Ilker ManapandClaude Opus 5.5 9c675e7293 Knowledge bases at scale: halfvec, a text index per collection, ef_search raised to the candidates wanted ...

A search asking for more than 10 passages got at most 40 candidates from
HNSW, pgvector's default ef_search. The full-text arm scored every chunk
holding a word of the question before limiting, over the whole
organization's GIN index; it now takes candidates by ts_rank from the
collection's own partial index and scores those. New collections index
halfvec on pgvector 0.7 and later (up to 4000 dimensions).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-08 22:08:29 +02:00

..

admin-api.md

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

admin-api.openapi.json

Trained adapters published, private to their owners like the knowledge bases they come from

2026-10-08 21:30:50 +02:00

choosing-models.md

Manage people and the tenancy tree, from the web and the CLI

2026-09-28 16:26:39 +02:00

clients.md

serve: tool calls declared, slots that hold the context, longer answers

2026-10-05 09:30:40 +02:00

console.md

Collections a part of the tree answers from when a request names none

2026-10-08 15:52:43 +02:00

data.md

Merge C18 offline bundles and the Helm chart

2026-10-05 00:15:47 +02:00

development.md

Docs: one way in — quick-install starts at the setup screens, quickstart becomes development, install.md no longer says engines are yours to install

2026-10-04 17:32:54 +02:00

fabrics.md

Measure two nodes' fabric rail by rail: llmgw ctl fabric-test

2026-09-29 21:29:23 +02:00

facility-aware-placement.md

Facility-aware placement: racks, PDUs, holds and power caps

2026-10-05 01:17:49 +02:00

guardrails.md

Qwen3Guard is the judge, and judges on a GPU and on CPUs are asked in turn

2026-10-08 10:22:47 +02:00

install.md

The store's PostgreSQL sized to its machine's memory

2026-10-08 21:48:53 +02:00

knowledge.md

Knowledge bases at scale: halfvec, a text index per collection, ef_search raised to the candidates wanted

2026-10-08 22:08:29 +02:00

kubernetes.md

Offline sites and Kubernetes: llmgw bundle create, import and trust, offline.mirror, server init --bundle; a Helm chart for the control plane

2026-10-05 00:13:39 +02:00

node-onboarding.md

Add a node with one command: llmgw node add, with a terminal screen

2026-09-29 19:33:47 +02:00

onboarding.md

A forgotten password is set through a one-time link

2026-10-07 13:20:11 +02:00

quick-install.md

Qwen3Guard is the judge, and judges on a GPU and on CPUs are asked in turn

2026-10-08 10:22:47 +02:00

reference.md

Trained adapters published, private to their owners like the knowledge bases they come from

2026-10-08 21:30:50 +02:00