73 lines
2.8 KiB
Python
73 lines
2.8 KiB
Python
|
"""Per-source result shaping for `/search` -- module 5 phase 4 (docs/kb/modules/05-faza4-plan.md,
|
||
|
|
§4 response shape, §6/decision 3 links). `kb_retrieval.retrieval` only ever touches
|
||
|
|
`document_chunk`/`document_summary`; the join to `envelope` (for `source` and link/metadata
|
||
|
|
fields) is new HTTP-layer code that belongs to kb-query, not the shared retrieval package.
|
||
|
|
|
||
|
|
Paperless link format verified live 2026-07-22: `curl -I https://paper.kapala.org/documents/1/details`
|
||
|
|
-> 302 to `/accounts/login/?next=/documents/1/details` (unauthenticated, but confirms the route
|
||
|
|
exists and is handled by the Angular app, not a 404) -- the plan's candidate format.
|
||
|
|
|
||
|
|
Gmail has nothing to link to (plan §2 decision 3: `envelope_id` **is** the Message-ID already,
|
||
|
|
nothing to extract) -- `mail_ui_url` stays a reserved `null` until kb-00's future mail-UI.
|
||
|
|
"""
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from typing import Optional
|
||
|
|
|
||
|
|
PAPERLESS_LINK_TEMPLATE = "https://paper.kapala.org/documents/{doc_id}/details"
|
||
|
|
|
||
|
|
|
||
|
|
def _extract_headers(entities: list) -> dict:
|
||
|
|
for entity in entities or []:
|
||
|
|
if isinstance(entity, dict) and entity.get("type") == "headers":
|
||
|
|
return entity
|
||
|
|
return {}
|
||
|
|
|
||
|
|
|
||
|
|
def _format_from(headers: dict) -> Optional[str]:
|
||
|
|
frm = headers.get("from")
|
||
|
|
if not isinstance(frm, dict):
|
||
|
|
return None
|
||
|
|
name = frm.get("name")
|
||
|
|
address = frm.get("address")
|
||
|
|
if name and address:
|
||
|
|
return f"{name} <{address}>"
|
||
|
|
return address or name
|
||
|
|
|
||
|
|
|
||
|
|
def _paperless_link(envelope_id: str) -> str:
|
||
|
|
# envelope_id is "paperless:<id>" (paperless_adapter.py:126) -- the raw Paperless doc id
|
||
|
|
# is everything after the first colon.
|
||
|
|
doc_id = envelope_id.split(":", 1)[1] if ":" in envelope_id else envelope_id
|
||
|
|
return PAPERLESS_LINK_TEMPLATE.format(doc_id=doc_id)
|
||
|
|
|
||
|
|
|
||
|
|
def build_result(chunk: dict, envelope: Optional[dict]) -> dict:
|
||
|
|
"""One `/search` result item: retrieval hit (`chunk`) + its envelope metadata (`envelope`,
|
||
|
|
`None` if the envelope vanished between chunk-embedding and this query -- shouldn't happen
|
||
|
|
on a read-only corpus, but the join must not crash on it)."""
|
||
|
|
source = (envelope or {}).get("source", "unknown")
|
||
|
|
result = {
|
||
|
|
"envelope_id": chunk["envelope_id"],
|
||
|
|
"source": source,
|
||
|
|
"dist": chunk["dist"],
|
||
|
|
"chunk_index": chunk["chunk_index"],
|
||
|
|
"text": chunk["text"],
|
||
|
|
}
|
||
|
|
|
||
|
|
if source == "paperless":
|
||
|
|
result["link"] = _paperless_link(chunk["envelope_id"])
|
||
|
|
return result
|
||
|
|
|
||
|
|
if source == "gmail":
|
||
|
|
headers = _extract_headers((envelope or {}).get("entities", []))
|
||
|
|
result["subject"] = headers.get("subject")
|
||
|
|
result["from"] = _format_from(headers)
|
||
|
|
result["date"] = headers.get("date_raw")
|
||
|
|
result["link"] = None
|
||
|
|
result["mail_ui_url"] = None
|
||
|
|
return result
|
||
|
|
|
||
|
|
result["link"] = None
|
||
|
|
return result
|