| Metadata | Value |
|---|---|
| Status | Active |
| Version | 1.0.0 |
| Last Updated | 2026-09-10 |
| Author | Sangeetha Grantha Team |
| Document Type | Evidence record |
[!NOTE] Historical evidence: results, counts, commands, and observations below belong to the original work described here. The editorial update date is not a new test or corpus verification. For present behavior, use embedding and search operations.
Execution Timestamp: 2026-09-08 06:48:40 UTC
Model: gemini-embedding-2 (768-D Matryoshka Representation Learning)
Database: PostgreSQL 18 with pgvector HNSW index
| Metric | Value |
|---|---|
| Total Krithis in Catalogue | 1226 |
| Krithis Target in this Run | 1 |
| Krithis Processed Successfully | 0 |
| Krithis Failed | 1 |
| New Embeddings Generated | 0 |
| Embeddings Skipped (Unchanged) | 0 |
| Obsolete Documents Retired | 0 |
| Elapsed Duration | 0m 0s |
| Embedding Rate | 0.00 docs/sec |
| Estimated Tokens Consumed | ~0 |
| Estimated API Cost | ~$0.0000 USD |
| Table | Total Rows |
|---|---|
search_documents (Composition Overviews) |
1226 |
search_documents (Section Passages) |
25809 |
document_embeddings (Active Vectors) |
27035 |
| HNSW Cosine Index Status | idx_doc_embeddings_hnsw_cosine (110 MB) |
Verification of vector retrieval against live embedded krithis:
Persisted to /Users/seshadri/project/sangeetha-grantha/tools/krithi-extract-enrich-worker/reports/embedding_failures_20260908_121840.json; exit status was non-zero.
| Krithi ID | Title | Error |
|---|---|---|
3747ba8d-2df1-4c7f-b272-20ba3c81a5d8 |
Chera Raavademi | 400 INVALID_ARGUMENT. {‘error’: {‘code’: 400, ‘message’: ‘API key not valid. Please pass a valid API key.’, ‘status’: ‘INVALID_ARGUMENT’, ‘details’: [{‘@type’: ‘type.googleapis.com/google.rpc.ErrorInfo’, ‘reason’: ‘API_KEY_INVALID’, ‘domain’: ‘googleapis.com’, ‘metadata’: {‘service’: ‘generativelanguage.googleapis.com’}}, {‘@type’: ‘type.googleapis.com/google.rpc.LocalizedMessage’, ‘locale’: ‘en-US’, ‘message’: ‘API key not valid. Please pass a valid API key.’}]}} |
POST /v1/search/hybrid and POST /v1/search/semantic are live and querying this dataset./krithis) provides instant toggling between Lexical, Hybrid (RRF), and Semantic modes.