Sharang ParnerkarandClaude Fable 5 617b2df75e fix(llm): chunk embed() requests under the backend batch cap ...

Found while prepping the C5 live test: the embeddings backend
(bge-multilingual-gemma2 via LiteLLM) caps input arrays at 25 per request
("given batch size overflow maximal one", max: 25), but embed() sent the whole
input in a single request. ControlIndex::build embeds the entire master-controls
corpus (~1.8k texts) in one embed() call, and the RAG pipeline batches docs too —
both 500 at scale. Unit tests passed only because they embed <=3 texts.

Fix: embed() now chunks into EMBED_BATCH_SIZE (16) requests and concatenates in
order; empty input short-circuits. Validated live — 1,784 texts over 112 chunked
requests succeed (~70s, one-time + cached by the index).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-21 17:34:17 +02:00

..

rules

feat(controls): B1 — custom semgrep detectors for 4 CRA controls (#218)

2026-07-21 12:31:20 +00:00

src

fix(llm): chunk embed() requests under the backend batch cap

2026-07-21 17:34:17 +02:00

tests

feat(oscal): live assessment endpoint POST /api/v1/oscal/assess (#212)

2026-07-20 19:13:47 +00:00

Cargo.toml

feat: control-driven SAST — LUT + grounded LLM triage over tool findings (#213)

2026-07-21 09:01:51 +00:00