAAC;IAED,OAAO,KAAK,CAAC;AACjB,CAAC;AAED,SAAS,gBAAgB,CAAC,QAAgB;IACtC,MAAM,KAAK,GAAG,IAAI,GAAG,EAAU,CAAC;IAEhC,OAAO,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC;IAEzB,KAAK,MAAM,IAAI,IAAI,eAAe,CAAC,QAAQ,CAAC,EAAE,CAAC;QAC3C,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;QAE3B,IAAI,IAAI,CAAC,IAAI,KAAK,KAAK,EAAE,CAAC;YACtB,YAAY,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;QACpC,CAAC;aAAM,CAAC;YACJ,kBAAkB,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;QAC1C,CAAC;IACL,CAAC;IAED,OAAO,CAAC,GAAG,KAAK,CAAC,CAAC;AACtB,CAAC;AAED,SAAS,eAAe,CAAC,KAAa;IAClC,MAAM,KAAK,GAAyD,EAAE,CAAC;IACvE,IAAI,OAAO,GAAG,EAAE,CAAC;IACjB,IAAI,WAA6C,CAAC;IAElD,KAAK,MAAM,SAAS,IAAI,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QACxC,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,YAAY,CAAC;QAC9D,IAAI,WAAW,KAAK,SAAS,IAAI,WAAW,KAAK,IAAI,EAAE,CAAC;YACpD,KAAK,CAAC,IAAI,CAAC;gBACP,KAAK,EAAE,OAAO;gBACd,IAAI,EAAE,WAAW;aACpB,CAAC,CAAC;YACH,OAAO,GAAG,EAAE,CAAC;QACjB,CAAC;QAED,OAAO,IAAI,SAAS,CAAC;QACrB,WAAW,GAAG,IAAI,CAAC;IACvB,CAAC;IAED,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,WAAW,KAAK,SAAS,EAAE,CAAC;QAClD,KAAK,CAAC,IAAI,CAAC;YACP,KAAK,EAAE,OAAO;YACd,IAAI,EAAE,WAAW;SACpB,CAAC,CAAC;IACP,CAAC;IAED,OAAO,KAAK,CAAC;AACjB,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAkB,EAAE,KAAa;IACzD,MAAM,cAAc,GAAG,KAAK;SACvB,KAAK,CAAC,QAAQ,CAAC;SACf,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAEvC,KAAK,MAAM,IAAI,IAAI,cAAc,EAAE,CAAC;QAChC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC;QACrB,iBAAiB,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC;IACnC,CAAC;AACL,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAkB,EAAE,KAAa;IACxD,MAAM,KAAK,GAAG,mBAAmB,CAAC,KAAK,CAAC,CAAC;IACzC,IAAI,KAAK,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QACpB,OAAO;IACX,CAAC;IAED,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACvB,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC;IACzB,CAAC;IAED,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;QACvD,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC;QAC7B,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;QAC9B,IAAI,OAAO,KAAK,SAAS,IAAI,IAAI,KAAK,SAAS,IAAI,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC;YACjE,OAAO,CAAC,KAAK,EAAE,GAAG,OAAO,GAAG,IAAI,EAAE,CAAC,CAAC;QACxC,CAAC;IACL,CAAC;AACL,CAAC;AAED,SAAS,mBAAmB,CAAC,KAAa;IACtC,OAAO,KAAK,CAAC,KAAK,CAAC,mCAAmC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;AACvE,CAAC;AAED,SAAS,YAAY,CAAC,KAAkB,EAAE,KAAa;IACnD,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAErC,KAAK,MAAM,IAAI,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QACxB,IAAI,UAAU,CAAC,MAAM,GAAG,IAAI,EAAE,CAAC;YAC3B,SAAS;QACb,CAAC;QAED,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,IAAI,UAAU,CAAC,MAAM,GAAG,IAAI,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;YAChE,OAAO,CAAC,KAAK,EAAE,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,GAAG,IAAI,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QACnE,CAAC;IACL,CAAC;AACL,CAAC;AAED,SAAS,OAAO,CAAC,KAAkB,EAAE,KAAa;IAC9C,MAAM,UAAU,GAAG,KAAK,CAAC,WAAW,EAAE,CAAC,IAAI,EAAE,CAAC;IAC9C,IAAI,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACxB,KAAK,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;IAC1B,CAAC;AACL,CAAC;AAED,SAAS,cAAc,CAAC,SAAiB;IACrC,OAAO,qBAAqB,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;AACjD,CAAC;AAED,SAAS,SAAS,CAAC,KAAa;IAC5B,OAAO,iBAAiB,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;AACzC,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"pg-vector-store.d.ts","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/pg-vector-store.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EACR,aAAa,EAChB,MAAM,aAAa,CAAC;AACrB,OAAO,KAAK,EACR,cAAc,EACd,aAAa,EACb,WAAW,EACd,MAAM,UAAU,CAAC;
|
|
1
|
+
{"version":3,"file":"pg-vector-store.d.ts","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/pg-vector-store.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EACR,aAAa,EAChB,MAAM,aAAa,CAAC;AACrB,OAAO,KAAK,EACR,cAAc,EACd,aAAa,EACb,WAAW,EACd,MAAM,UAAU,CAAC;AAUlB,OAAO,KAAK,EAER,uBAAuB,EAE1B,MAAM,SAAS,CAAC;AAEjB,MAAM,WAAW,oBAAqB,SAAQ,uBAAuB;IACjE,UAAU,EAAE,MAAM,CAAC;CACtB;AAED,qBAAa,aAAc,YAAW,WAAW;IAC7C,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAwB;IAC3C,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAqB;gBAEhC,OAAO,EAAE,oBAAoB;IAMnC,MAAM,CAAC,KAAK,EAAE,aAAa,EAAE,GAAG,OAAO,CAAC,IAAI,CAAC;IAmC7C,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,EAAE,OAAO,GAAE,aAAkB,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;IAoDhF,gBAAgB,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;CAM5D"}
|
|
@@ -13,23 +13,29 @@ class PgVectorStore {
|
|
|
13
13
|
this.dimensions = (0, embeddings_1.assertValidEmbeddingDimensions)(options.dimensions);
|
|
14
14
|
}
|
|
15
15
|
async upsert(items) {
|
|
16
|
+
// 先整体校验维度再分批写入,避免批次中途失败留下半写状态。
|
|
16
17
|
for (const item of items) {
|
|
17
18
|
(0, embeddings_1.assertEmbeddingDimensions)(item.embedding, this.dimensions, `chunk ${item.chunk.id} embedding`);
|
|
19
|
+
}
|
|
20
|
+
for (const batch of (0, sql_1.chunkBatches)((0, sql_1.dedupeByKey)(items, (item) => item.chunk.id))) {
|
|
18
21
|
await this.db.query(`
|
|
19
22
|
INSERT INTO ${this.tables.embeddings} (
|
|
20
23
|
chunk_id, document_id, embedding, updated_at
|
|
21
|
-
) VALUES
|
|
22
|
-
|
|
23
|
-
|
|
24
|
+
) VALUES
|
|
25
|
+
${(0, sql_1.createMultiRowValuesSql)({
