a640cf1455
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).
66 lines
2.5 KiB
Python
66 lines
2.5 KiB
Python
"""`/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.
|
|
|
|
`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).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import aiohttp
|
|
import asyncpg
|
|
|
|
from kb_retrieval.retrieval import cascade_query, flat_query, hybrid_query
|
|
|
|
from app.db import fetch_envelopes, fetch_summaries
|
|
from app.links import build_result
|
|
|
|
|
|
async def run_search(
|
|
conn: asyncpg.Connection,
|
|
session: aiohttp.ClientSession,
|
|
ollama_url: str,
|
|
query_text: str,
|
|
mode: str,
|
|
embed_model: str,
|
|
summary_model: str,
|
|
) -> dict:
|
|
if mode == "flat":
|
|
retrieval = await flat_query(conn, session, ollama_url, query_text, embed_model=embed_model)
|
|
elif mode == "hybrid":
|
|
retrieval = await hybrid_query(
|
|
conn, session, ollama_url, query_text,
|
|
summary_model=summary_model, embed_model=embed_model,
|
|
)
|
|
else:
|
|
retrieval = await cascade_query(
|
|
conn, session, ollama_url, query_text,
|
|
summary_model=summary_model, embed_model=embed_model,
|
|
)
|
|
|
|
chunks = retrieval["chunks"]
|
|
envelope_ids = sorted({c["envelope_id"] for c in chunks})
|
|
envelopes = await fetch_envelopes(conn, envelope_ids)
|
|
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)
|
|
|
|
return {
|
|
"query": query_text,
|
|
"mode": mode,
|
|
"sol_status": "up", # reaching this point means the embed call above succeeded
|
|
"results": results,
|
|
}
|