feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
"""`/search` core -- module 5 phase 4 (docs/kb/modules/05-faza4-plan.md §4). Kept decoupled
|
|
|
|
|
from FastAPI so it can be unit-tested with fake `conn`/`session` objects, the same style as
|
|
|
|
|
`kb_retrieval`'s own tests, instead of needing a live DB/Ollama behind a TestClient.
|
|
|
|
|
|
|
|
|
|
Response shape (plan §4 exactly): `{"query", "mode", "sol_status", "results": [...]}`, each
|
|
|
|
|
result carrying `dist` un-filtered -- the 0.45/0.55 colour thresholds (plan §7) are a frontend
|
|
|
|
|
concern (Krok 4, out of this step's scope), never applied server-side.
|
feat(kb-query): add search frontend (module 5 phase 4, plan §7, Krok 4)
Krok 4 of the phase-4 plan done ahead of the local-embed-fallback step
(Krok 2, deliberately deferred -- embed stays a plain SOLARIA call, per
task instruction): one FastAPI process now serves both the /search API
and the UI, no separate frontend build (plan §2 decision 4).
- GET / renders a Jinja2 shell; app/static/app.js (vanilla, no build) and
style.css are the whole client. Query -> /search, results grouped by
envelope_id client-side (chunks sorted by dist, <details> fragments).
- Colour thresholds per plan §7: dist<0.45 green, 0.45-0.55 yellow (still
shown with a warning), >0.55 never rendered as an individual result; if
a query ends up with nothing renderable, one "Brak odpowiedzi w KB"
message replaces the list, carrying the best observed dist.
- Paperless hits link out; gmail hits get a "kopiuj Message-ID" button
(there's nothing to link to yet, plan §2 decision 3) plus header
metadata. Cascade/flat toggle defaults to cascade. Footer shows
sol_status, refreshed from /healthz on load and after each search.
- /search gained additive summary/summary_tags fields (document_summary,
haiku track) so the UI can show a document summary as each result
group's header -- non-breaking, existing response shape untouched.
- Tests: app/db.py + app/search.py unit tests (mocked DB/HTTP, no live
deps) cover the new summary join; tests/test_frontend.py drives GET /
and /static/* via TestClient without running the DB-requiring lifespan;
tests/frontend/app.test.js (Node's built-in test runner, no framework)
covers query-URL encoding, threshold colouring, and envelope grouping.
- Verified live: docker build + container against kb-postgres@PIHA over
LAN and Ollama@SOLARIA over Tailscale -- GET / (HTML), /static/app.js,
/healthz, and /search (cascade + flat) all round-tripped correctly,
including real summary/summary_tags data.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:39:46 +02:00
|
|
|
|
|
|
|
|
`summary`/`summary_tags` (document_summary, haiku track) are an additive field added in Krok 4
|
|
|
|
|
for the frontend's per-envelope result header (plan §7) -- `None`/`[]` when the envelope has no
|
|
|
|
|
summary for `summary_model` yet. Purely additive: does not change any field already covered by
|
|
|
|
|
the phase-4 gate's HTTP-equivalence check (plan §9).
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
|
|
|
|
|
Embed fallback (plan §2 decision 2 / §5, `app/fallback.py`): the query embedding is computed
|
|
|
|
|
once via `embed_with_fallback` (SOLARIA, or PIHA if SOLARIA is down/times out), then handed to
|
|
|
|
|
`kb_retrieval`'s `*_retrieve` functions as a plain vector literal -- `flat_query`/`cascade_query`/
|
|
|
|
|
`hybrid_query` (which embed *and* retrieve in one call) are deliberately bypassed here so the
|
|
|
|
|
fallback decision lives entirely in this HTTP layer, per this task's constraint of zero changes
|
|
|
|
|
to `kb_retrieval`'s retrieval logic. `sol_status` in the response is the real outcome of that
|
|
|
|
|
call, not a hardcoded "up".
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
"""
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
import aiohttp
|
|
|
|
|
import asyncpg
|
|
|
|
|
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
from kb_retrieval.embed import _vector_literal
|
|
|
|
|
from kb_retrieval.retrieval import cascade_retrieve, flat_retrieve, hybrid_retrieve
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
|
feat(kb-query): add search frontend (module 5 phase 4, plan §7, Krok 4)
Krok 4 of the phase-4 plan done ahead of the local-embed-fallback step
(Krok 2, deliberately deferred -- embed stays a plain SOLARIA call, per
task instruction): one FastAPI process now serves both the /search API
and the UI, no separate frontend build (plan §2 decision 4).