|
|
26
|
+
rowCount: batch.length,
|
|
27
|
+
casts: ['', '', '::vector'],
|
|
28
|
+
rowSuffix: ', now()',
|
|
29
|
+
})}
|
|
24
30
|
ON CONFLICT (chunk_id) DO UPDATE SET
|
|
25
31
|
document_id = EXCLUDED.document_id,
|
|
26
32
|
embedding = EXCLUDED.embedding,
|
|
27
33
|
updated_at = now()
|
|
28
|
-
`.trim(), [
|
|
34
|
+
`.trim(), batch.flatMap((item) => [
|
|
29
35
|
item.chunk.id,
|
|
30
36
|
item.chunk.documentId,
|
|
31
37
|
(0, sql_1.toVectorLiteral)(item.embedding),
|
|
32
|
-
]);
|
|
38
|
+
]));
|
|
33
39
|
}
|
|
34
40
|
}
|
|
35
41
|
async search(vector, options = {}) {
|
|
@@ -43,6 +49,9 @@ ON CONFLICT (chunk_id) DO UPDATE SET
|
|
|
43
49
|
? ''
|
|
44
50
|
: `${where.clause.length === 0 ? 'WHERE' : 'AND'} 1 - (e.embedding <=> $1::vector) >= $${where.values.length + 2}`;
|
|
45
51
|
const limitPlaceholder = `$${where.values.length + (options.minScore === undefined ? 2 : 3)}`;
|
|
52
|
+
// ORDER BY 只保留向量距离表达式:一旦追加 document_id / chunk_id 等次级排序键,
|
|
53
|
+
// planner 就无法走 HNSW 索引,会退化成全表扫描。
|
|
54
|
+
// 确定性 tie-break(同分按 documentId/chunkId)挪到 Node 侧对返回的 topK 结果做稳定排序。
|
|
46
55
|
const result = await this.db.query(`
|
|
47
56
|
SELECT
|
|
48
57
|
e.chunk_id,
|
|
@@ -52,7 +61,7 @@ FROM ${this.tables.embeddings} e
|
|
|
52
61
|
JOIN ${this.tables.chunks} c ON c.id = e.chunk_id
|
|
53
62
|
${where.clause}
|
|
54
63
|
${minScoreClause}
|
|
55
|
-
ORDER BY e.embedding <=> $1::vector ASC
|
|
64
|
+
ORDER BY e.embedding <=> $1::vector ASC
|
|
56
65
|
LIMIT ${limitPlaceholder}
|
|
57
66
|
`.trim(), [
|
|
58
67
|
(0, sql_1.toVectorLiteral)(vector),
|
|
@@ -60,14 +69,18 @@ LIMIT ${limitPlaceholder}
|
|
|
60
69
|
...(options.minScore === undefined ? [] : [options.minScore]),
|
|
61
70
|
topK,
|
|
62
71
|
]);
|
|
63
|
-
return result.rows
|
|
72
|
+
return result.rows
|
|
73
|
+
.map((row) => ({
|
|
64
74
|
chunkId: String(row.chunk_id),
|
|
65
75
|
documentId: String(row.document_id),
|
|
66
76
|
score: Number(row.score ?? 0),
|
|
67
77
|
metadata: {
|
|
68
78
|
source: 'vector',
|
|
69
79
|
},
|
|
70
|
-
}))
|
|
80
|
+
}))
|
|
81
|
+
.sort((left, right) => (right.score - left.score
|
|
82
|
+
|| left.documentId.localeCompare(right.documentId)
|
|
83
|
+
|| left.chunkId.localeCompare(right.chunkId)));
|
|
71
84
|
}
|
|
72
85
|
async deleteByDocument(documentId) {
|
|
73
86
|
await this.db.query(`DELETE FROM ${this.tables.embeddings} WHERE document_id = $1`, [documentId]);
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"pg-vector-store.js","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/pg-vector-store.ts"],"names":[],"mappings":";;;AAAA,iDAG0B;AAS1B,+
|
|
1
|
+
