ocr-provenance-mcp 1.0.0
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.
Potentially problematic release.
This version of ocr-provenance-mcp might be problematic. Click here for more details.
- package/.env.example +55 -0
- package/LICENSE +78 -0
- package/README.md +1154 -0
- package/dist/bin-http.d.ts +24 -0
- package/dist/bin-http.d.ts.map +1 -0
- package/dist/bin-http.js +275 -0
- package/dist/bin-http.js.map +1 -0
- package/dist/bin-setup.d.ts +11 -0
- package/dist/bin-setup.d.ts.map +1 -0
- package/dist/bin-setup.js +610 -0
- package/dist/bin-setup.js.map +1 -0
- package/dist/bin.d.ts +16 -0
- package/dist/bin.d.ts.map +1 -0
- package/dist/bin.js +16 -0
- package/dist/bin.js.map +1 -0
- package/dist/index.d.ts +13 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +90 -0
- package/dist/index.js.map +1 -0
- package/dist/models/chunk.d.ts +136 -0
- package/dist/models/chunk.d.ts.map +1 -0
- package/dist/models/chunk.js +27 -0
- package/dist/models/chunk.js.map +1 -0
- package/dist/models/cluster.d.ts +79 -0
- package/dist/models/cluster.d.ts.map +1 -0
- package/dist/models/cluster.js +10 -0
- package/dist/models/cluster.js.map +1 -0
- package/dist/models/comparison.d.ts +62 -0
- package/dist/models/comparison.d.ts.map +1 -0
- package/dist/models/comparison.js +8 -0
- package/dist/models/comparison.js.map +1 -0
- package/dist/models/document.d.ts +104 -0
- package/dist/models/document.d.ts.map +1 -0
- package/dist/models/document.js +15 -0
- package/dist/models/document.js.map +1 -0
- package/dist/models/embedding.d.ts +87 -0
- package/dist/models/embedding.d.ts.map +1 -0
- package/dist/models/embedding.js +23 -0
- package/dist/models/embedding.js.map +1 -0
- package/dist/models/extraction.d.ts +15 -0
- package/dist/models/extraction.d.ts.map +1 -0
- package/dist/models/extraction.js +2 -0
- package/dist/models/extraction.js.map +1 -0
- package/dist/models/form-fill.d.ts +23 -0
- package/dist/models/form-fill.d.ts.map +1 -0
- package/dist/models/form-fill.js +2 -0
- package/dist/models/form-fill.js.map +1 -0
- package/dist/models/image.d.ts +177 -0
- package/dist/models/image.d.ts.map +1 -0
- package/dist/models/image.js +8 -0
- package/dist/models/image.js.map +1 -0
- package/dist/models/index.d.ts +14 -0
- package/dist/models/index.d.ts.map +1 -0
- package/dist/models/index.js +22 -0
- package/dist/models/index.js.map +1 -0
- package/dist/models/provenance.d.ts +174 -0
- package/dist/models/provenance.d.ts.map +1 -0
- package/dist/models/provenance.js +53 -0
- package/dist/models/provenance.js.map +1 -0
- package/dist/models/uploaded-file.d.ts +20 -0
- package/dist/models/uploaded-file.d.ts.map +1 -0
- package/dist/models/uploaded-file.js +2 -0
- package/dist/models/uploaded-file.js.map +1 -0
- package/dist/server/errors.d.ts +93 -0
- package/dist/server/errors.d.ts.map +1 -0
- package/dist/server/errors.js +256 -0
- package/dist/server/errors.js.map +1 -0
- package/dist/server/events.d.ts +36 -0
- package/dist/server/events.d.ts.map +1 -0
- package/dist/server/events.js +48 -0
- package/dist/server/events.js.map +1 -0
- package/dist/server/permissions.d.ts +26 -0
- package/dist/server/permissions.d.ts.map +1 -0
- package/dist/server/permissions.js +194 -0
- package/dist/server/permissions.js.map +1 -0
- package/dist/server/register-tools.d.ts +25 -0
- package/dist/server/register-tools.d.ts.map +1 -0
- package/dist/server/register-tools.js +102 -0
- package/dist/server/register-tools.js.map +1 -0
- package/dist/server/startup.d.ts +16 -0
- package/dist/server/startup.d.ts.map +1 -0
- package/dist/server/startup.js +37 -0
- package/dist/server/startup.js.map +1 -0
- package/dist/server/state.d.ts +166 -0
- package/dist/server/state.d.ts.map +1 -0
- package/dist/server/state.js +424 -0
- package/dist/server/state.js.map +1 -0
- package/dist/server/transports/http-transport.d.ts +37 -0
- package/dist/server/transports/http-transport.d.ts.map +1 -0
- package/dist/server/transports/http-transport.js +204 -0
- package/dist/server/transports/http-transport.js.map +1 -0
- package/dist/server/transports/index.d.ts +9 -0
- package/dist/server/transports/index.d.ts.map +1 -0
- package/dist/server/transports/index.js +9 -0
- package/dist/server/transports/index.js.map +1 -0
- package/dist/server/transports/session-manager.d.ts +40 -0
- package/dist/server/transports/session-manager.d.ts.map +1 -0
- package/dist/server/transports/session-manager.js +74 -0
- package/dist/server/transports/session-manager.js.map +1 -0
- package/dist/server/types.d.ts +82 -0
- package/dist/server/types.d.ts.map +1 -0
- package/dist/server/types.js +14 -0
- package/dist/server/types.js.map +1 -0
- package/dist/services/audit.d.ts +26 -0
- package/dist/services/audit.d.ts.map +1 -0
- package/dist/services/audit.js +43 -0
- package/dist/services/audit.js.map +1 -0
- package/dist/services/chunking/chunk-deduplicator.d.ts +33 -0
- package/dist/services/chunking/chunk-deduplicator.d.ts.map +1 -0
- package/dist/services/chunking/chunk-deduplicator.js +46 -0
- package/dist/services/chunking/chunk-deduplicator.js.map +1 -0
- package/dist/services/chunking/chunk-merger.d.ts +26 -0
- package/dist/services/chunking/chunk-merger.d.ts.map +1 -0
- package/dist/services/chunking/chunk-merger.js +94 -0
- package/dist/services/chunking/chunk-merger.js.map +1 -0
- package/dist/services/chunking/chunker.d.ts +62 -0
- package/dist/services/chunking/chunker.d.ts.map +1 -0
- package/dist/services/chunking/chunker.js +566 -0
- package/dist/services/chunking/chunker.js.map +1 -0
- package/dist/services/chunking/heading-normalizer.d.ts +33 -0
- package/dist/services/chunking/heading-normalizer.d.ts.map +1 -0
- package/dist/services/chunking/heading-normalizer.js +101 -0
- package/dist/services/chunking/heading-normalizer.js.map +1 -0
- package/dist/services/chunking/json-block-analyzer.d.ts +163 -0
- package/dist/services/chunking/json-block-analyzer.d.ts.map +1 -0
- package/dist/services/chunking/json-block-analyzer.js +1033 -0
- package/dist/services/chunking/json-block-analyzer.js.map +1 -0
- package/dist/services/chunking/markdown-parser.d.ts +75 -0
- package/dist/services/chunking/markdown-parser.d.ts.map +1 -0
- package/dist/services/chunking/markdown-parser.js +428 -0
- package/dist/services/chunking/markdown-parser.js.map +1 -0
- package/dist/services/chunking/text-normalizer.d.ts +20 -0
- package/dist/services/chunking/text-normalizer.d.ts.map +1 -0
- package/dist/services/chunking/text-normalizer.js +36 -0
- package/dist/services/chunking/text-normalizer.js.map +1 -0
- package/dist/services/clm/contract-schemas.d.ts +36 -0
- package/dist/services/clm/contract-schemas.d.ts.map +1 -0
- package/dist/services/clm/contract-schemas.js +92 -0
- package/dist/services/clm/contract-schemas.js.map +1 -0
- package/dist/services/clm/summarization.d.ts +46 -0
- package/dist/services/clm/summarization.d.ts.map +1 -0
- package/dist/services/clm/summarization.js +61 -0
- package/dist/services/clm/summarization.js.map +1 -0
- package/dist/services/clustering/clustering-service.d.ts +58 -0
- package/dist/services/clustering/clustering-service.d.ts.map +1 -0
- package/dist/services/clustering/clustering-service.js +467 -0
- package/dist/services/clustering/clustering-service.js.map +1 -0
- package/dist/services/comparison/diff-service.d.ts +41 -0
- package/dist/services/comparison/diff-service.d.ts.map +1 -0
- package/dist/services/comparison/diff-service.js +120 -0
- package/dist/services/comparison/diff-service.js.map +1 -0
- package/dist/services/embedding/embedder.d.ts +55 -0
- package/dist/services/embedding/embedder.d.ts.map +1 -0
- package/dist/services/embedding/embedder.js +202 -0
- package/dist/services/embedding/embedder.js.map +1 -0
- package/dist/services/embedding/nomic.d.ts +67 -0
- package/dist/services/embedding/nomic.d.ts.map +1 -0
- package/dist/services/embedding/nomic.js +280 -0
- package/dist/services/embedding/nomic.js.map +1 -0
- package/dist/services/gemini/circuit-breaker.d.ts +106 -0
- package/dist/services/gemini/circuit-breaker.d.ts.map +1 -0
- package/dist/services/gemini/circuit-breaker.js +237 -0
- package/dist/services/gemini/circuit-breaker.js.map +1 -0
- package/dist/services/gemini/client.d.ts +173 -0
- package/dist/services/gemini/client.d.ts.map +1 -0
- package/dist/services/gemini/client.js +483 -0
