Skip to content

Vector Database

Vector Database dashboard - four KPI cards (Traces with RAG, Vector queries, Avg top_k, Avg query latency) and charts for Operations / minute stacked, Query latency p50/p95/p99, top_k distribution histogram, Similarity threshold distribution, DB systems donut, Avg returned docs by db (Recent searches sits below these)

Vector Database - Similarity threshold distribution buckets thresholds into 6 bands (0.0-0.1, 0.1-0.3, ..., 0.9-1.0) so an over-strict threshold is visible without per-query inspection.

Purpose - RAG-side observability. Beyond simple "did the agent retrieve" questions, this tab surfaces retrieval parameters (top_k, similarity threshold) and per-DB returned-doc counts - the indicators that determine RAG quality.

When to look here

  • "Did the agent actually use RAG?" - Traces with RAG count + Vector queries count.
  • "Are queries slow against the configured store?" - Query latency p50 / p95 / p99.
  • "Is top_k being set sensibly?" - top_k distribution (a spike at 1 or above 50 usually indicates an agent miscalibration).
  • "Is the similarity threshold too strict?" - Similarity threshold distribution (everything in 0.9-1.0 → almost no recall).
  • "Multi-store mix?" - DB systems donut (Chroma / Pinecone / SimpleVectorStore / etc.).
  • "How many docs per query, on average?" - Avg returned docs by db.

Data source

Not trace spans: every vector-store operation is recorded in a memory-only operation log (VectorOperationLog) - up to 5000 operations plus the text of the last 20 queries, never written to disk and cleared on restart. Two kinds of search are left out: searches against the dynamic tool-discovery index (Agentic Chat's tool search) and the placeholder "list everything" query the Vector Database screen runs to fill its grid.

Controls

All dashboards share the Observability global settings - time window, refresh interval, custom range. Vector Database has no tab-specific controls beyond those.

KPI cards (four)

Card Shows Source
Traces with RAG Number of chat turns that included a vector query TraceRecord.hasRag true count - set when a document-store query (RAG pipeline, document source, or chat attachment excerpt search) ran during the turn; tool-index searches do not count
Vector queries Number of query operations (adds and deletes appear only in Operations / minute) Operation log, query count
Avg top_k Mean of the requested top_k parameter db.vector.query.top_k attribute averaged
Avg query latency Mean duration of query operations Operation log durations

Charts (seven)

Chart Type Reading
Operations / minute Stacked bar (query / add / delete) Add bursts during document ingestion; query bursts during chat. A pipeline with Multi-Query expansion issues one query per variant, so a single turn can show several
Query latency p50 / p95 / p99 Multi-line, ms, query operations only Tail latency on remote vector stores can be ten-fold higher than SimpleVectorStore
top_k distribution Histogram Distribution of requested k values. Top-K is a per-pipeline setting, so a spread here means different RAG pipelines are in use rather than one value drifting
Similarity threshold distribution Histogram, 6 bands ([0.0, 0.1) ... [0.9, 1.0]) Where the agent is anchoring relevance - strictness vs recall
DB systems Donut by db.system One backend = single configuration; multiple = mixed stores
Avg returned docs by db Horizontal bar Combined with similarity threshold, this is the retrieval-recall signal
Recent searches List, "last 20, kept in memory only" One line per query: HH:mm:ss · N docs · N ms · <query text> (text cut at 200 characters). Empty state: No searches yet. The text never leaves memory and is gone after a restart

Cross-references