{"version":3,"file":"pg-vector-store.js","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/pg-vector-store.ts"],"names":[],"mappings":";;;AAAA,iDAG0B;AAS1B,+BAQe;AAWf,MAAa,aAAa;IACb,UAAU,CAAS;IACX,EAAE,CAAwB;IAC1B,MAAM,CAAqB;IAE5C,YAAY,OAA6B;QACrC,IAAI,CAAC,EAAE,GAAG,OAAO,CAAC,EAAE,CAAC;QACrB,IAAI,CAAC,MAAM,GAAG,IAAA,+BAAyB,EAAC,OAAO,CAAC,WAAW,CAAC,CAAC;QAC7D,IAAI,CAAC,UAAU,GAAG,IAAA,2CAA8B,EAAC,OAAO,CAAC,UAAU,CAAC,CAAC;IACzE,CAAC;IAED,KAAK,CAAC,MAAM,CAAC,KAAsB;QAC/B,+BAA+B;QAC/B,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACvB,IAAA,sCAAyB,EACrB,IAAI,CAAC,SAAS,EACd,IAAI,CAAC,UAAU,EACf,SAAS,IAAI,CAAC,KAAK,CAAC,EAAE,YAAY,CACrC,CAAC;QACN,CAAC;QAED,KAAK,MAAM,KAAK,IAAI,IAAA,kBAAY,EAAC,IAAA,iBAAW,EAAC,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;YAC5E,MAAM,IAAI,CAAC,EAAE,CAAC,KAAK,CACf;cACF,IAAI,CAAC,MAAM,CAAC,UAAU;;;EAGlC,IAAA,6BAAuB,EAAC;gBACtB,QAAQ,EAAE,KAAK,CAAC,MAAM;gBACtB,KAAK,EAAE,CAAC,EAAE,EAAE,EAAE,EAAE,UAAU,CAAC;gBAC3B,SAAS,EAAE,SAAS;aACvB,CAAC;;;;;CAKD,CAAC,IAAI,EAAE,EACQ,KAAK,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC;gBACpB,IAAI,CAAC,KAAK,CAAC,EAAE;gBACb,IAAI,CAAC,KAAK,CAAC,UAAU;gBACrB,IAAA,qBAAe,EAAC,IAAI,CAAC,SAAS,CAAC;aAClC,CAAC,CACL,CAAC;QACN,CAAC;IACL,CAAC;IAED,KAAK,CAAC,MAAM,CAAC,MAAgB,EAAE,UAAyB,EAAE;QACtD,IAAA,sCAAyB,EAAC,MAAM,EAAE,IAAI,CAAC,UAAU,EAAE,iBAAiB,CAAC,CAAC;QACtE,MAAM,IAAI,GAAG,IAAA,mBAAa,EAAC,OAAO,CAAC,IAAI,CAAC,CAAC;QACzC,IAAI,IAAI,KAAK,CAAC,EAAE,CAAC;YACb,OAAO,EAAE,CAAC;QACd,CAAC;QAED,MAAM,KAAK,GAAG,IAAA,2BAAqB,EAAC,OAAO,EAAE,CAAC,EAAE,GAAG,CAAC,CAAC;QACrD,MAAM,cAAc,GAAG,OAAO,CAAC,QAAQ,KAAK,SAAS;YACjD,CAAC,CAAC,EAAE;YACJ,CAAC,CAAC,GAAG,KAAK,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,yCAAyC,KAAK,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACvH,MAAM,gBAAgB,GAAG,IAAI,KAAK,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,OAAO,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QAC9F,0DAA0D;QAC1D,iCAAiC;QACjC,mEAAmE;QACnE,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,EAAE,CAAC,KAAK,CAC9B;;;;;OAKL,IAAI,CAAC,MAAM,CAAC,UAAU;OACtB,IAAI,CAAC,MAAM,CAAC,MAAM;EACvB,KAAK,CAAC,MAAM;EACZ,cAAc;;QAER,gBAAgB;CACvB,CAAC,IAAI,EAAE,EACI;YACI,IAAA,qBAAe,EAAC,MAAM,CAAC;YACvB,GAAG,KAAK,CAAC,MAAM;YACf,GAAG,CAAC,OAAO,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;YAC7D,IAAI;SACP,CACJ,CAAC;QAEF,OAAO,MAAM,CAAC,IAAI;aACb,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;YACX,OAAO,EAAE,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC;YAC7B,UAAU,EAAE,MAAM,CAAC,GAAG,CAAC,WAAW,CAAC;YACnC,KAAK,EAAE,MAAM,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,CAAC;YAC7B,QAAQ,EAAE;gBACN,MAAM,EAAE,QAAQ;aACnB;SACJ,CAAC,CAAC;aACF,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,CACnB,KAAK,