8de94eba08
Some checks failed
lakehouse/auditor 16 blocking issues: cloud: claim not backed — "Verified end-to-end via playwright on devop.live/lakehouse:"
stronger local rung is now the small-model-pipeline tier-1 default across both Rust legacy + Go rewrite (cf. golangLAKEHOUSE phase 1). same JSON-clean property as qwen2.5, more capacity. ollama still serves both side-by-side; rollback is a 4-line revert if a workload regresses. active-default sites: - lakehouse.toml [ai] gen_model + rerank_model → qwen3.5:latest - mcp-server/observer.ts diagnose call (Phase 44 /v1/chat path) → qwen3.5:latest - mcp-server/index.ts model roster doc → qwen3.5:latest first - crates/vectord/src/rag.rs ContinuableOpts + RagResponse.model → qwen3.5:latest skipped: execution_loop/mod.rs comments describing historic qwen2.5 tool_call quirks — those are documentation of past behavior, not active defaults. data/_catalog/profiles/*.json are runtime-generated (gitignored), not in scope for tracked changes. cargo check -p vectord: clean. no behavioral change in the audit pipeline — same JSON-clean local model, same think=Some(false) posture, just stronger upstream. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
86 lines
2.5 KiB
TOML
86 lines
2.5 KiB
TOML
# Lakehouse Configuration
|
|
|
|
[gateway]
|
|
host = "0.0.0.0"
|
|
port = 3100
|
|
|
|
[storage]
|
|
root = "./data"
|
|
profile_root = "./data/_profiles"
|
|
rescue_bucket = "rescue"
|
|
|
|
[[storage.buckets]]
|
|
name = "primary"
|
|
backend = "local"
|
|
root = "./data"
|
|
|
|
[[storage.buckets]]
|
|
name = "rescue"
|
|
backend = "local"
|
|
root = "./data/_rescue"
|
|
|
|
[[storage.buckets]]
|
|
name = "testing"
|
|
backend = "local"
|
|
root = "./data/_testing"
|
|
|
|
# S3 bucket via MinIO. The name "s3:lakehouse" is the convention
|
|
# lance_backend.rs uses to emit s3:// URIs for Lance datasets.
|
|
# Credentials resolved via environment (AWS_ACCESS_KEY_ID etc) or
|
|
# the secrets provider.
|
|
[[storage.buckets]]
|
|
name = "s3:lakehouse"
|
|
backend = "s3"
|
|
bucket = "lakehouse"
|
|
endpoint = "http://localhost:9000"
|
|
region = "us-east-1"
|
|
secret_ref = "minio-lakehouse"
|
|
|
|
[catalog]
|
|
# Manifests persisted to object storage under this prefix
|
|
manifest_prefix = "_catalog/manifests"
|
|
|
|
[query]
|
|
# max_rows_per_query = 10000
|
|
|
|
[sidecar]
|
|
url = "http://localhost:3200"
|
|
|
|
[ai]
|
|
embed_model = "nomic-embed-text"
|
|
# Local-tier defaults bumped 2026-04-30: qwen3.5:latest is the
|
|
# stronger local rung in the 5-loop substrate (per
|
|
# project_small_model_pipeline_vision.md). Same JSON-clean property
|
|
# as qwen2.5, more capacity. Ollama still serves both — bump back
|
|
# in this file if a workload regressed.
|
|
gen_model = "qwen3.5:latest"
|
|
rerank_model = "qwen3.5:latest"
|
|
|
|
[auth]
|
|
enabled = false
|
|
# api_key = "changeme"
|
|
|
|
[observability]
|
|
# Export traces to stdout (set to "otlp" for OpenTelemetry collector)
|
|
exporter = "stdout"
|
|
service_name = "lakehouse"
|
|
|
|
[agent]
|
|
# Phase 16.2 — background autotune agent. Opt-in: set enabled = true to
|
|
# let the agent continuously propose + trial HNSW configs and auto-promote
|
|
# winners. Defaults are conservative so it stays out of the way of live
|
|
# search traffic on shared Ollama.
|
|
enabled = true
|
|
cycle_interval_secs = 120 # periodic wake if no triggers
|
|
cooldown_between_trials_secs = 10 # min gap between trials
|
|
min_recall = 0.9 # never promote below this
|
|
max_trials_per_hour = 20 # hard budget cap
|
|
|
|
# Model roster — available for profile hot-swap
|
|
# qwen3.5:latest: stronger local rung — JSON-clean, 8K+ context,
|
|
# default for gen_model and rerank_model
|
|
# qwen3: 8.2B, 40K context, thinking+tools, best for reasoning tasks
|
|
# qwen2.5: 7B, 8K context, fast — kept loaded for the 2026-04 era
|
|
# comparison runs; new defaults use qwen3.5:latest
|
|
# nomic-embed-text: 137M, embedding-only, used by all profiles
|