Files
sim/apps/docs/content/docs/en/tools/airweave.mdx
Ewan Tauran 1e21ec1fa3 feat(airweave): add airweave block (#3079)
* feat(icons): add Airweave icon and update registry with Airweave block and tool

* feat(icons): add Airweave icon and update icon mapping and metadata

* fix(search): update API key header from Authorization to X-API-Key for Airweave search tool

* refactor(icon-mapping): reorder icon imports for consistency and formatting improvements; update airweave block retrieval strategy description formatting; add newline at end of meta.json

* refactor(search): update visibility settings for retrieval strategy and query options to allow access for both users and LLMs
2026-02-06 11:43:06 -08:00

53 lines
2.1 KiB
Plaintext

---
title: Airweave
description: Search your synced data collections
---
import { BlockInfoCard } from "@/components/ui/block-info-card"
<BlockInfoCard
type="airweave"
color="#6366F1"
/>
## Usage Instructions
Search across your synced data sources using Airweave. Supports semantic search with hybrid, neural, or keyword retrieval strategies. Optionally generate AI-powered answers from search results.
## Tools
### `airweave_search`
Search your synced data collections using Airweave. Supports semantic search with hybrid, neural, or keyword retrieval strategies. Optionally generate AI-powered answers from search results.
#### Input
| Parameter | Type | Required | Description |
| --------- | ---- | -------- | ----------- |
| `apiKey` | string | Yes | Airweave API Key for authentication |
| `collectionId` | string | Yes | The readable ID of the collection to search |
| `query` | string | Yes | The search query text |
| `limit` | number | No | Maximum number of results to return \(default: 100\) |
| `retrievalStrategy` | string | No | Retrieval strategy: hybrid \(default\), neural, or keyword |
| `expandQuery` | boolean | No | Generate query variations to improve recall |
| `rerank` | boolean | No | Reorder results for improved relevance using LLM |
| `generateAnswer` | boolean | No | Generate a natural-language answer to the query |
#### Output
| Parameter | Type | Description |
| --------- | ---- | ----------- |
| `results` | array | Search results with content, scores, and metadata from your synced data |
| ↳ `entity_id` | string | Unique identifier for the search result entity |
| ↳ `source_name` | string | Name of the data source \(e.g., "GitHub", "Slack"\) |
| ↳ `md_content` | string | Markdown-formatted content of the result |
| ↳ `score` | number | Relevance score from the search |
| ↳ `metadata` | object | Additional metadata associated with the result |
| ↳ `breadcrumbs` | array | Navigation path to the result within its source |
| ↳ `url` | string | URL to the original content |
| `completion` | string | AI-generated answer to the query \(when generateAnswer is enabled\) |