- package/dist/services/gemini/client.js.map +1 -0
- package/dist/services/gemini/config.d.ts +116 -0
- package/dist/services/gemini/config.d.ts.map +1 -0
- package/dist/services/gemini/config.js +118 -0
- package/dist/services/gemini/config.js.map +1 -0
- package/dist/services/gemini/index.d.ts +9 -0
- package/dist/services/gemini/index.d.ts.map +1 -0
- package/dist/services/gemini/index.js +13 -0
- package/dist/services/gemini/index.js.map +1 -0
- package/dist/services/gemini/rate-limiter.d.ts +62 -0
- package/dist/services/gemini/rate-limiter.d.ts.map +1 -0
- package/dist/services/gemini/rate-limiter.js +120 -0
- package/dist/services/gemini/rate-limiter.js.map +1 -0
- package/dist/services/images/extractor.d.ts +88 -0
- package/dist/services/images/extractor.d.ts.map +1 -0
- package/dist/services/images/extractor.js +340 -0
- package/dist/services/images/extractor.js.map +1 -0
- package/dist/services/images/optimizer.d.ts +130 -0
- package/dist/services/images/optimizer.d.ts.map +1 -0
- package/dist/services/images/optimizer.js +228 -0
- package/dist/services/images/optimizer.js.map +1 -0
- package/dist/services/ocr/datalab.d.ts +64 -0
- package/dist/services/ocr/datalab.d.ts.map +1 -0
- package/dist/services/ocr/datalab.js +425 -0
- package/dist/services/ocr/datalab.js.map +1 -0
- package/dist/services/ocr/errors.d.ts +38 -0
- package/dist/services/ocr/errors.d.ts.map +1 -0
- package/dist/services/ocr/errors.js +83 -0
- package/dist/services/ocr/errors.js.map +1 -0
- package/dist/services/ocr/file-manager.d.ts +76 -0
- package/dist/services/ocr/file-manager.d.ts.map +1 -0
- package/dist/services/ocr/file-manager.js +238 -0
- package/dist/services/ocr/file-manager.js.map +1 -0
- package/dist/services/ocr/form-fill.d.ts +48 -0
- package/dist/services/ocr/form-fill.d.ts.map +1 -0
- package/dist/services/ocr/form-fill.js +213 -0
- package/dist/services/ocr/form-fill.js.map +1 -0
- package/dist/services/ocr/processor.d.ts +95 -0
- package/dist/services/ocr/processor.d.ts.map +1 -0
- package/dist/services/ocr/processor.js +259 -0
- package/dist/services/ocr/processor.js.map +1 -0
- package/dist/services/provenance/agent-metadata.d.ts +82 -0
- package/dist/services/provenance/agent-metadata.d.ts.map +1 -0
- package/dist/services/provenance/agent-metadata.js +106 -0
- package/dist/services/provenance/agent-metadata.js.map +1 -0
- package/dist/services/provenance/chain-hash.d.ts +57 -0
- package/dist/services/provenance/chain-hash.d.ts.map +1 -0
- package/dist/services/provenance/chain-hash.js +131 -0
- package/dist/services/provenance/chain-hash.js.map +1 -0
- package/dist/services/provenance/exporter.d.ts +202 -0
- package/dist/services/provenance/exporter.d.ts.map +1 -0
- package/dist/services/provenance/exporter.js +457 -0
- package/dist/services/provenance/exporter.js.map +1 -0
- package/dist/services/provenance/index.d.ts +15 -0
- package/dist/services/provenance/index.d.ts.map +1 -0
- package/dist/services/provenance/index.js +17 -0
- package/dist/services/provenance/index.js.map +1 -0
- package/dist/services/provenance/tracker.d.ts +138 -0
- package/dist/services/provenance/tracker.d.ts.map +1 -0
- package/dist/services/provenance/tracker.js +293 -0
- package/dist/services/provenance/tracker.js.map +1 -0
- package/dist/services/provenance/verifier.d.ts +153 -0
- package/dist/services/provenance/verifier.d.ts.map +1 -0
- package/dist/services/provenance/verifier.js +536 -0
- package/dist/services/provenance/verifier.js.map +1 -0
- package/dist/services/python-pool.d.ts +70 -0
- package/dist/services/python-pool.d.ts.map +1 -0
- package/dist/services/python-pool.js +265 -0
- package/dist/services/python-pool.js.map +1 -0
- package/dist/services/search/bm25.d.ts +180 -0
- package/dist/services/search/bm25.d.ts.map +1 -0
- package/dist/services/search/bm25.js +656 -0
- package/dist/services/search/bm25.js.map +1 -0
- package/dist/services/search/fusion.d.ts +103 -0
- package/dist/services/search/fusion.d.ts.map +1 -0
- package/dist/services/search/fusion.js +122 -0
- package/dist/services/search/fusion.js.map +1 -0
- package/dist/services/search/local-reranker.d.ts +30 -0
- package/dist/services/search/local-reranker.d.ts.map +1 -0
- package/dist/services/search/local-reranker.js +123 -0
- package/dist/services/search/local-reranker.js.map +1 -0
- package/dist/services/search/quality.d.ts +11 -0
- package/dist/services/search/quality.d.ts.map +1 -0
- package/dist/services/search/quality.js +17 -0
- package/dist/services/search/quality.js.map +1 -0
- package/dist/services/search/query-classifier.d.ts +34 -0
- package/dist/services/search/query-classifier.d.ts.map +1 -0
- package/dist/services/search/query-classifier.js +114 -0
- package/dist/services/search/query-classifier.js.map +1 -0
- package/dist/services/search/query-expander.d.ts +73 -0
- package/dist/services/search/query-expander.d.ts.map +1 -0
- package/dist/services/search/query-expander.js +281 -0
- package/dist/services/search/query-expander.js.map +1 -0
- package/dist/services/search/reranker.d.ts +44 -0
- package/dist/services/search/reranker.d.ts.map +1 -0
- package/dist/services/search/reranker.js +101 -0
- package/dist/services/search/reranker.js.map +1 -0
- package/dist/services/storage/database/annotation-operations.d.ts +113 -0
- package/dist/services/storage/database/annotation-operations.d.ts.map +1 -0
- package/dist/services/storage/database/annotation-operations.js +177 -0
- package/dist/services/storage/database/annotation-operations.js.map +1 -0
- package/dist/services/storage/database/approval-operations.d.ts +132 -0
- package/dist/services/storage/database/approval-operations.d.ts.map +1 -0
- package/dist/services/storage/database/approval-operations.js +206 -0
- package/dist/services/storage/database/approval-operations.js.map +1 -0
- package/dist/services/storage/database/chunk-operations.d.ts +132 -0
- package/dist/services/storage/database/chunk-operations.d.ts.map +1 -0
- package/dist/services/storage/database/chunk-operations.js +306 -0
- package/dist/services/storage/database/chunk-operations.js.map +1 -0
- package/dist/services/storage/database/cluster-operations.d.ts +97 -0
- package/dist/services/storage/database/cluster-operations.d.ts.map +1 -0
- package/dist/services/storage/database/cluster-operations.js +258 -0
- package/dist/services/storage/database/cluster-operations.js.map +1 -0
- package/dist/services/storage/database/comparison-operations.d.ts +41 -0
- package/dist/services/storage/database/comparison-operations.d.ts.map +1 -0
- package/dist/services/storage/database/comparison-operations.js +65 -0
- package/dist/services/storage/database/comparison-operations.js.map +1 -0
- package/dist/services/storage/database/converters.d.ts +36 -0
- package/dist/services/storage/database/converters.d.ts.map +1 -0
- package/dist/services/storage/database/converters.js +244 -0
- package/dist/services/storage/database/converters.js.map +1 -0
- package/dist/services/storage/database/document-operations.d.ts +145 -0
- package/dist/services/storage/database/document-operations.d.ts.map +1 -0
- package/dist/services/storage/database/document-operations.js +498 -0
- package/dist/services/storage/database/document-operations.js.map +1 -0
- package/dist/services/storage/database/embedding-operations.d.ts +130 -0
- package/dist/services/storage/database/embedding-operations.d.ts.map +1 -0
- package/dist/services/storage/database/embedding-operations.js +315 -0
- package/dist/services/storage/database/embedding-operations.js.map +1 -0
- package/dist/services/storage/database/extraction-operations.d.ts +47 -0
- package/dist/services/storage/database/extraction-operations.d.ts.map +1 -0
- package/dist/services/storage/database/extraction-operations.js +85 -0
- package/dist/services/storage/database/extraction-operations.js.map +1 -0
- package/dist/services/storage/database/form-fill-operations.d.ts +58 -0
- package/dist/services/storage/database/form-fill-operations.d.ts.map +1 -0
- package/dist/services/storage/database/form-fill-operations.js +116 -0
- package/dist/services/storage/database/form-fill-operations.js.map +1 -0
- package/dist/services/storage/database/helpers.d.ts +29 -0
- package/dist/services/storage/database/helpers.d.ts.map +1 -0
- package/dist/services/storage/database/helpers.js +55 -0
