---
title: "Search a knowledge base"
method: POST
path: "/v1/retrieve"
tags: ["Products"]
---

# Search a knowledge base

`POST /v1/retrieve`

## Request

- Base URL: `https://api.algenta.ai`
- URL: `https://api.algenta.ai/v1/retrieve`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-API-Key`

Search documents or a connected data source and get ranked, relevant results.

Combines BM25 keyword search, dense vector similarity, and cross-encoder reranking. No setup required — pass documents inline or connect a data source.

## Request body

- RetrieveRequest: Search your knowledge base and get ranked, relevant results. Plug-and-play enterprise search and RAG pipeline. Pass documents inline or reference a connected collection.
  - `query` string, required: What are you looking for?
  - `documents` RetrieveDocument[], nullable: Documents to search (inline mode)
    - `id` string, nullable
    - `content` string, required
    - `metadata` object, nullable
  - `collection_id` string, nullable: ID of a connected data source to search
  - `top_k` integer: Number of results to return
  - `rerank` boolean: Apply cross-encoder reranking for higher accuracy

## Response `200`

Successful Response

- RetrieveResponse
  - `retrieval_id` string, required
  - `query` string, required
  - `results` RetrieveResult[], required
    - `rank` integer, required
    - `document_id` string, nullable, required
    - `content` string, required
    - `relevance_score` number, required
    - `snippet` string, required
  - `total_searched` integer, required
  - `latency_ms` number, required

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/codna/apis/algenta-api.md) · [All operations](https://skmtc.dev/codna/apis/algenta-api/llms.txt) · [OpenAPI document](https://skmtc.dev/codna/apis/algenta-api/revisions/35d30f84a5df?raw)