Types¶
Literal aliases for the enum-ish string args, and TypedDicts for
dict-shaped return values. Importing from here gives you IDE
autocomplete on result fields and rejects typos in arguments.
from kglite_docs.types import Verdict, SearchHit
def my_fn(verdict: Verdict) -> list[SearchHit]:
...
Public type aliases.
TypedDicts for the dict-shaped values our methods return, and Literals
for the enum-ish string arguments. Importing from here gives IDE/type-checker
autocomplete on result fields and rejects typos in arguments.
Example::
from kglite_docs.types import Verdict, SearchHit
def my_fn(verdict: Verdict) -> list[SearchHit]:
...
SearchHit ¶
Bases: TypedDict
One row from Corpus.search(). Fields beyond id, score,
type are best-effort — some are added by post-join enrichment and
may be missing when the underlying chunk has unusual state.
DocumentRow ¶
Bases: TypedDict
One row from Corpus.list_documents().
DocumentDetail ¶
Bases: TypedDict
Corpus.get_document() return shape.
SectionRow ¶
Bases: TypedDict
One row from Corpus.list_sections() — the grain between document and
chunk (derived from the PDF outline or top-level headings at ingest).
ChunkDetail ¶
Bases: TypedDict
Corpus.get_chunk() return shape.
SummaryRow ¶
Bases: TypedDict
Corpus.get_summaries() row.
IngestSummary ¶
Bases: TypedDict
Aggregate of Corpus.ingest_dir() results.
PendingOcrRow ¶
Bases: TypedDict
Corpus.list_pending_ocr() row.
OcrStatusRow ¶
Bases: TypedDict
Per-document OCR status (the documents array in ocr_status()).
OcrStatus ¶
Bases: TypedDict
Corpus.ocr_status() return shape.
CoverageDocRow ¶
Bases: TypedDict
Per-document row in coverage_report().
CoverageReport ¶
Bases: TypedDict
Corpus.coverage_report() return shape — honest extraction + embedding
coverage with a human-readable summary.
CorpusStatus ¶
Bases: TypedDict
Corpus.status() — one-call snapshot of the corpus.
TriageMap ¶
Bases: TypedDict
Corpus.triage_map() — aggregated content signals for orientation.
ReviewTicketRow ¶
Bases: TypedDict
One row from Corpus.list_review_queue(). Add target and
events by going through Corpus.get_review_ticket().
ReviewEvent ¶
Bases: TypedDict
One event in a ticket's audit trail.
ReviewTicketDetail ¶
ReviewStats ¶
Bases: TypedDict
Corpus.review_stats() return shape.
AgentRow ¶
Bases: TypedDict
Corpus.list_agents() row — identity + counters, no template.
AgentConfig ¶
Bases: TypedDict
Corpus.get_agent() return shape — full template + counters.
tools and context are hydrated from the underlying JSON
properties so callers receive a real list / dict, not strings.
AgentActivity ¶
Bases: TypedDict
Corpus.agent_activity() return shape — what an agent has
done, optionally scoped to one target node.
TagRow ¶
Bases: TypedDict
Corpus.list_tags() row.
ContextItem ¶
Bases: TypedDict
One entry in Corpus.compose_context()['items'].
ComposedContext ¶
Bases: TypedDict
Corpus.compose_context() return shape.
GroundingSentence ¶
Bases: TypedDict
One sentence's grounding analysis inside check_grounding.
ComparisonQueryResult ¶
Bases: TypedDict
Per-query hits from each side of a compare_documents call.
ComparisonResult ¶
Bases: TypedDict
Corpus.compare_documents() return shape.
Side-by-side cross-document retrieval result. For each query in the input list, you get the top hits from each document independently plus a budgeted merged context bundle suitable for handing to a downstream LLM that's writing a comparison.
GroundingReport ¶
Bases: TypedDict
Corpus.check_grounding() return shape.
StudyRow ¶
Bases: TypedDict
One study from Corpus.list_studies() / get_study().
AssessmentRow ¶
Bases: TypedDict
One ranked row in a study ledger.
Ledger ¶
Bases: TypedDict
Corpus.study_ledger() return shape — weight-ranked evidence.
FindingRow ¶
Bases: TypedDict
One cross-chunk Finding from Corpus.list_findings() — a pattern asserted
over a set of chunks.
ReportRow ¶
Bases: TypedDict
A versioned study report from Corpus.get_report().
ConflictRow ¶
Bases: TypedDict
One contested chunk — current supports vs against assessments.
ConflictReport ¶
Bases: TypedDict
Corpus.study_conflicts() return shape.