AI Gateway · Component · embeddings-reranking
Embedding and rerank APIs
What it does
Route embedding and document reranking calls, with embedding batching and usage accounting.
Core pattern
Batched text embeddings + candidate reranking
- Input
- Texts or query/document candidates
- Output
- Vectors or reranked results
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| model | — | — | — |
| input_batch | array | — | — |
| query | string | — | — |
| top_n | integer | 1 | 1–1000000 |
| provider_supported_embedding_options | — | — | — |
Maturity and limits
Controllers, normalizers and priced batching implementations. Static source inspection only; no runtime, provider, deployment or test-pass claim.
config with credentials present. MIT; retain notices. Provider compatibility is configuration-dependent; metadata/privacy and optional payload plugins need review. Static inspection only.
Used in pipelines
Industry tags
- Legal servicesTransferable use
For clause lookup in an authorized contract library, use batched text embeddings followed by candidate reranking.
Skills pack
Contract scaffold and deterministic mock
Download · 11KBSHA-256 b2a402e000e16e7caa9eb7f0739e5737b62183da5821cd18dce7783b5a66ba39
Related components
-
Image generation, editing, upscaling and prediction jobs
Image generation or masked edits + async result tracking
Working 1 pipeline -
Speech transcription and audio translation adapters
Audio transcription or translation + language and format controls
Working 1 pipeline -
Asynchronous video generation and retained media
Async media requests + result polling and usage records
Working 1 pipeline -
Web search and research synthesis
Search request aggregation + source-linked research output
Working 1 pipeline