FTS5
FTS5 is a full-text search extension module built into SQLite. It accelerates text matching through an inverted index and supports boolean queries, phrase searches, and prefix matching. The module has no external dependencies and is lightweight, and it provides very fast query performance.
Timeline (last 90 days)
DevWhisper stores transcripts in a local SQLite database and supports full-text search via FTS5.
Benchmarking on a frozen snapshot of 517 facts with 79 queries (55 exact, 12 paraphrased, 6 third-party relevant, 6 with no expected answer, with hit metrics based on 73 answerable queries): without embeddings and without keywords, overall Hit@1 was 84.9% and paraphrase@1 was 33.3%; without embeddings and with keywords, 90.4% and 66.7%; with embeddings and without keywords, 87.7% and 41.7%; with embeddings and with keywords, 91.8% and 66.7%.
In the local SQLite fact storage, FTS5 provides an inverted index for lexical retrieval, and a prefetch mechanism injects up to 5 facts into context per turn.
The seven-layer architecture includes: permanent memory (Markdown), fact storage (SQLite+FTS5+HRR+embeddings), technical wiki (Markdown), procedural memory (skills and scripts), history (SQLite and text search), compression (context summarization), and preservation (backup and restore).
PentaCore bundles the all-MiniLM-L6-v2 embedding model and supports exact word search (FTS5) and semantic search.
Chat history can be stored in SQLite and searched with FTS5 full-text indexing; it can also be embedded and stored in another collection in ChromaDB, but care must be taken to distinguish the document collection from the conversation collection to avoid retrieval contamination.
SQLite's built-in FTS5 full-text search engine and R*Tree spatial index are themselves implementations of virtual tables.
When the embedding service is unavailable, session-indexer automatically falls back to FTS5's BM25 full-text search.
FTS5 (Full-Text Search version 5) is a full-text search extension built into SQLite starting from version 3.9.0 (2015).
FTS5 is a full-text search extension built into SQLite starting from version 3.9.0 (2015) and is an upgrade over FTS3/FTS4.
7 more timeline events
All Facts (19)
Hermes Agent使用数据库的FTS5扩展做全文索引进行历史对话检索
85%UnverifiedContext Mode uses an SQLite database and the FTS5 full-text search engine to track 26 types of events, including file reads and writes, Git operations, task status, error messages, and user decisions.
60%UnverifiedDevWhisper stores transcripts in a local SQLite database and supports full-text search via FTS5.
50%UnverifiedThe seven-layer architecture includes: permanent memory (Markdown), fact storage (SQLite+FTS5+HRR+embeddings), technical wiki (Markdown), procedural memory (skills and scripts), history (SQLite and text search), compression (context summarization), and preservation (backup and restore).
50%UnverifiedIn the local SQLite fact storage, FTS5 provides an inverted index for lexical retrieval, and a prefetch mechanism injects up to 5 facts into context per turn.
50%UnverifiedBenchmarking on a frozen snapshot of 517 facts with 79 queries (55 exact, 12 paraphrased, 6 third-party relevant, 6 with no expected answer, with hit metrics based on 73 answerable queries): without embeddings and without keywords, overall Hit@1 was 84.9% and paraphrase@1 was 33.3%; without embeddings and with keywords, 90.4% and 66.7%; with embeddings and without keywords, 87.7% and 41.7%; with embeddings and with keywords, 91.8% and 66.7%.
50%UnverifiedPentaCore bundles the all-MiniLM-L6-v2 embedding model and supports exact word search (FTS5) and semantic search.
50%UnverifiedChat history can be stored in SQLite and searched with FTS5 full-text indexing; it can also be embedded and stored in another collection in ChromaDB, but care must be taken to distinguish the document collection from the conversation collection to avoid retrieval contamination.
50%UnverifiedSQLite's built-in FTS5 full-text search engine and R*Tree spatial index are themselves implementations of virtual tables.
50%UnverifiedWhen the embedding service is unavailable, session-indexer automatically falls back to FTS5's BM25 full-text search.
50%UnverifiedFTS5 (Full-Text Search version 5) is a full-text search extension built into SQLite starting from version 3.9.0 (2015).
50%UnverifiedFTS5 is a full-text search extension built into SQLite starting from version 3.9.0 (2015) and is an upgrade over FTS3/FTS4.
50%UnverifiedThe solution uses the broadcast date as the primary key to associate program listings, filenames, and audio files together.
50%UnverifiedFor personal projects and small-to-medium-scale data management, SQLite FTS5 is more suitable than large-scale search infrastructure such as Elasticsearch or vector databases.
50%UnverifiedFTS5 is based on the inverted index principle, recording the documents and positions where each term appears using terms as keys, which is the same underlying principle as search engines.
50%UnverifiedFTS5 默认使用 BM25 排序算法，综合考虑词频、逆文档频率和文档长度归一化
50%Unverified对于事实性、关键词导向的智能体记忆场景，基于关键词的 FTS5 检索完全够用，且响应更快、成本几乎为零
50%UnverifiedFTS5 依赖字面匹配，当查询词与存储内容用词不同但语义相近时可能漏检，是纯全文方案的固有局限
50%Unverified在实际基准测试中，FTS5 对百万级文档的检索延迟通常在个位数毫秒级别
50%