Expand description
chunk-to-chunk graph runtime (G1). mirrors ann: a flat csr is parsed
off the graph_adjacency (0x0C) section at open time and walked with zero
allocation. bounded_bfs GENERATES candidate chunk ordinals seeded from
the exact-cosine top-k; the candidates are handed to the SAME mandatory
exact rerank (score_subset) so a graph edge can never leak into a
returned score. recall stays f32::NAN (we never lie).
Structs§
- CsrIndex
- flat csr adjacency over chunk ordinals.
offsets[node..node+1]bounds node’s run inneighbors(andedge_types), so one node’s neighbors are a contiguous&[u32]slice. - Traversal
- reusable traversal scratch. allocate once per
CsrIndex, reuse across queries;bounded_bfsbumps the generation so stale stamps read as unvisited without clearing the buffer.