# Filters, rewriting and compression

Inspect typed filters, cosine MMR and bounded model transformations.

CLI version: 0.2.1 · [Read online](<https://ragvidence.medo-id.com/docs/advanced-techniques>)

## Typed metadata filters

**filters.json**

```
{"all":[{"field":"record_metadata.product","op":"eq","value":"Orion"}]}
```

eq, in, gt, gte, lt and lte combine with AND. Missing fields/type mismatches exclude a source; CSV values remain strings. Strings compare lexically without date/version conversion. Filters apply before ranking and parent expansion cannot reintroduce excluded sources.

## Cosine MMR

MMR trades query cosine relevance against maximum cosine similarity to already selected candidates. --mmr-lambda controls that balance; --mmr-candidates caps the pool. It needs an embedding provider, even after lexical ranking. Diversity can displace needed similar passages.

## Bounded model queries

rewrite requests one query; auto-multi-query requests up to three by default, configurable 1–8. Set --rewrite-model and --rewrite-provider, with RAGVIDENCE\_TRANSFORM\_BASE\_URL/API\_KEY for your service. The model receives the question and instruction, without corpus, answers or reviewed evidence IDs. Strict JSON is required. --rewrite-failure original explicitly permits a disclosed fallback; default fail does not invent a successful result.

## Exact-span compression

**Terminal**

```
ragvi compress ./docs --questions ./questions.txt --compression-max-spans 2
```

The default sentence selector ranks punctuation/newline spans by lexical question-word overlap, keeping up to two positive-overlap spans per source. An explicit --compression-model can select exact offsets from candidate bodies. No added summary earns evidence credit. Removed conditions lose credit even when an output passes validation.

## Model and suite bounds

Timeouts, output caps, prompt/JSON/query sizes and suite call bounds are validated. Invalid model output fails unless explicit original-text fallback is selected and disclosed. The CLI does not supply the server, API access or an answer correctness judge.

- [Full schemas, provider settings, bounds and composition](<https://github.com/Medo-ID/ragvidence/blob/v0.2.1/docs/portable-advanced-techniques.md>)