- package/dist/services/storage/database/helpers.js.map +1 -0
- package/dist/services/storage/database/image-operations.d.ts +202 -0
- package/dist/services/storage/database/image-operations.d.ts.map +1 -0
- package/dist/services/storage/database/image-operations.js +484 -0
- package/dist/services/storage/database/image-operations.js.map +1 -0
- package/dist/services/storage/database/index.d.ts +13 -0
- package/dist/services/storage/database/index.d.ts.map +1 -0
- package/dist/services/storage/database/index.js +16 -0
- package/dist/services/storage/database/index.js.map +1 -0
- package/dist/services/storage/database/lock-operations.d.ts +59 -0
- package/dist/services/storage/database/lock-operations.d.ts.map +1 -0
- package/dist/services/storage/database/lock-operations.js +89 -0
- package/dist/services/storage/database/lock-operations.js.map +1 -0
- package/dist/services/storage/database/obligation-operations.d.ts +88 -0
- package/dist/services/storage/database/obligation-operations.d.ts.map +1 -0
- package/dist/services/storage/database/obligation-operations.js +206 -0
- package/dist/services/storage/database/obligation-operations.js.map +1 -0
- package/dist/services/storage/database/ocr-operations.d.ts +33 -0
- package/dist/services/storage/database/ocr-operations.d.ts.map +1 -0
- package/dist/services/storage/database/ocr-operations.js +70 -0
- package/dist/services/storage/database/ocr-operations.js.map +1 -0
- package/dist/services/storage/database/playbook-operations.d.ts +72 -0
- package/dist/services/storage/database/playbook-operations.d.ts.map +1 -0
- package/dist/services/storage/database/playbook-operations.js +247 -0
- package/dist/services/storage/database/playbook-operations.js.map +1 -0
- package/dist/services/storage/database/provenance-operations.d.ts +112 -0
- package/dist/services/storage/database/provenance-operations.d.ts.map +1 -0
- package/dist/services/storage/database/provenance-operations.js +251 -0
- package/dist/services/storage/database/provenance-operations.js.map +1 -0
- package/dist/services/storage/database/service.d.ts +142 -0
- package/dist/services/storage/database/service.d.ts.map +1 -0
- package/dist/services/storage/database/service.js +310 -0
- package/dist/services/storage/database/service.js.map +1 -0
- package/dist/services/storage/database/static-operations.d.ts +30 -0
- package/dist/services/storage/database/static-operations.d.ts.map +1 -0
- package/dist/services/storage/database/static-operations.js +218 -0
- package/dist/services/storage/database/static-operations.js.map +1 -0
- package/dist/services/storage/database/stats-operations.d.ts +101 -0
- package/dist/services/storage/database/stats-operations.d.ts.map +1 -0
- package/dist/services/storage/database/stats-operations.js +394 -0
- package/dist/services/storage/database/stats-operations.js.map +1 -0
- package/dist/services/storage/database/tag-operations.d.ts +76 -0
- package/dist/services/storage/database/tag-operations.d.ts.map +1 -0
- package/dist/services/storage/database/tag-operations.js +178 -0
- package/dist/services/storage/database/tag-operations.js.map +1 -0
- package/dist/services/storage/database/types.d.ts +286 -0
- package/dist/services/storage/database/types.d.ts.map +1 -0
- package/dist/services/storage/database/types.js +39 -0
- package/dist/services/storage/database/types.js.map +1 -0
- package/dist/services/storage/database/upload-operations.d.ts +71 -0
- package/dist/services/storage/database/upload-operations.d.ts.map +1 -0
- package/dist/services/storage/database/upload-operations.js +124 -0
- package/dist/services/storage/database/upload-operations.js.map +1 -0
- package/dist/services/storage/database/user-operations.d.ts +102 -0
- package/dist/services/storage/database/user-operations.d.ts.map +1 -0
- package/dist/services/storage/database/user-operations.js +151 -0
- package/dist/services/storage/database/user-operations.js.map +1 -0
- package/dist/services/storage/database/workflow-operations.d.ts +98 -0
- package/dist/services/storage/database/workflow-operations.d.ts.map +1 -0
- package/dist/services/storage/database/workflow-operations.js +157 -0
- package/dist/services/storage/database/workflow-operations.js.map +1 -0
- package/dist/services/storage/database.d.ts +16 -0
- package/dist/services/storage/database.d.ts.map +1 -0
- package/dist/services/storage/database.js +15 -0
- package/dist/services/storage/database.js.map +1 -0
- package/dist/services/storage/index.d.ts +10 -0
- package/dist/services/storage/index.d.ts.map +1 -0
- package/dist/services/storage/index.js +10 -0
- package/dist/services/storage/index.js.map +1 -0
- package/dist/services/storage/migrations/index.d.ts +16 -0
- package/dist/services/storage/migrations/index.d.ts.map +1 -0
- package/dist/services/storage/migrations/index.js +20 -0
- package/dist/services/storage/migrations/index.js.map +1 -0
- package/dist/services/storage/migrations/operations.d.ts +40 -0
- package/dist/services/storage/migrations/operations.d.ts.map +1 -0
- package/dist/services/storage/migrations/operations.js +2910 -0
- package/dist/services/storage/migrations/operations.js.map +1 -0
- package/dist/services/storage/migrations/schema-definitions.d.ts +306 -0
- package/dist/services/storage/migrations/schema-definitions.d.ts.map +1 -0
- package/dist/services/storage/migrations/schema-definitions.js +1006 -0
- package/dist/services/storage/migrations/schema-definitions.js.map +1 -0
- package/dist/services/storage/migrations/schema-helpers.d.ts +50 -0
- package/dist/services/storage/migrations/schema-helpers.d.ts.map +1 -0
- package/dist/services/storage/migrations/schema-helpers.js +176 -0
- package/dist/services/storage/migrations/schema-helpers.js.map +1 -0
- package/dist/services/storage/migrations/types.d.ts +15 -0
- package/dist/services/storage/migrations/types.d.ts.map +1 -0
- package/dist/services/storage/migrations/types.js +21 -0
- package/dist/services/storage/migrations/types.js.map +1 -0
- package/dist/services/storage/migrations/verification.d.ts +20 -0
- package/dist/services/storage/migrations/verification.d.ts.map +1 -0
- package/dist/services/storage/migrations/verification.js +78 -0
- package/dist/services/storage/migrations/verification.js.map +1 -0
- package/dist/services/storage/migrations.d.ts +16 -0
- package/dist/services/storage/migrations.d.ts.map +1 -0
- package/dist/services/storage/migrations.js +17 -0
- package/dist/services/storage/migrations.js.map +1 -0
- package/dist/services/storage/types.d.ts +12 -0
- package/dist/services/storage/types.d.ts.map +1 -0
- package/dist/services/storage/types.js +5 -0
- package/dist/services/storage/types.js.map +1 -0
- package/dist/services/storage/vector.d.ts +208 -0
- package/dist/services/storage/vector.d.ts.map +1 -0
- package/dist/services/storage/vector.js +526 -0
- package/dist/services/storage/vector.js.map +1 -0
- package/dist/services/vlm/pipeline.d.ts +194 -0
- package/dist/services/vlm/pipeline.d.ts.map +1 -0
- package/dist/services/vlm/pipeline.js +800 -0
- package/dist/services/vlm/pipeline.js.map +1 -0
- package/dist/services/vlm/prompts.d.ts +171 -0
- package/dist/services/vlm/prompts.d.ts.map +1 -0
- package/dist/services/vlm/prompts.js +229 -0
- package/dist/services/vlm/prompts.js.map +1 -0
- package/dist/services/vlm/service.d.ts +174 -0
- package/dist/services/vlm/service.d.ts.map +1 -0
- package/dist/services/vlm/service.js +256 -0
- package/dist/services/vlm/service.js.map +1 -0
- package/dist/services/webhook-delivery.d.ts +4 -0
- package/dist/services/webhook-delivery.d.ts.map +1 -0
- package/dist/services/webhook-delivery.js +140 -0
- package/dist/services/webhook-delivery.js.map +1 -0
- package/dist/tools/chunks.d.ts +19 -0
- package/dist/tools/chunks.d.ts.map +1 -0
- package/dist/tools/chunks.js +392 -0
- package/dist/tools/chunks.js.map +1 -0
- package/dist/tools/clm.d.ts +16 -0
- package/dist/tools/clm.d.ts.map +1 -0
- package/dist/tools/clm.js +668 -0
- package/dist/tools/clm.js.map +1 -0
- package/dist/tools/clustering.d.ts +13 -0
- package/dist/tools/clustering.d.ts.map +1 -0
- package/dist/tools/clustering.js +498 -0
- package/dist/tools/clustering.js.map +1 -0
- package/dist/tools/collaboration.d.ts +15 -0
- package/dist/tools/collaboration.d.ts.map +1 -0
