Skip to content

Search

txi search is a group of subcommands for querying the index. Three modes are available:

  • txi search fts — full-text (BM25) search across turns.
  • txi search semantic — vector KNN search across chunk embeddings.
  • txi search hybrid — FTS + semantic merged with Reciprocal Rank Fusion (RRF).
txi search fts "release planning"
txi search semantic "how should we sequence the launch?"
txi search hybrid "release planning"

Full-text search

txi search fts "release planning"

turns (4):
  [142#37] 2026-04-22  Riley Stone: we should land the release planning doc by friday
        (Q2 roadmap sync)
  ...

Options:

  • --speaker NAME — filter turn hits by speaker name.
  • --since ISO_DATE / --until ISO_DATE — bound results by conversation date.
  • --limit N / -n N — max hits. Default 20.
  • --config PATH — override the default config file.

Query syntax: passed through to SQLite's FTS5 matcher, so phrase queries ("exact phrase"), prefix matches (plan*), and boolean operators (release AND planning, release NOT marketing) all work.

txi search semantic "how should we sequence the launch?"

chunks (5):
  [142/4081] 2026-04-22  d=0.2103  turns 36-39
        Riley Stone: we should land the release planning doc by friday
        (Q2 roadmap sync)
  ...

The query is embedded with the active embedding provider/model (see Configuration) and matched against chunk_embeddings via sqlite-vec KNN. Distance is the provider's metric (lower is better).

Options:

  • --k N / -n N — number of nearest neighbors. Default 20.
  • --since ISO_DATE / --until ISO_DATE — bound results by conversation date.
  • --conversation ID — restrict to a single conversation.
  • --config PATH — override the default config file.

Run txi sync (or txi embed) at least once before semantic search; vectors are populated as part of the sync pipeline.

txi search hybrid "release planning"

conversations (3):
  [142] 2026-04-22  score=0.0327  [fts,sem]  Q2 roadmap sync
  [98]  2026-03-14  score=0.0163  [sem]      Engineering offsite recap
  [171] 2026-05-02  score=0.0163  [fts]      Friday release check

Hits are grouped by conversation_id and scored with Reciprocal Rank Fusion (1 / (60 + rank)) — a conversation that surfaces in both FTS and semantic results outranks one that surfaces in only one.

Options mirror the FTS and semantic variants: --speaker, --since, --until, --k/-n, --config.

Use hybrid when you want a single ranked list that reflects both keyword and semantic relevance. Use FTS when you need exact-match precision; use semantic when the query is paraphrastic.