- GET / renders a Jinja2 shell; app/static/app.js (vanilla, no build) and
style.css are the whole client. Query -> /search, results grouped by
envelope_id client-side (chunks sorted by dist, <details> fragments).
- Colour thresholds per plan §7: dist<0.45 green, 0.45-0.55 yellow (still
shown with a warning), >0.55 never rendered as an individual result; if
a query ends up with nothing renderable, one "Brak odpowiedzi w KB"
message replaces the list, carrying the best observed dist.
- Paperless hits link out; gmail hits get a "kopiuj Message-ID" button
(there's nothing to link to yet, plan §2 decision 3) plus header
metadata. Cascade/flat toggle defaults to cascade. Footer shows
sol_status, refreshed from /healthz on load and after each search.
- /search gained additive summary/summary_tags fields (document_summary,
haiku track) so the UI can show a document summary as each result
group's header -- non-breaking, existing response shape untouched.
- Tests: app/db.py + app/search.py unit tests (mocked DB/HTTP, no live
deps) cover the new summary join; tests/test_frontend.py drives GET /
and /static/* via TestClient without running the DB-requiring lifespan;
tests/frontend/app.test.js (Node's built-in test runner, no framework)
covers query-URL encoding, threshold colouring, and envelope grouping.
- Verified live: docker build + container against kb-postgres@PIHA over
LAN and Ollama@SOLARIA over Tailscale -- GET / (HTML), /static/app.js,
/healthz, and /search (cascade + flat) all round-tripped correctly,
including real summary/summary_tags data.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:39:46 +02:00
|
|
|
from app.db import fetch_envelopes, fetch_summaries
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
from app.fallback import SolCircuitBreaker, embed_with_fallback
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
from app.links import build_result
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def run_search(
|
|
|
|
|
conn: asyncpg.Connection,
|
|
|
|
|
session: aiohttp.ClientSession,
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
breaker: SolCircuitBreaker,
|
|
|
|
|
solaria_url: str,
|
|
|
|
|
piha_url: str,
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
query_text: str,
|
|
|
|
|
mode: str,
|
|
|
|
|
embed_model: str,
|
|
|
|
|
summary_model: str,
|
|
|
|
|
) -> dict:
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
embedding, sol_status = await embed_with_fallback(
|
|
|
|
|
breaker, session, solaria_url, piha_url, embed_model, query_text
|
|
|
|
|
)
|
|
|
|
|
query_vector = _vector_literal(embedding)
|
|
|
|
|
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
if mode == "flat":
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
chunks = await flat_retrieve(conn, query_vector) # flat_retrieve returns a plain list
|
feat(kb-retrieval,kb-query): add hybrid retrieval mode (faza mailowa Krok 3)
Mail (gmail) envelopes never get a document_summary (Decyzja 6 -- a mail
"summary" would usually be longer than the mail itself), so they're invisible
to the cascade's stage-1 pre-filter. hybrid_retrieve runs the existing
cascade for summarized sources (paperless) and, in parallel, a direct chunk
scan restricted to summaryless_sources (gmail), merging both by dist -- same
embedder/cosine space, so the merge is a plain sort, no re-normalization.
hybrid_query mirrors cascade_query (one shared query embed).
kb-query: mode pattern extended to ^(cascade|flat|hybrid)$, /search routes
"hybrid" to hybrid_query. Default mode stays "cascade" until the quality gate
(plan §8) PASSes on the full mail corpus -- flipping the default, and
deploying this to the running kb-query container, are separate follow-ups
for the operator; this task only adds the code path + tests
(docs/kb/modules/05-faza-mailowa-plan.md, §6, Krok 3).
2026-07-22 19:01:21 +02:00
|
|
|
elif mode == "hybrid":
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
chunks = (await hybrid_retrieve(conn, query_vector, summary_model=summary_model))["chunks"]
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
else:
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
chunks = (await cascade_retrieve(conn, query_vector, summary_model=summary_model))["chunks"]
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
|
|
|
|
|
envelope_ids = sorted({c["envelope_id"] for c in chunks})
|
|
|
|
|
envelopes = await fetch_envelopes(conn, envelope_ids)
|
feat(kb-query): add search frontend (module 5 phase 4, plan §7, Krok 4)
Krok 4 of the phase-4 plan done ahead of the local-embed-fallback step
(Krok 2, deliberately deferred -- embed stays a plain SOLARIA call, per
task instruction): one FastAPI process now serves both the /search API
and the UI, no separate frontend build (plan §2 decision 4).