- package/dist/tools/collaboration.js +516 -0
- package/dist/tools/collaboration.js.map +1 -0
- package/dist/tools/comparison.d.ts +13 -0
- package/dist/tools/comparison.d.ts.map +1 -0
- package/dist/tools/comparison.js +735 -0
- package/dist/tools/comparison.js.map +1 -0
- package/dist/tools/compliance.d.ts +15 -0
- package/dist/tools/compliance.d.ts.map +1 -0
- package/dist/tools/compliance.js +640 -0
- package/dist/tools/compliance.js.map +1 -0
- package/dist/tools/config.d.ts +19 -0
- package/dist/tools/config.d.ts.map +1 -0
- package/dist/tools/config.js +213 -0
- package/dist/tools/config.js.map +1 -0
- package/dist/tools/database.d.ts +62 -0
- package/dist/tools/database.d.ts.map +1 -0
- package/dist/tools/database.js +288 -0
- package/dist/tools/database.js.map +1 -0
- package/dist/tools/documents.d.ts +61 -0
- package/dist/tools/documents.d.ts.map +1 -0
- package/dist/tools/documents.js +1624 -0
- package/dist/tools/documents.js.map +1 -0
- package/dist/tools/embeddings.d.ts +14 -0
- package/dist/tools/embeddings.d.ts.map +1 -0
- package/dist/tools/embeddings.js +626 -0
- package/dist/tools/embeddings.js.map +1 -0
- package/dist/tools/evaluation.d.ts +25 -0
- package/dist/tools/evaluation.d.ts.map +1 -0
- package/dist/tools/evaluation.js +523 -0
- package/dist/tools/evaluation.js.map +1 -0
- package/dist/tools/events.d.ts +16 -0
- package/dist/tools/events.d.ts.map +1 -0
- package/dist/tools/events.js +493 -0
- package/dist/tools/events.js.map +1 -0
- package/dist/tools/extraction-structured.d.ts +13 -0
- package/dist/tools/extraction-structured.d.ts.map +1 -0
- package/dist/tools/extraction-structured.js +390 -0
- package/dist/tools/extraction-structured.js.map +1 -0
- package/dist/tools/extraction.d.ts +24 -0
- package/dist/tools/extraction.d.ts.map +1 -0
- package/dist/tools/extraction.js +424 -0
- package/dist/tools/extraction.js.map +1 -0
- package/dist/tools/file-management.d.ts +14 -0
- package/dist/tools/file-management.d.ts.map +1 -0
- package/dist/tools/file-management.js +523 -0
- package/dist/tools/file-management.js.map +1 -0
- package/dist/tools/form-fill.d.ts +13 -0
- package/dist/tools/form-fill.d.ts.map +1 -0
- package/dist/tools/form-fill.js +250 -0
- package/dist/tools/form-fill.js.map +1 -0
- package/dist/tools/health.d.ts +19 -0
- package/dist/tools/health.d.ts.map +1 -0
- package/dist/tools/health.js +229 -0
- package/dist/tools/health.js.map +1 -0
- package/dist/tools/images.d.ts +54 -0
- package/dist/tools/images.d.ts.map +1 -0
- package/dist/tools/images.js +787 -0
- package/dist/tools/images.js.map +1 -0
- package/dist/tools/ingestion.d.ts +94 -0
- package/dist/tools/ingestion.d.ts.map +1 -0
- package/dist/tools/ingestion.js +1659 -0
- package/dist/tools/ingestion.js.map +1 -0
- package/dist/tools/intelligence.d.ts +18 -0
- package/dist/tools/intelligence.d.ts.map +1 -0
- package/dist/tools/intelligence.js +1039 -0
- package/dist/tools/intelligence.js.map +1 -0
- package/dist/tools/provenance.d.ts +51 -0
- package/dist/tools/provenance.d.ts.map +1 -0
- package/dist/tools/provenance.js +691 -0
- package/dist/tools/provenance.js.map +1 -0
- package/dist/tools/reports.d.ts +41 -0
- package/dist/tools/reports.d.ts.map +1 -0
- package/dist/tools/reports.js +1394 -0
- package/dist/tools/reports.js.map +1 -0
- package/dist/tools/search.d.ts +35 -0
- package/dist/tools/search.d.ts.map +1 -0
- package/dist/tools/search.js +2528 -0
- package/dist/tools/search.js.map +1 -0
- package/dist/tools/shared.d.ts +52 -0
- package/dist/tools/shared.d.ts.map +1 -0
- package/dist/tools/shared.js +54 -0
- package/dist/tools/shared.js.map +1 -0
- package/dist/tools/tags.d.ts +15 -0
- package/dist/tools/tags.d.ts.map +1 -0
- package/dist/tools/tags.js +287 -0
- package/dist/tools/tags.js.map +1 -0
- package/dist/tools/timeline.d.ts +15 -0
- package/dist/tools/timeline.d.ts.map +1 -0
- package/dist/tools/timeline.js +14 -0
- package/dist/tools/timeline.js.map +1 -0
- package/dist/tools/users.d.ts +14 -0
- package/dist/tools/users.d.ts.map +1 -0
- package/dist/tools/users.js +257 -0
- package/dist/tools/users.js.map +1 -0
- package/dist/tools/vlm.d.ts +40 -0
- package/dist/tools/vlm.d.ts.map +1 -0
- package/dist/tools/vlm.js +475 -0
- package/dist/tools/vlm.js.map +1 -0
- package/dist/tools/workflow.d.ts +16 -0
- package/dist/tools/workflow.d.ts.map +1 -0
- package/dist/tools/workflow.js +495 -0
- package/dist/tools/workflow.js.map +1 -0
- package/dist/utils/backoff.d.ts +53 -0
- package/dist/utils/backoff.d.ts.map +1 -0
- package/dist/utils/backoff.js +78 -0
- package/dist/utils/backoff.js.map +1 -0
- package/dist/utils/config-persistence.d.ts +33 -0
- package/dist/utils/config-persistence.d.ts.map +1 -0
- package/dist/utils/config-persistence.js +61 -0
- package/dist/utils/config-persistence.js.map +1 -0
- package/dist/utils/hash.d.ts +65 -0
- package/dist/utils/hash.d.ts.map +1 -0
- package/dist/utils/hash.js +146 -0
- package/dist/utils/hash.js.map +1 -0
- package/dist/utils/math.d.ts +21 -0
- package/dist/utils/math.d.ts.map +1 -0
- package/dist/utils/math.js +39 -0
- package/dist/utils/math.js.map +1 -0
- package/dist/utils/validation.d.ts +697 -0
- package/dist/utils/validation.d.ts.map +1 -0
- package/dist/utils/validation.js +529 -0
- package/dist/utils/validation.js.map +1 -0
- package/package.json +96 -0
- package/python/.gitkeep +0 -0
- package/python/__init__.py +104 -0
- package/python/clustering_worker.py +440 -0
- package/python/docx_image_extractor.py +524 -0
- package/python/embedding_worker.py +552 -0
- package/python/file_manager_worker.py +564 -0
- package/python/form_fill_worker.py +399 -0
- package/python/gpu_utils.py +582 -0
- package/python/image_extractor.py +317 -0
- package/python/image_optimizer.py +444 -0
- package/python/ocr_worker.py +712 -0
- package/python/pyproject.toml +76 -0
- package/python/requirements.txt +51 -0
- package/python/reranker_worker.py +87 -0
|
@@ -0,0 +1,265 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Python Worker Process Pool
|
|
3
|
+
*
|
|
4
|
+
* Maintains warm Python processes to amortize import costs (torch, transformers).
|
|
5
|
+
* Workers accept JSON commands on stdin, return JSON on stdout.
|
|
6
|
+
* Auto-restart on crash, health checks via heartbeat.
|
|
7
|
+
*
|
|
8
|
+
* CRITICAL: NEVER use console.log() - stdout is JSON-RPC protocol.
|
|
9
|
+
*
|
|
10
|
+
* @module services/python-pool
|
|
11
|
+
*/
|
|
12
|
+
import { spawn } from 'child_process';
|
|
13
|
+
import { EventEmitter } from 'events';
|
|
14
|
+
// ═══════════════════════════════════════════════════════════════════════════════
|
|
15
|
+
// POOL IMPLEMENTATION
|
|
16
|
+
// ═══════════════════════════════════════════════════════════════════════════════
|
|
17
|
+
export class PythonPool extends EventEmitter {
|
|
18
|
+
workers = new Map();
|
|
19
|
+
taskQueue = [];
|
|
20
|
+
config;
|
|
21
|
+
healthCheckTimer = null;
|
|
22
|
+
nextWorkerId = 0;
|
|
23
|
+
shuttingDown = false;
|
|
24
|
+
pythonCommand;
|
|
25
|
+
constructor(config) {
|
|
26
|
+
super();
|
|
27
|
+
this.config = {
|
|
28
|
+
poolSize: config?.poolSize ?? 3,
|
|
29
|
+
maxTasksPerWorker: config?.maxTasksPerWorker ?? 100,
|
|
30
|
+
healthCheckIntervalMs: config?.healthCheckIntervalMs ?? 30000,
|
|
31
|
+
taskTimeoutMs: config?.taskTimeoutMs ?? 120000,
|
|
32
|
+
};
|
|
33
|
+
this.pythonCommand = process.platform === 'win32' ? 'python' : 'python3';
|
|
34
|
+
}
|
|
35
|
+
/**
|
|
36
|
+
* Start the pool with the given Python script.
|
|
37
|
+
*
|
|
38
|
+
* @param scriptPath - Path to the Python worker script
|
|
39
|
+
* @throws Error if pool is shutting down
|
|
40
|
+
*/
|
|
41
|
+
start(scriptPath) {
|
|
42
|
+
if (this.shuttingDown)
|
|
43
|
+
throw new Error('Pool is shutting down');
|
|
44
|
+
for (let i = 0; i < this.config.poolSize; i++) {
|
|
45
|
+
this.spawnWorker(scriptPath);
|
|
46
|
+
}
|
|
47
|
+
this.healthCheckTimer = setInterval(() => this.healthCheck(), this.config.healthCheckIntervalMs);
|
|
48
|
+
this.healthCheckTimer.unref();
|
|
49
|
+
console.error(`[PythonPool] Started with ${this.config.poolSize} workers for ${scriptPath}`);
|
|
50
|
+
}
|
|
51
|
+
/**
|
|
52
|
+
* Execute a command on the next available worker.
|
|
53
|
+
*
|
|
54
|
+
* If all workers are busy, the task is queued and dispatched when
|
|
55
|
+
* a worker becomes available.