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK;eACrB,IAAI,CAAC,UAAU,CAAC,aAAa,CAAC,KAAK,CAAC,UAAU,CAAC;eAC/C,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,KAAK,CAAC,OAAO,CAAC,CAC/C,CAAC,CAAC;IACX,CAAC;IAED,KAAK,CAAC,gBAAgB,CAAC,UAAkB;QACrC,MAAM,IAAI,CAAC,EAAE,CAAC,KAAK,CACf,eAAe,IAAI,CAAC,MAAM,CAAC,UAAU,yBAAyB,EAC9D,CAAC,UAAU,CAAC,CACf,CAAC;IACN,CAAC;CACJ;AAxGD,sCAwGC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"postgres-document-store.d.ts","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/postgres-document-store.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACR,KAAK,EAIL,WAAW,EACd,MAAM,aAAa,CAAC;AACrB,OAAO,KAAK,EACR,aAAa,EAChB,MAAM,UAAU,CAAC;
|
|
1
|
+
{"version":3,"file":"postgres-document-store.d.ts","sourceRoot":"","sources":["../../../../src/rag/stores/postgres/postgres-document-store.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACR,KAAK,EAIL,WAAW,EACd,MAAM,aAAa,CAAC;AACrB,OAAO,KAAK,EACR,aAAa,EAChB,MAAM,UAAU,CAAC;AAelB,OAAO,KAAK,EAER,uBAAuB,EAE1B,MAAM,SAAS,CAAC;AAWjB,qBAAa,qBAAsB,YAAW,aAAa;IACvD,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAwB;IAC3C,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAqB;gBAEhC,OAAO,EAAE,uBAAuB;IAKtC,eAAe,CAAC,SAAS,EAAE,WAAW,EAAE,GAAG,OAAO,CAAC,IAAI,CAAC;IAiDxD,YAAY,CAAC,MAAM,EAAE,KAAK,EAAE,GAAG,OAAO,CAAC,IAAI,CAAC;IAwD5C,SAAS,CAAC,GAAG,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAoB1C,mBAAmB,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAczD,cAAc,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAOjD,WAAW,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,GAAG,SAAS,CAAC;CAS1E"}
|
|
@@ -2,6 +2,14 @@
|
|
|
2
2
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
3
|
exports.PostgresDocumentStore = void 0;
|
|
4
4
|
const sql_1 = require("./sql");
|
|
5
|
+
// 逐行 INSERT 在大批量入库时网络往返开销是主要瓶颈,
|
|
6
|
+
// 这里统一走 multi-row VALUES 批量插入,ON CONFLICT 语义与逐行版本一致。
|
|
7
|
+
const DOCUMENT_COLUMN_CASTS = [
|
|
8
|
+
'', '', '::jsonb', '::jsonb', '', '', '', '', '', '::text[]', '', '', '', '',
|
|
9
|
+
];
|
|
10
|
+
const CHUNK_COLUMN_CASTS = [
|
|
11
|
+
'', '', '', '', '', '::jsonb', '', '', '', '', '::text[]', '', '', '', '', '::text[]', '::jsonb',
|
|
12
|
+
];
|
|
5
13
|
class PostgresDocumentStore {
|
|
6
14
|
db;
|
|
7
15
|
tables;
|
|
@@ -10,14 +18,17 @@ class PostgresDocumentStore {
|
|
|
10
18
|
this.tables = (0, sql_1.resolvePostgresTableNames)(options.tablePrefix);
|
|
11
19
|
}
|
|
12
20
|
async upsertDocuments(documents) {
|
|
13
|
-
for (const
|
|
21
|
+
for (const batch of (0, sql_1.chunkBatches)((0, sql_1.dedupeByKey)(documents, (document) => document.id))) {
|
|
14
22
|
await this.db.query(`
|
|
15
23
|
INSERT INTO ${this.tables.documents} (
