Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -127,6 +127,11 @@ React Native ExecuTorch powers [Private Mind](https://privatemind.swmansion.com/

<img width="2620" height="985" alt="Private Mind promo" src="https://raw.githubusercontent.com/software-mansion-labs/private-mind/main/promo/promo.png" />

It also powers these libraries:

- [React Native RAG](https://github.com/software-mansion-labs/react-native-rag): private, on-device retrieval-augmented generation for your own documents.
- [React Native OCR](https://github.com/software-mansion-labs/react-native-ocr): on-device document OCR with page layout, tables, dewarping and vertical text.

## Created by Software Mansion

Since 2012, [Software Mansion](https://swmansion.com) has been building mobile and web apps, contributing to open-source software, and dealing with all kinds of React Native challenges. We are Core React Native Contributors. We can help you build your next AI product – [Hire us](https://swmansion.com/contact?utm_source=react-native-executorch&utm_medium=readme).
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -183,8 +183,8 @@ The library provides mixed-precision fused PP-OCRv6 models from the [Software Ma
| :----------------- | :----------------------------------------------------------------------- | :--------------- | :----------------------------------------------- | :--------------------------------------------------------------------------- |
| **PP-OCRv6 Small** | [See](../../06-api-reference/variables/models.md#ocrpaddleppocrv6_small) | 7.9 MB – 25.0 MB | XNNPACK (CPU), Core ML (Apple), Vulkan (Android) | Full end-to-end on-device text detection & recognition in a single pipeline. |

:::note Legacy CRAFT Models & Future EasyOCR Package
The HuggingFace OCR collection may also list legacy **CRAFT** text detector models. Direct CRAFT support has been deprecated in core `react-native-executorch` in favor of the significantly faster and lighter fused **PP-OCRv6** pipeline. Advanced EasyOCR-style recognition features will be introduced in a dedicated companion package.
:::note Legacy CRAFT Models & EasyOCR
The HuggingFace OCR collection may also list legacy **CRAFT** text detector models. Direct CRAFT support has been deprecated in core `react-native-executorch` in favor of the significantly faster and lighter fused **PP-OCRv6** pipeline. EasyOCR alphabets, vertical text and document features (layout, tables, dewarping) are available in the companion [React Native OCR](https://github.com/software-mansion-labs/react-native-ocr) package.
:::

:::tip Using Custom Models
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,10 @@ function MyChatComponent() {
See [`src/app/(screens)/llm-chat.tsx`](<https://github.com/software-mansion-labs/react-native-executorch-gallery/blob/main/src/app/(screens)/llm-chat.tsx>) in the [React Native ExecuTorch Gallery](https://github.com/software-mansion-labs/react-native-executorch-gallery) for a complete, runnable chat UI with token streaming, token/sec benchmarking, and message history.
:::

:::tip Answering From Your Own Documents
[React Native RAG](https://github.com/software-mansion-labs/react-native-rag) combines these LLMs with [Text Embeddings](./03-text-embeddings.md) and a vector store for on-device retrieval-augmented generation.
:::

## Understanding the Output & Turn Result

When you call [`sendMessage()`](../../06-api-reference/type-aliases/LLMChatSession.md#sendmessage), the promise resolves to an [`LLMChatTurnResult`](../../06-api-reference/type-aliases/LLMChatTurnResult.md) describing what happened during that turn:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ const matches = store.query(await embedder.embed('How do I change my password?')
// [{ id, score, metadata: { text } }, ...] — most similar first
```

The store is in memory and searches exhaustively, which takes a few milliseconds for tens of thousands of vectors. `remove`, `get`, `has` and per-query `filter`/`minScore` are also available. Nothing is persisted.
The store is in memory and searches exhaustively, which takes a few milliseconds for tens of thousands of vectors. `remove`, `get`, `has` and per-query `filter`/`minScore` are also available. Nothing is persisted. For a persistent store, document splitting and retrieval-augmented generation with an [LLM](./02-llm-chat-and-generation.md), see [React Native RAG](https://github.com/software-mansion-labs/react-native-rag).

## Asymmetric Retrieval & Prompt Prefixes

Expand Down
Loading