|
|
56
|
+
*
|
|
57
|
+
* @param command - JSON-serializable command object
|
|
58
|
+
* @returns Promise resolving with the worker's JSON response
|
|
59
|
+
* @throws Error if pool is shutting down or task times out
|
|
60
|
+
*/
|
|
61
|
+
async execute(command) {
|
|
62
|
+
if (this.shuttingDown)
|
|
63
|
+
throw new Error('Pool is shutting down');
|
|
64
|
+
return new Promise((resolve, reject) => {
|
|
65
|
+
const timeoutId = setTimeout(() => {
|
|
66
|
+
reject(new Error(`Python pool task timed out after ${this.config.taskTimeoutMs}ms`));
|
|
67
|
+
}, this.config.taskTimeoutMs);
|
|
68
|
+
const task = { command, resolve, reject, timeoutId };
|
|
69
|
+
// Try to dispatch immediately to a free worker
|
|
70
|
+
const worker = this.getAvailableWorker();
|
|
71
|
+
if (worker) {
|
|
72
|
+
this.dispatchTask(worker, task);
|
|
73
|
+
}
|
|
74
|
+
else {
|
|
75
|
+
this.taskQueue.push(task);
|
|
76
|
+
}
|
|
77
|
+
});
|
|
78
|
+
}
|
|
79
|
+
/**
|
|
80
|
+
* Shut down all workers and reject queued tasks.
|
|
81
|
+
*/
|
|
82
|
+
async shutdown() {
|
|
83
|
+
this.shuttingDown = true;
|
|
84
|
+
if (this.healthCheckTimer) {
|
|
85
|
+
clearInterval(this.healthCheckTimer);
|
|
86
|
+
this.healthCheckTimer = null;
|
|
87
|
+
}
|
|
88
|
+
// Reject all queued tasks
|
|
89
|
+
for (const task of this.taskQueue) {
|
|
90
|
+
clearTimeout(task.timeoutId);
|
|
91
|
+
task.reject(new Error('Pool shutting down'));
|
|
92
|
+
}
|
|
93
|
+
this.taskQueue = [];
|
|
94
|
+
// Kill all workers
|
|
95
|
+
for (const [, worker] of this.workers) {
|
|
96
|
+
try {
|
|
97
|
+
worker.process.kill('SIGTERM');
|
|
98
|
+
// Force kill after 5s
|
|
99
|
+
const forceTimer = setTimeout(() => {
|
|
100
|
+
try {
|
|
101
|
+
worker.process.kill('SIGKILL');
|
|
102
|
+
}
|
|
103
|
+
catch {
|
|
104
|
+
/* already dead */
|
|
105
|
+
}
|
|
106
|
+
}, 5000);
|
|
107
|
+
forceTimer.unref();
|
|
108
|
+
}
|
|
109
|
+
catch {
|
|
110
|
+
// Worker already dead
|
|
111
|
+
}
|
|
112
|
+
}
|
|
113
|
+
this.workers.clear();
|
|
114
|
+
console.error('[PythonPool] Shut down');
|
|
115
|
+
}
|
|
116
|
+
/**
|
|
117
|
+
* Get pool status for diagnostics.
|
|
118
|
+
*/
|
|
119
|
+
getStatus() {
|
|
120
|
+
let busy = 0;
|
|
121
|
+
let idle = 0;
|
|
122
|
+
for (const w of this.workers.values()) {
|
|
123
|
+
if (w.busy)
|
|
124
|
+
busy++;
|
|
125
|
+
else
|
|
126
|
+
idle++;
|
|
127
|
+
}
|
|
128
|
+
return {
|
|
129
|
+
total: this.workers.size,
|
|
130
|
+
busy,
|
|
131
|
+
idle,
|
|
132
|
+
queued: this.taskQueue.length,
|
|
133
|
+
};
|
|
134
|
+
}
|
|
135
|
+
// ═════════════════════════════════════════════════════════════════════════════
|
|
136
|
+
// PRIVATE METHODS
|
|
137
|
+
// ═════════════════════════════════════════════════════════════════════════════
|
|
138
|
+
spawnWorker(scriptPath) {
|
|
139
|
+
const id = this.nextWorkerId++;
|
|
140
|
+
const proc = spawn(this.pythonCommand, [scriptPath], {
|
|
141
|
+
stdio: ['pipe', 'pipe', 'pipe'],
|
|
142
|
+
env: { ...process.env },
|
|
143
|
+
});
|
|
144
|
+
const worker = {
|
|
145
|
+
process: proc,
|
|
146
|
+
busy: false,
|
|
147
|
+
taskCount: 0,
|
|
148
|
+
lastHeartbeat: Date.now(),
|
|
149
|
+
scriptPath,
|
|
150
|
+
};
|
|
151
|
+
// Capture stderr for logging
|
|
152
|
+
let stderrBuf = '';
|
|
153
|
+
proc.stderr?.on('data', (data) => {
|
|
154
|
+
stderrBuf += data.toString();
|
|
155
|
+
const lines = stderrBuf.split('\n');
|
|
156
|
+
stderrBuf = lines.pop() ?? '';
|
|
157
|
+
for (const line of lines) {
|
|
158
|
+
if (line.trim())
|
|
159
|
+
console.error(`[PythonPool:${id}] ${line}`);
|
|
160
|
+
}
|
|
161
|
+
});
|
|
162
|
+
proc.on('exit', (code) => {
|
|
163
|
+
console.error(`[PythonPool] Worker ${id} exited with code ${code}`);
|
|
164
|
+
this.workers.delete(id);
|
|
165
|
+
// Auto-restart if not shutting down
|
|
166
|
+
if (!this.shuttingDown) {
|
|
167
|
+
console.error(`[PythonPool] Restarting worker ${id}...`);
|
|
168
|
+
this.spawnWorker(scriptPath);
|
|
169
|
+
}
|
|
170
|
+
});
|
|
171
|
+
proc.on('error', (err) => {
|
|
172
|
+
console.error(`[PythonPool] Worker ${id} error: ${err.message}`);
|
|
173
|
+
});
|
|
174
|
+
this.workers.set(id, worker);
|
|
175
|
+
}
|
|
176
|
+
getAvailableWorker() {
|
|
177
|
+
for (const [id, worker] of this.workers) {
|
|
178
|
+
if (!worker.busy)
|
|
179
|
+
return [id, worker];
|
|
180
|
+
}
|
|
181
|
+
return null;
|
|
182
|
+
}
|
|
183
|
+
dispatchTask(entry, task) {
|
|
184
|
+
const [id, worker] = entry;
|
|
185
|
+
worker.busy = true;
|
|
186
|
+
worker.taskCount++;
|
|
187
|
+
let stdoutBuf = '';
|
|
188
|
+
const onData = (data) => {
|
|
189
|
+
stdoutBuf += data.toString();
|
|
190
|
+
// Try to parse complete JSON response (newline-delimited)
|
|
191
|
+
const newlineIdx = stdoutBuf.indexOf('\n');
|
|
192
|
+
if (newlineIdx !== -1) {
|
|
193
|
+
const line = stdoutBuf.substring(0, newlineIdx);
|
|
194
|
+
stdoutBuf = stdoutBuf.substring(newlineIdx + 1);
|
|
195
|
+
cleanup();
|
|
196
|
+
clearTimeout(task.timeoutId);
|
|
197
|
+
try {
|
|
198
|
+
const result = JSON.parse(line);
|
|
199
|
+
if (result.error) {
|
|
200
|
+
task.reject(new Error(String(result.error)));
|
|
201
|
+
}
|
|
202
|
+
else {
|
|
203
|
+
task.resolve(result);
|
|
204
|
+
}
|
|
205
|
+
}
|
|
206
|
+
catch {
|
|
207
|
+
task.reject(new Error(`Failed to parse worker response: ${line.substring(0, 200)}`));
|
|
208
|
+
}
|
|
209
|
+
worker.busy = false;
|
|
210
|
+
worker.lastHeartbeat = Date.now();
|
|
211
|
+
// Restart worker if it hit max tasks
|
|
212
|
+
if (worker.taskCount >= this.config.maxTasksPerWorker) {
|
|
213
|
+
console.error(`[PythonPool] Worker ${id} hit max tasks (${this.config.maxTasksPerWorker}), recycling`);
|
|
214
|
+
worker.process.kill('SIGTERM');
|
|
215
|
+
}
|
|
216
|
+
else {
|
|
217
|
+
// Process next task in queue
|
|
218
|
+
this.processQueue();
|
|
219
|
+
}
|
|
220
|
+
}
|
|
221
|
+
};
|
|
222
|
+
const onError = (err) => {
|
|
223
|
+
cleanup();
|
|
224
|
+
clearTimeout(task.timeoutId);
|
|
225
|
+
worker.busy = false;
|
|
226
|
+
task.reject(err);
|
|
227
|
+
};
|
|
228
|
+
const cleanup = () => {
|
|
229
|
+
worker.process.stdout?.removeListener('data', onData);
|
|
230
|
+
worker.process.removeListener('error', onError);
|
|
231
|
+
};
|
|
232
|
+
worker.process.stdout?.on('data', onData);
|
|
233
|
+
worker.process.on('error', onError);
|
|
234
|
+
// Send command as newline-delimited JSON
|
|
235
|
+
const cmdStr = JSON.stringify(task.command) + '\n';
|
|
236
|
+
worker.process.stdin?.write(cmdStr, (err) => {
|
|
237
|
+
if (err) {
|
|
238
|
+
cleanup();
|
|
239
|
+
clearTimeout(task.timeoutId);
|
|
240
|
+
worker.busy = false;
|
|
241
|
+
task.reject(new Error(`Failed to write to worker: ${err.message}`));
|
|
242
|
+
}
|
|
243
|
+
});
|
|
244
|
+
}
|
|
245
|
+
processQueue() {
|
|
246
|
+
while (this.taskQueue.length > 0) {
|
|
247
|
+