- GET / renders a Jinja2 shell; app/static/app.js (vanilla, no build) and
style.css are the whole client. Query -> /search, results grouped by
envelope_id client-side (chunks sorted by dist, <details> fragments).
- Colour thresholds per plan §7: dist<0.45 green, 0.45-0.55 yellow (still
shown with a warning), >0.55 never rendered as an individual result; if
a query ends up with nothing renderable, one "Brak odpowiedzi w KB"
message replaces the list, carrying the best observed dist.
- Paperless hits link out; gmail hits get a "kopiuj Message-ID" button
(there's nothing to link to yet, plan §2 decision 3) plus header
metadata. Cascade/flat toggle defaults to cascade. Footer shows
sol_status, refreshed from /healthz on load and after each search.
- /search gained additive summary/summary_tags fields (document_summary,
haiku track) so the UI can show a document summary as each result
group's header -- non-breaking, existing response shape untouched.
- Tests: app/db.py + app/search.py unit tests (mocked DB/HTTP, no live
deps) cover the new summary join; tests/test_frontend.py drives GET /
and /static/* via TestClient without running the DB-requiring lifespan;
tests/frontend/app.test.js (Node's built-in test runner, no framework)
covers query-URL encoding, threshold colouring, and envelope grouping.
- Verified live: docker build + container against kb-postgres@PIHA over
LAN and Ollama@SOLARIA over Tailscale -- GET / (HTML), /static/app.js,
/healthz, and /search (cascade + flat) all round-tripped correctly,
including real summary/summary_tags data.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:39:46 +02:00
|
|
|
summaries = await fetch_summaries(conn, envelope_ids, summary_model)
|
|
|
|
|
|
|
|
|
|
results = []
|
|
|
|
|
for chunk in chunks:
|
|
|
|
|
result = build_result(chunk, envelopes.get(chunk["envelope_id"]))
|
|
|
|
|
summary = summaries.get(chunk["envelope_id"])
|
|
|
|
|
result["summary"] = summary["summary"] if summary else None
|
|
|
|
|
result["summary_tags"] = summary["tags"] if summary else []
|
|
|
|
|
results.append(result)
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
"query": query_text,
|
|
|
|
|
"mode": mode,
|
feat(kb-query): active embed fallback SOLARIA→PIHA (module 5 phase 4, plan §2/§5)
Last missing core piece of KB phase 4: kb-query no longer hard-fails /search
when Ollama@SOLARIA is unreachable. app/fallback.py implements the plan's
circuit-breaker exactly (30s cached health probe, 3s hard embed timeout on
SOLARIA, one-shot same-request switch to a new local ollama-piha@PIHA
container on timeout/error). sol_status in /healthz and /search now reflects
the real breaker state instead of a hardcoded "up".
New services/ollama-piha (bge-m3, OLLAMA_KEEP_ALIVE=0, arm64/no-GPU) is the
local fallback leg. Live calibration on PIHA (2026-07-27, normal load):
embed latency 4.2-5.2s, RAM peak ~983MiB against a 2.5GiB ceiling -- both
inside the plan's go-bar, so the fallback is enabled by default rather than
gated behind a flag. Calibration also surfaced and disabled (not removed) a
previously-undocumented orphaned native ollama.service on PIHA that had been
conflicting with the container's port.
The embed-model invariant (query embedding == document_chunk.model) still
enforces once at startup, since both fallback legs share one EMBED_MODEL
constant by construction; a redundant per-request DB check was deliberately
skipped and the invariant is instead proven structurally by test.
retrieval_eval.py gains --transport http (plan §2 decision 6/§9), previously
unimplemented. Verified live: HTTP transport is bit-identical to direct
transport against the same live SOLARIA (0 mismatches), and a live sol-down
simulation (kb-query's own OLLAMA_URL pointed at a dead address, no other
Ollama consumer touched) shows the PIHA fallback answering with the same
hit@3 gate outcome and dist within ~3e-4 of the SOLARIA baseline.
Zero changes to DB schema or kb_retrieval's retrieval logic -- only the
embed + health layer, per task constraints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-27 18:57:46 +02:00
|
|
|
"sol_status": sol_status,
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
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>
2026-07-22 16:06:18 +02:00
|
|
|
"results": results,
|
|
|
|
|
}
|