> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# veryfront/embedding

> Embedding — RAG primitives for chunking, embedding, and similarity search. Provides a facade over AI SDK (embeddings, similarity) and LangChain (text splitting) behind veryfront's own API.

# veryfront/embedding

Embedding — RAG primitives for chunking, embedding, and similarity search. Provides a facade over AI SDK (embeddings, similarity) and LangChain (text splitting) behind veryfront's own API.

## Import

```ts  theme={null}
import {
  chunk,
  clearEmbeddingProviders,
  createUploadHandler,
  embedding,
  loadUpload,
  ragStore,
} from "veryfront/embedding";
```

## Examples

```ts  theme={null}
import { ragStore, createUploadHandler } from "veryfront/embedding";

const store = ragStore({});
export const { POST, GET, DELETE } = createUploadHandler(store);
```

## Exports

### Functions

| Name                        | Description                                                                        |
| --------------------------- | ---------------------------------------------------------------------------------- |
| `chunk`                     | Splits text into overlapping chunks for embedding.                                 |
| `clearEmbeddingProviders`   | Clear all registered embedding providers (for testing).                            |
| `createUploadHandler`       | Creates HTTP route handlers for upload, listing, and deletion.                     |
| `embedding`                 | Creates an embedding facade.                                                       |
| `loadUpload`                | Extracts plain text from various upload formats.                                   |
| `ragStore`                  | Creates a persistent RAG store with lazy embedding and similarity search.          |
| `registerEmbeddingProvider` | Register an embedding provider factory.                                            |
| `resolveEmbeddingModel`     | Resolve a "provider/model" string to an AI SDK EmbeddingModel instance.            |
| `useUploads`                | useUploads hook for managing RAG upload lifecycle.                                 |
| `vectorStore`               | Creates an in-memory vector store with integrated embedding and similarity search. |

### Types

| Name                | Description |
| ------------------- | ----------- |
| `ChunkOptions`      |             |
| `Embedding`         |             |
| `EmbeddingConfig`   |             |
| `RagChunk`          |             |
| `RagDocumentMeta`   |             |
| `RagSearchOptions`  |             |
| `RagSearchResult`   |             |
| `RagStore`          |             |
| `RagStoreBackend`   |             |
| `RagStoreConfig`    |             |
| `RagStoreData`      |             |
| `SearchOptions`     |             |
| `SearchResult`      |             |
| `UseUploadsOptions` |             |
| `UseUploadsResult`  |             |
| `VectorStore`       |             |
| `VectorStoreConfig` |             |


Built with [Mintlify](https://mintlify.com).