const worker = this.getAvailableWorker();
|
|
248
|
+
if (!worker)
|
|
249
|
+
break;
|
|
250
|
+
const task = this.taskQueue.shift();
|
|
251
|
+
this.dispatchTask(worker, task);
|
|
252
|
+
}
|
|
253
|
+
}
|
|
254
|
+
healthCheck() {
|
|
255
|
+
const now = Date.now();
|
|
256
|
+
for (const [id, worker] of this.workers) {
|
|
257
|
+
if (worker.busy &&
|
|
258
|
+
now - worker.lastHeartbeat > this.config.taskTimeoutMs * 2) {
|
|
259
|
+
console.error(`[PythonPool] Worker ${id} appears hung, killing`);
|
|
260
|
+
worker.process.kill('SIGKILL');
|
|
261
|
+
}
|
|
262
|
+
}
|
|
263
|
+
}
|
|
264
|
+
}
|
|
265
|
+
//# sourceMappingURL=python-pool.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"python-pool.js","sourceRoot":"","sources":["../../src/services/python-pool.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,KAAK,EAAqB,MAAM,eAAe,CAAC;AACzD,OAAO,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAC;AAuCtC,kFAAkF;AAClF,sBAAsB;AACtB,kFAAkF;AAElF,MAAM,OAAO,UAAW,SAAQ,YAAY;IAClC,OAAO,GAA8B,IAAI,GAAG,EAAE,CAAC;IAC/C,SAAS,GAAe,EAAE,CAAC;IAClB,MAAM,CAAa;IAC5B,gBAAgB,GAA0B,IAAI,CAAC;IAC/C,YAAY,GAAG,CAAC,CAAC;IACjB,YAAY,GAAG,KAAK,CAAC;IACZ,aAAa,CAAS;IAEvC,YAAY,MAA4B;QACtC,KAAK,EAAE,CAAC;QACR,IAAI,CAAC,MAAM,GAAG;YACZ,QAAQ,EAAE,MAAM,EAAE,QAAQ,IAAI,CAAC;YAC/B,iBAAiB,EAAE,MAAM,EAAE,iBAAiB,IAAI,GAAG;YACnD,qBAAqB,EAAE,MAAM,EAAE,qBAAqB,IAAI,KAAK;YAC7D,aAAa,EAAE,MAAM,EAAE,aAAa,IAAI,MAAM;SAC/C,CAAC;QACF,IAAI,CAAC,aAAa,GAAG,OAAO,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC;IAC3E,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,UAAkB;QACtB,IAAI,IAAI,CAAC,YAAY;YAAE,MAAM,IAAI,KAAK,CAAC,uBAAuB,CAAC,CAAC;QAChE,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,CAAC,EAAE,EAAE,CAAC;YAC9C,IAAI,CAAC,WAAW,CAAC,UAAU,CAAC,CAAC;QAC/B,CAAC;QACD,IAAI,CAAC,gBAAgB,GAAG,WAAW,CACjC,GAAG,EAAE,CAAC,IAAI,CAAC,WAAW,EAAE,EACxB,IAAI,CAAC,MAAM,CAAC,qBAAqB,CAClC,CAAC;QACF,IAAI,CAAC,gBAAgB,CAAC,KAAK,EAAE,CAAC;QAC9B,OAAO,CAAC,KAAK,CACX,6BAA6B,IAAI,CAAC,MAAM,CAAC,QAAQ,gBAAgB,UAAU,EAAE,CAC9E,CAAC;IACJ,CAAC;IAED;;;;;;;;;OASG;IACH,KAAK,CAAC,OAAO,CAAC,OAAgC;QAC5C,IAAI,IAAI,CAAC,YAAY;YAAE,MAAM,IAAI,KAAK,CAAC,uBAAuB,CAAC,CAAC;QAEhE,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;YACrC,MAAM,SAAS,GAAG,UAAU,CAAC,GAAG,EAAE;gBAChC,MAAM,CACJ,IAAI,KAAK,CACP,oCAAoC,IAAI,CAAC,MAAM,CAAC,aAAa,IAAI,CAClE,CACF,CAAC;YACJ,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC;YAE9B,MAAM,IAAI,GAAa,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC;YAE/D,+CAA+C;YAC/C,MAAM,MAAM,GAAG,IAAI,CAAC,kBAAkB,EAAE,CAAC;YACzC,IAAI,MAAM,EAAE,CAAC;gBACX,IAAI,CAAC,YAAY,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YAClC,CAAC;iBAAM,CAAC;gBACN,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YAC5B,CAAC;QACH,CAAC,CAAC,CAAC;IACL,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,QAAQ;QACZ,IAAI,CAAC,YAAY,GAAG,IAAI,CAAC;QACzB,IAAI,IAAI,CAAC,gBAAgB,EAAE,CAAC;YAC1B,aAAa,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC;YACrC,IAAI,CAAC,gBAAgB,GAAG,IAAI,CAAC;QAC/B,CAAC;QAED,0BAA0B;QAC1B,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,SAAS,EAAE,CAAC;YAClC,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,IAAI,KAAK,CAAC,oBAAoB,CAAC,CAAC,CAAC;QAC/C,CAAC;QACD,IAAI,CAAC,SAAS,GAAG,EAAE,CAAC;QAEpB,mBAAmB;QACnB,KAAK,MAAM,CAAC,EAAE,MAAM,CAAC,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YACtC,IAAI,CAAC;gBACH,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;gBAC/B,sBAAsB;gBACtB,MAAM,UAAU,GAAG,UAAU,CAAC,GAAG,EAAE;oBACjC,IAAI,CAAC;wBACH,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;oBACjC,CAAC;oBAAC,MAAM,CAAC;wBACP,kBAAkB;oBACpB,CAAC;gBACH,CAAC,EAAE,IAAI,CAAC,CAAC;gBACT,UAAU,CAAC,KAAK,EAAE,CAAC;YACrB,CAAC;YAAC,MAAM,CAAC;gBACP,sBAAsB;YACxB,CAAC;QACH,CAAC;QACD,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,CAAC;QACrB,OAAO,CAAC,KAAK,CAAC,wBAAwB,CAAC,CAAC;IAC1C,CAAC;IAED;;OAEG;IACH,SAAS;QACP,IAAI,IAAI,GAAG,CAAC,CAAC;QACb,IAAI,IAAI,GAAG,CAAC,CAAC;QACb,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC;YACtC,IAAI,CAAC,CAAC,IAAI;gBAAE,IAAI,EAAE,CAAC;;gBACd,IAAI,EAAE,CAAC;QACd,CAAC;QACD,OAAO;YACL,KAAK,EAAE,IAAI,CAAC,OAAO,CAAC,IAAI;YACxB,IAAI;YACJ,IAAI;YACJ,MAAM,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM;SAC9B,CAAC;IACJ,CAAC;IAED,gFAAgF;IAChF,kBAAkB;IAClB,gFAAgF;IAExE,WAAW,CAAC,UAAkB;QACpC,MAAM,EAAE,GAAG,IAAI,CAAC,YAAY,EAAE,CAAC;QAC/B,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,aAAa,EAAE,CAAC,UAAU,CAAC,EAAE;YACnD,KAAK,EAAE,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC;YAC/B,GAAG,EAAE,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE;SACxB,CAAC,CAAC;QAEH,MAAM,MAAM,GAAiB;YAC3B,OAAO,EAAE,IAAI;YACb,IAAI,EAAE,KAAK;YACX,SAAS,EAAE,CAAC;YACZ,aAAa,EAAE,IAAI,CAAC,GAAG,EAAE;YACzB,UAAU;SACX,CAAC;QAEF,6BAA6B;QAC7B,IAAI,SAAS,GAAG,EAAE,CAAC;QACnB,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,EAAE,CAAC,IAAY,EAAE,EAAE;YACvC,SAAS,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;YAC7B,MAAM,KAAK,GAAG,SAAS,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YACpC,SAAS,GAAG,KAAK,CAAC,GAAG,EAAE,IAAI,EAAE,CAAC;YAC9B,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBACzB,IAAI,IAAI,CAAC,IAAI,EAAE;oBAAE,OAAO,CAAC,KAAK,CAAC,eAAe,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC;YAC/D,CAAC;QACH,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,EAAE;YACvB,OAAO,CAAC,KAAK,CAAC,uBAAuB,EAAE,qBAAqB,IAAI,EAAE,CAAC,CAAC;YACpE,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACxB,oCAAoC;YACpC,IAAI,CAAC,IAAI,CAAC,YAAY,EAAE,CAAC;gBACvB,OAAO,CAAC,KAAK,CAAC,kCAAkC,EAAE,KAAK,CAAC,CAAC;gBACzD,IAAI,CAAC,WAAW,CAAC,UAAU,CAAC,CAAC;YAC/B,CAAC;QACH,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE;YACvB,OAAO,CAAC,KAAK,CAAC,uBAAuB,EAAE,WAAW,GAAG,CAAC,OAAO,EAAE,CAAC,CAAC;QACnE,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,EAAE,EAAE,MAAM,CAAC,CAAC;IAC/B,CAAC;IAEO,kBAAkB;QACxB,KAAK,MAAM,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YACxC,IAAI,CAAC,MAAM,CAAC,IAAI;gBAAE,OAAO,CAAC,EAAE,EAAE,MAAM,CAAC,CAAC;QACxC,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC;IAEO,YAAY,CAClB,KAA6B,EAC7B,IAAc;QAEd,MAAM,CAAC,EAAE,EAAE,MAAM,CAAC,GAAG,KAAK,CAAC;QAC3B,MAAM,CAAC,IAAI,GAAG,IAAI,CAAC;QACnB,MAAM,CAAC,SAAS,EAAE,CAAC;QAEnB,IAAI,SAAS,GAAG,EAAE,CAAC;QAEnB,MAAM,MAAM,GAAG,CAAC,IAAY,EAAQ,EAAE;YACpC,SAAS,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;YAC7B,0DAA0D;YAC1D,MAAM,UAAU,GAAG,SAAS,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YAC3C,IAAI,UAAU,KAAK,CAAC,CAAC,EAAE,CAAC;gBACtB,MAAM,IAAI,GAAG,SAAS,CAAC,SAAS,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC;gBAChD,SAAS,GAAG,SAAS,CAAC,SAAS,CAAC,UAAU,GAAG,CAAC,CAAC,CAAC;gBAEhD,OAAO,EAAE,CAAC;gBACV,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;gBAE7B,IAAI,CAAC;oBACH,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAA4B,CAAC;oBAC3D,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;wBACjB,IAAI,CAAC,MAAM,CAAC,IAAI,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;oBAC/C,CAAC;yBAAM,CAAC;wBACN,