1bee0e4969
Pulled qwen3 (8.2B, 40K context, thinking, tool-calling). Created agent-qwen3 profile. Ran structured plan: 5 contracts (16/16 filled via hybrid), 5 intelligence questions (2/5 — same RAG counting gap). Key playbook entry generated: "count/aggregation questions must use /sql not /search. RAG returns 5 chunks from 10K — cannot count the full dataset." This routing rule is now in the playbooks database for future agent runs to learn from. Pattern confirmed across qwen2.5, mistral, AND qwen3: the structured matching path (hybrid SQL+vector) is production-ready across all models. The RAG counting gap is a routing problem, not a model problem — the fix is query classification, not a better model. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
79 lines
2.0 KiB
TOML
79 lines
2.0 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"
|
|
gen_model = "qwen2.5"
|
|
rerank_model = "qwen2.5"
|
|
|
|
[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: 8.2B, 40K context, thinking+tools, best for reasoning tasks
|
|
# qwen2.5: 7B, 8K context, fast, good for SQL generation
|
|
# mistral: 7B, 8K context, good for general generation
|
|
# nomic-embed-text: 137M, embedding-only, used by all profiles
|