|
|
16
24
|
id, content, metadata, blocks, source, title, mime_type, tenant_id, knowledge_base_id,
|
|
17
25
|
acl, version, checksum, created_at_meta, updated_at_meta, updated_at
|
|
18
|
-
) VALUES
|
|
19
|
-
|
|
20
|
-
|
|
26
|
+
) VALUES
|
|
27
|
+
${(0, sql_1.createMultiRowValuesSql)({
|
|
28
|
+
rowCount: batch.length,
|
|
29
|
+
casts: DOCUMENT_COLUMN_CASTS,
|
|
30
|
+
rowSuffix: ', now()',
|
|
31
|
+
})}
|
|
21
32
|
ON CONFLICT (id) DO UPDATE SET
|
|
22
33
|
content = EXCLUDED.content,
|
|
23
34
|
metadata = EXCLUDED.metadata,
|
|
@@ -33,7 +44,7 @@ ON CONFLICT (id) DO UPDATE SET
|
|
|
33
44
|
created_at_meta = EXCLUDED.created_at_meta,
|
|
34
45
|
updated_at_meta = EXCLUDED.updated_at_meta,
|
|
35
46
|
updated_at = now()
|
|
36
|
-
`.trim(), [
|
|
47
|
+
`.trim(), batch.flatMap((document) => [
|
|
37
48
|
document.id,
|
|
38
49
|
document.content,
|
|
39
50
|
(0, sql_1.createJson)(document.metadata),
|
|
@@ -48,20 +59,22 @@ ON CONFLICT (id) DO UPDATE SET
|
|
|
48
59
|
document.metadata.checksum ?? null,
|
|
49
60
|
document.metadata.createdAt ?? null,
|
|
50
61
|
document.metadata.updatedAt ?? null,
|
|
51
|
-
]);
|
|
62
|
+
]));
|
|
52
63
|
}
|
|
53
64
|
}
|
|
54
65
|
async upsertChunks(chunks) {
|
|
55
|
-
for (const
|
|
66
|
+
for (const batch of (0, sql_1.chunkBatches)((0, sql_1.dedupeByKey)(chunks, (chunk) => chunk.id))) {
|
|
56
67
|
await this.db.query(`
|
|
57
68
|
INSERT INTO ${this.tables.chunks} (
|
|
58
69
|
id, document_id, parent_id, content, kind, metadata, source, title, tenant_id,
|
|
59
70
|
knowledge_base_id, heading_path, page, start_offset, end_offset, chunk_index, acl, extra,
|
|
60
71
|
updated_at
|
|
61
|
-
) VALUES
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
72
|
+
) VALUES
|
|
73
|
+
${(0, sql_1.createMultiRowValuesSql)({
|
|
74
|
+
rowCount: batch.length,
|
|
75
|
+
casts: CHUNK_COLUMN_CASTS,
|
|
76
|
+
rowSuffix: ', now()',
|
|
77
|
+
})}
|
|
65
78
|
ON CONFLICT (id) DO UPDATE SET
|
|
66
79
|
document_id = EXCLUDED.document_id,
|
|
67
80
|
parent_id = EXCLUDED.parent_id,
|
|
@@ -80,7 +93,7 @@ ON CONFLICT (id) DO UPDATE SET
|
|
|
80
93
|
acl = EXCLUDED.acl,
|
|
81
94
|
extra = EXCLUDED.extra,
|
|
82
95
|
updated_at = now()
|
|
83
|
-
`.trim(), [
|
|
96
|
+
`.trim(), batch.flatMap((chunk) => [
|
|
84
97
|
chunk.id,
|
|
85
98
|
chunk.documentId,
|
|
86
99
|
chunk.parentId ?? null,
|
|
@@ -98,7 +111,7 @@ ON CONFLICT (id) DO UPDATE SET
|
|
|
98
111
|
chunk.metadata.chunkIndex,
|
|
99
112
|
chunk.metadata.acl ?? null,
|
|
100
113
|
(0, sql_1.createOptionalJson)(chunk.metadata.extra),
|
|
101
|
-
]);
|
|
114
|
+
]));
|
|
102
115
|
}
|
|
103
116
|
}
|
|
104
117
|
async getChunks(ids) {
|