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;oBACvB,CAAC;gBACH,CAAC;gBAAC,MAAM,CAAC;oBACP,IAAI,CAAC,MAAM,CACT,IAAI,KAAK,CACP,oCAAoC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,CAC7D,CACF,CAAC;gBACJ,CAAC;gBAED,MAAM,CAAC,IAAI,GAAG,KAAK,CAAC;gBACpB,MAAM,CAAC,aAAa,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;gBAElC,qCAAqC;gBACrC,IAAI,MAAM,CAAC,SAAS,IAAI,IAAI,CAAC,MAAM,CAAC,iBAAiB,EAAE,CAAC;oBACtD,OAAO,CAAC,KAAK,CACX,uBAAuB,EAAE,mBAAmB,IAAI,CAAC,MAAM,CAAC,iBAAiB,cAAc,CACxF,CAAC;oBACF,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;gBACjC,CAAC;qBAAM,CAAC;oBACN,6BAA6B;oBAC7B,IAAI,CAAC,YAAY,EAAE,CAAC;gBACtB,CAAC;YACH,CAAC;QACH,CAAC,CAAC;QAEF,MAAM,OAAO,GAAG,CAAC,GAAU,EAAQ,EAAE;YACnC,OAAO,EAAE,CAAC;YACV,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;YAC7B,MAAM,CAAC,IAAI,GAAG,KAAK,CAAC;YACpB,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QACnB,CAAC,CAAC;QAEF,MAAM,OAAO,GAAG,GAAS,EAAE;YACzB,MAAM,CAAC,OAAO,CAAC,MAAM,EAAE,cAAc,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;YACtD,MAAM,CAAC,OAAO,CAAC,cAAc,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;QAClD,CAAC,CAAC;QAEF,MAAM,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC1C,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;QAEpC,yCAAyC;QACzC,MAAM,MAAM,GAAG,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC;QACnD,MAAM,CAAC,OAAO,CAAC,KAAK,EAAE,KAAK,CAAC,MAAM,EAAE,CAAC,GAAG,EAAE,EAAE;YAC1C,IAAI,GAAG,EAAE,CAAC;gBACR,OAAO,EAAE,CAAC;gBACV,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;gBAC7B,MAAM,CAAC,IAAI,GAAG,KAAK,CAAC;gBACpB,IAAI,CAAC,MAAM,CAAC,IAAI,KAAK,CAAC,8BAA8B,GAAG,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC;YACtE,CAAC;QACH,CAAC,CAAC,CAAC;IACL,CAAC;IAEO,YAAY;QAClB,OAAO,IAAI,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACjC,MAAM,MAAM,GAAG,IAAI,CAAC,kBAAkB,EAAE,CAAC;YACzC,IAAI,CAAC,MAAM;gBAAE,MAAM;YACnB,MAAM,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,KAAK,EAAG,CAAC;YACrC,IAAI,CAAC,YAAY,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;QAClC,CAAC;IACH,CAAC;IAEO,WAAW;QACjB,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QACvB,KAAK,MAAM,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YACxC,IACE,MAAM,CAAC,IAAI;gBACX,GAAG,GAAG,MAAM,CAAC,aAAa,GAAG,IAAI,CAAC,MAAM,CAAC,aAAa,GAAG,CAAC,EAC1D,CAAC;gBACD,OAAO,CAAC,KAAK,CACX,uBAAuB,EAAE,wBAAwB,CAClD,CAAC;gBACF,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;YACjC,CAAC;QACH,CAAC;IACH,CAAC;CACF"}
|
|
@@ -0,0 +1,180 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* BM25 Search Service using SQLite FTS5
|
|
3
|
+
*
|
|
4
|
+
* FAIL FAST: All errors throw immediately with detailed messages
|
|
5
|
+
* PROVENANCE: Every result includes provenance_id and content_hash
|
|
6
|
+
*/
|
|
7
|
+
import type Database from 'better-sqlite3';
|
|
8
|
+
interface ChunkFilterSQL {
|
|
9
|
+
conditions: string[];
|
|
10
|
+
params: unknown[];
|
|
11
|
+
}
|
|
12
|
+
interface BM25SearchOptions {
|
|
13
|
+
query: string;
|
|
14
|
+
limit?: number;
|
|
15
|
+
phraseSearch?: boolean;
|
|
16
|
+
documentFilter?: string[];
|
|
17
|
+
includeHighlight?: boolean;
|
|
18
|
+
chunkFilter?: ChunkFilterSQL;
|
|
19
|
+
/** Page range filter applied to VLM/extraction searches (which lack chunk metadata) */
|
|
20
|
+
pageRangeFilter?: {
|
|
21
|
+
min_page?: number;
|
|
22
|
+
max_page?: number;
|
|
23
|
+
};
|
|
24
|
+
/**
|
|
25
|
+
* When true, the query is already a valid FTS5 expression (e.g. OR-joined
|
|
26
|
+
* terms from expandQuery) and must NOT be re-processed by sanitizeFTS5Query().
|
|
27
|
+
* Re-processing would insert implicit AND between consecutive non-operator
|
|
28
|
+
* tokens, corrupting the OR semantics (H-2 fix).
|
|
29
|
+
*/
|
|
30
|
+
preSanitized?: boolean;
|
|
31
|
+
}
|
|
32
|
+
interface BM25SearchResult {
|
|
33
|
+
chunk_id: string | null;
|
|
34
|
+
image_id: string | null;
|
|
35
|
+
embedding_id: string | null;
|
|
36
|
+
extraction_id: string | null;
|
|
37
|
+
document_id: string;
|
|
38
|
+
original_text: string;
|
|
39
|
+
bm25_score: number;
|
|
40
|
+
rank: number;
|
|
41
|
+
result_type: 'chunk' | 'vlm' | 'extraction';
|
|
42
|
+
source_file_path: string;
|
|
43
|
+
source_file_name: string;
|
|
44
|
+
source_file_hash: string;
|
|
45
|
+
page_number: number | null;
|
|
46
|
+
character_start: number;
|
|
47
|
+
character_end: number;
|
|
48
|
+
chunk_index: number;
|
|
49
|
+
provenance_id: string;
|
|
50
|
+
content_hash: string;
|
|
51
|
+
highlight?: string;
|
|
52
|
+
heading_context?: string | null;
|
|
53
|
+
section_path?: string | null;
|
|
54
|
+
content_types?: string | null;
|
|
55
|
+
is_atomic?: boolean;
|
|
56
|
+
page_range?: string | null;
|
|
57
|
+
heading_level?: number | null;
|
|
58
|
+
ocr_quality_score?: number | null;
|
|
59
|
+
doc_title?: string | null;
|
|
60
|
+
doc_author?: string | null;
|
|
61
|
+
doc_subject?: string | null;
|
|
62
|
+
overlap_previous?: number;
|
|
63
|
+
overlap_next?: number;
|
|
64
|
+
chunking_strategy?: string | null;
|
|
65
|
+
embedding_status?: string;
|
|
66
|
+
doc_page_count?: number | null;
|
|
67
|
+
datalab_mode?: string | null;
|
|
68
|
+
total_chunks?: number;
|
|
69
|
+
}
|
|
70
|
+
export declare class BM25SearchService {
|
|
71
|
+
private readonly db;
|
|
72
|
+
constructor(db: Database.Database);
|
|
73
|
+
private verifyFTSTableExists;
|
|
74
|
+
search(options: BM25SearchOptions): BM25SearchResult[];
|
|
75
|
+
/**
|
|
76
|
+
* Search VLM description embeddings using FTS5
|
|
77
|
+
* Queries vlm_fts JOIN embeddings JOIN images JOIN documents
|
|
78
|
+
*
|
|
79
|
+
* NOTE: VLM results only support page_range_filter from chunk filters
|
|
80
|
+
* (VLM embeddings don't have heading_context, section_path, etc.)
|
|
81
|
+
*/
|
|
82
|
+
searchVLM(options: BM25SearchOptions): BM25SearchResult[];
|
|
83
|
+
/**
|
|
84
|
+
* Search extraction content using FTS5
|
|
85
|
+
* Queries extractions_fts JOIN extractions JOIN documents
|
|
86
|
+
*
|
|
87
|
+
* NOTE: Extractions don't have page numbers or chunk metadata,
|
|
88
|
+
* so chunkFilter and pageRangeFilter are not applied here.
|
|
89
|
+
*/
|
|
90
|
+
searchExtractions(options: BM25SearchOptions): BM25SearchResult[];
|
|
91
|
+
rebuildIndex(): {
|
|
92
|
+
chunks_indexed: number;
|
|
93
|
+
vlm_indexed: number;
|
|
94
|
+
extractions_indexed: number;
|
|
95
|
+
duration_ms: number;
|
|
96
|
+
content_hash: string;
|
|
97
|
+
};
|
|
98
|
+
/**
|
|
99
|
+
* Rebuild VLM FTS index from embeddings where image_id IS NOT NULL
|
|
100
|
+
*/
|
|
101
|
+
rebuildVLMIndex(): {
|
|
102
|
+
vlm_indexed: number;
|
|
103
|
+
duration_ms: number;
|
|
104
|
+
};
|
|
105
|
+
/**
|
|
106
|
+
* Rebuild extractions FTS index
|
|
107
|
+
*/
|
|
108
|
+
rebuildExtractionIndex(): {
|
|
109
|
+
extractions_indexed: number;
|
|
110
|
+
duration_ms: number;
|
|
111
|
+
};
|
|
112
|
+
/**
|
|
113
|
+
* Search document metadata (title, author, subject) using FTS5.
