b2379e3275
Module 5 phase 4 step 1 (docs/kb/modules/05-faza4-plan.md, §4): first user-facing HTTP entry point to the KB. FastAPI wrapping kb_retrieval.cascade_query/flat_query — GET /search (query_text -> embed via Ollama@SOLARIA -> cascade/flat -> envelope join -> JSON with per-source links) and GET /healthz. Search API only, no answer synthesis (phase 5) and no server-side dist filtering — the 0.45/0.55 colour thresholds are a frontend concern (plan §7, a later step). Hard startup invariant (plan §2 decision 2): refuses to start unless the configured EMBED_MODEL is present in both document_chunk.model and document_summary.embedding_model. Note the latter: document_summary.model is the LLM that *wrote* the summary (claude-haiku-4-5/gemma3:12b), not the embedder — checked live against kb-postgres@PIHA before writing this, see app/startup.py's docstring. Verified end-to-end with a live docker run: the invariant crash-loops on a mismatched EMBED_MODEL and passes through to a real /search hit against the live corpus with a correct model. Repo-only: no deploy, no npm/OIDC/DNS wiring (plan §8, later step), no local embed fallback (plan §5, later step) — Ollama@SOLARIA is called directly and a failure surfaces as 503, not a crash. Also: scripts/deploy/deploy.sh's gate now builds each service via `docker compose build` instead of a raw `docker build <svc_dir>`, so a service whose docker-compose.yml declares a repo-root build context (needed here to COPY packages/kb-retrieval/, the packages/ Dockerfile convention already documented in CLAUDE.md) resolves the same way in the gate as it does at real deploy time (deploy-node.sh's `docker compose ... up --build`). No behavior change for existing single-context services — verified against llm-gateway's compose file. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
"""kb-postgres access for kb-query beyond what `kb_retrieval.retrieval` covers -- the envelope
|
|
join (`source` + `entities` for link/metadata building, app/links.py) is out of scope for the
|
|
shared retrieval package (module 5 phase 4 plan §4: "to jest nowy kod w warstwie
|
|
HTTP-handlera kb-query, nie zmiana w kb_retrieval")."""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
import asyncpg
|
|
|
|
|
|
async def create_pool(dsn: str) -> asyncpg.Pool:
|
|
return await asyncpg.create_pool(dsn, min_size=1, max_size=5)
|
|
|
|
|
|
def _decode_jsonb(value: object) -> object:
|
|
"""asyncpg may return jsonb as a str or an already-decoded object."""
|
|
if value is None:
|
|
return None
|
|
if isinstance(value, str):
|
|
return json.loads(value)
|
|
return value
|
|
|
|
|
|
async def fetch_envelopes(conn: asyncpg.Connection, envelope_ids: list[str]) -> dict[str, dict]:
|
|
"""Batch-fetch `source`/`entities` for a set of chunk hits, keyed by envelope id."""
|
|
if not envelope_ids:
|
|
return {}
|
|
rows = await conn.fetch(
|
|
"SELECT id, source, entities FROM envelope WHERE id = ANY($1::text[])",
|
|
envelope_ids,
|
|
)
|
|
return {
|
|
r["id"]: {"source": r["source"], "entities": _decode_jsonb(r["entities"]) or []}
|
|
for r in rows
|
|
}
|