|
|
114
|
+
* Queries documents_fts table (v30+).
|
|
115
|
+
*
|
|
116
|
+
* Returns document IDs and metadata fields matching the query.
|
|
117
|
+
* Used to find documents by metadata rather than content.
|
|
118
|
+
*/
|
|
119
|
+
searchDocumentMetadata(options: {
|
|
120
|
+
query: string;
|
|
121
|
+
limit?: number;
|
|
122
|
+
phraseSearch?: boolean;
|
|
123
|
+
}): Array<{
|
|
124
|
+
document_id: string;
|
|
125
|
+
file_name: string;
|
|
126
|
+
doc_title: string | null;
|
|
127
|
+
doc_author: string | null;
|
|
128
|
+
doc_subject: string | null;
|
|
129
|
+
bm25_score: number;
|
|
130
|
+
rank: number;
|
|
131
|
+
result_type: 'document_metadata';
|
|
132
|
+
}>;
|
|
133
|
+
/**
|
|
134
|
+
* Check whether all expected FTS triggers exist for a given set of trigger names.
|
|
135
|
+
* If all triggers are present, the FTS index is kept in sync atomically and cannot be stale.
|
|
136
|
+
* If any trigger is missing, the index IS stale (triggers are the sync mechanism).
|
|
137
|
+
*/
|
|
138
|
+
private checkTriggersExist;
|
|
139
|
+
getStatus(): {
|
|
140
|
+
chunks_indexed: number;
|
|
141
|
+
current_chunk_count: number;
|
|
142
|
+
index_stale: boolean;
|
|
143
|
+
last_rebuild_at: string | null;
|
|
144
|
+
tokenizer: string;
|
|
145
|
+
content_hash: string | null;
|
|
146
|
+
vlm_indexed: number;
|
|
147
|
+
current_vlm_count: number;
|
|
148
|
+
vlm_index_stale: boolean;
|
|
149
|
+
vlm_last_rebuild_at: string | null;
|
|
150
|
+
extractions_indexed: number;
|
|
151
|
+
current_extraction_count: number;
|
|
152
|
+
extraction_index_stale: boolean;
|
|
153
|
+
extraction_last_rebuild_at: string | null;
|
|
154
|
+
};
|
|
155
|
+
private computeContentHash;
|
|
156
|
+
}
|
|
157
|
+
/**
|
|
158
|
+
* Sanitize a user-provided query for safe use in FTS5 MATCH expressions.
|
|
159
|
+
*
|
|
160
|
+
* - Preserves FTS5 boolean operators (AND, OR, NOT)
|
|
161
|
+
* - Treats hyphens as word separators (matching unicode61 tokenizer)
|
|
162
|
+
* - Strips all FTS5 metacharacters (' " ( ) * : ^ ~ + etc.)
|
|
163
|
+
* - Inserts implicit AND between consecutive non-operator tokens
|
|
164
|
+
* - Strips leading/trailing/consecutive operators
|
|
165
|
+
*
|
|
166
|
+
* This is the SINGLE authoritative FTS5 sanitizer for the entire codebase.
|
|
167
|
+
*
|
|
168
|
+
* @param query - Raw user query string
|
|
169
|
+
* @returns Sanitized FTS5 query string
|
|
170
|
+
* @throws Error if query contains no valid tokens after sanitization
|
|
171
|
+
*/
|
|
172
|
+
export declare function sanitizeFTS5Query(query: string): string;
|
|
173
|
+
/**
|
|
174
|
+
* Compute SHA-256 content hash of all chunk IDs and text_hashes for FTS index integrity verification.
|
|
175
|
+
* L-10 fix: Uses incremental hashing with iterate() instead of loading all rows into memory.
|
|
176
|
+
* Used by both BM25SearchService and the v3->v4 migration.
|
|
177
|
+
*/
|
|
178
|
+
export declare function computeFTSContentHash(db: Database.Database): string;
|
|
179
|
+
export {};
|
|
180
|
+
//# sourceMappingURL=bm25.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"bm25.d.ts","sourceRoot":"","sources":["../../../src/services/search/bm25.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAGH,OAAO,KAAK,QAAQ,MAAM,gBAAgB,CAAC;AAI3C,UAAU,cAAc;IACtB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,MAAM,EAAE,OAAO,EAAE,CAAC;CACnB;AAED,UAAU,iBAAiB;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;IAC1B,gBAAgB,CAAC,EAAE,OAAO,CAAC;IAC3B,WAAW,CAAC,EAAE,cAAc,CAAC;IAC7B,uFAAuF;IACvF,eAAe,CAAC,EAAE;QAAE,QAAQ,CAAC,EAAE,MAAM,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,CAAA;KAAE,CAAC;IAC3D;;;;;OAKG;IACH,YAAY,CAAC,EAAE,OAAO,CAAC;CACxB;AAED,UAAU,gBAAgB;IACxB,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,YAAY,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,aAAa,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;IACtB,UAAU,EAAE,MAAM,CAAC;IACnB,IAAI,EAAE,MAAM,CAAC;IACb,WAAW,EAAE,OAAO,GAAG,KAAK,GAAG,YAAY,CAAC;IAC5C,gBAAgB,EAAE,MAAM,CAAC;IACzB,gBAAgB,EAAE,MAAM,CAAC;IACzB,gBAAgB,EAAE,MAAM,CAAC;IACzB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3B,eAAe,EAAE,MAAM,CAAC;IACxB,aAAa,EAAE,MAAM,CAAC;IACtB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;IACtB,YAAY,EAAE,MAAM,CAAC;IACrB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,eAAe,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAChC,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,UAAU,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3B,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,iBAAiB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAClC,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,UAAU,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3B,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,iBAAiB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAClC,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,cAAc,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,YAAY,CAAC,EAAE,MAAM,CAAC;CACvB;AAeD,qBAAa,iBAAiB;IAChB,OAAO,CAAC,QAAQ,CAAC,EAAE;gBAAF,EAAE,EAAE,QAAQ,CAAC,QAAQ;IAIlD,OAAO,CAAC,oBAAoB;IAa5B,MAAM,CAAC,OAAO,EAAE,iBAAiB,GAAG,gBAAgB,EAAE;IAuItD;;;;;;OAMG;IACH,SAAS,CAAC,OAAO,EAAE,iBAAiB,GAAG,gBAAgB,EAAE;IAsHzD;;;;;;OAMG;IACH,iBAAiB,CAAC,OAAO,EAAE,iBAAiB,GAAG,gBAAgB,EAAE;IAqGjE,YAAY,IAAI;QACd,cAAc,EAAE,MAAM,CAAC;QACvB,WAAW,EAAE,MAAM,CAAC;QACpB,mBAAmB,EAAE,MAAM,CAAC;QAC5B,WAAW,EAAE,MAAM,CAAC;QACpB,YAAY,EAAE,MAAM,CAAC;KACtB;IAuCD;;OAEG;IACH,eAAe,IAAI;QAAE,WAAW,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,CAAA;KAAE;IA+C/D;;OAEG;IACH,sBAAsB,IAAI;QAAE,mBAAmB,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,CAAA;KAAE;IAiC9E;;;;;;OAMG;IACH,sBAAsB,CAAC,OAAO,EAAE;QAC9B,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,YAAY,CAAC,EAAE,OAAO,CAAC;KACxB,GAAG,KAAK,CAAC;QACR,WAAW,EAAE,MAAM,CAAC;QACpB,SAAS,EAAE,MAAM,CAAC;QAClB,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;QACzB,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;QAC1B,WAAW,EAAE,MAAM,GAAG,IAAI,CAAC;QAC3B,UAAU,EAAE,MAAM,CAAC;QACnB,IAAI,EAAE,MAAM,CAAC;QACb,WAAW,EAAE,mBAAmB,CAAC;KAClC,CAAC;IA4CF;;;;OAIG;IACH,OAAO,CAAC,kBAAkB;IAW1B,SAAS,IAAI;QACX,cAAc,EAAE,MAAM,CAAC;QACvB,mBAAmB,EAAE,MAAM,CAAC;QAC5B,WAAW,EAAE,OAAO,CAAC;QACrB,eAAe,EAAE,MAAM,GAAG,IAAI,CAAC;QAC/B,SAAS,EAAE,MAAM,CAAC;QAClB,YAAY,EAAE,MAAM,GAAG,IAAI,CAAC;QAC5B,WAAW,EAAE,MAAM,CAAC;QACpB,iBAAiB,EAAE,MAAM,CAAC;QAC1B,eAAe,EAAE,OAAO,CAAC;QACzB,mBAAmB,EAAE,MAAM,GAAG,IAAI,CAAC;QACnC,mBAAmB,EAAE,MAAM,CAAC;QAC5B,wBAAwB,EAAE,MAAM,CAAC;QACjC,sBAAsB,EAAE,OAAO,CAAC;QAChC,0BAA0B,EAAE,MAAM,GAAG,IAAI,CAAC;KAC3C;IAyFD,OAAO,CAAC,kBAAkB;CAG3B;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CA2DvD;AAED;;;;GAIG;AACH,wBAAgB,qBAAqB,CAAC,EAAE,EAAE,QAAQ,CAAC,QAAQ,GAAG,MAAM,CAUnE"}
|