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

# Changelog

> Release notes for Moorcheh On-Edge - moorcheh-edge, local API server, CLI, and Python SDK.

## Moorcheh On-Edge Changelog

Track releases of the on-device Moorcheh On-Edge stack: `moorcheh-edge` on PyPI, the `moorcheh/moorcheh-edge` Docker image, REST API, `moorcheh-edge` CLI, and `MoorchehEdge` / `MoorchehEdgeApiClient`.

<Update label="Version 0.2.2" description="Released July 3, 2026">
  ### Catalog sync (retail kiosk)

  Patch release: export edge catalog text and sync it to the kiosk Admin on the display PC. **No breaking API changes.**

  #### Install and upgrade

  ```bash theme={null}
  pip install moorcheh-edge==0.2.2
  # or
  pip install -U moorcheh-edge
  ```

  ```bash theme={null}
  docker pull moorcheh/moorcheh-edge:0.2.2
  # or
  docker pull moorcheh/moorcheh-edge:latest
  ```

  #### What's new

  * **`GET /export`** - export all catalog chunk text from Moorcheh Edge (no vectors). See [Export store](/api-references/export).
  * **`export_store()`** - Python client helper for the same endpoint. See [export\_store](/python-client/export).
  * **Voice `POST /catalog/document`** - chunk, embed on edge hardware, and upload to Moorcheh Edge. See [Voice server](/api-references/voice-serve#post-catalogdocument).
  * **Retail kiosk sync** - Admin **Sync from UNO Q** pulls `GET /export` and replaces the local SQLite catalog; document saves embed on the UNO Q. See [Retail Kiosk](/examples/retail-kiosk#catalog-and-sync).
</Update>

<Update label="Version 0.2.1" description="Released June 26, 2026">
  ### Qwen LLM, anti-hallucination, and kiosk voice

  Patch release: default LLM switch to **Qwen 0.5B**, anti-hallucination when search returns no context, and retail-kiosk voice/doc updates. **No breaking API changes.**

  #### Install and upgrade

  ```bash theme={null}
  pip install moorcheh-edge==0.2.1
  # or
  pip install -U moorcheh-edge
  ```

  Docker (multi-arch **`linux/amd64`** + **`linux/arm64`**):

  ```bash theme={null}
  docker pull moorcheh/moorcheh-edge:0.2.1
  # or
  docker pull moorcheh/moorcheh-edge:latest
  ```

  #### What's new

  * **Default LLM** - `qwen2.5:0.5b-instruct` (replaces `llama3.2:1b-instruct-q4_K_M`, \~400 MB pull on `moorcheh-edge up --with-llm`)
  * **No-context answers** - when search returns zero passages, `/answer` and `/answer/stream` return *I don't have enough information to answer that question.* without calling Ollama
  * **Voice streaming** - `/ask/stream` with `speak: true` streams tokens to the UI immediately; TTS runs after the full answer is ready
  * **Thinking loop** - ambient kiosk audio while RAG runs (`voice cache-thinking`, `thinking_enabled` on `/ask/stream`)
  * **Kiosk audio docs** - `voice cache-holding` and `voice cache-thinking` documented under [Retail Kiosk](/examples/retail-kiosk#kiosk-audio-cache) (not general CLI pages)
  * **Bluetooth** - [manual pairing guide](/cli/voice/bluetooth); automated `voice bluetooth` CLI removed
  * **Docs** - Qwen model, `--with-llm`, and no-context behavior updated across guides and API reference
</Update>

<Update label="Version 0.2.0" description="Released June 3, 2026">
  ### Flat store, text mode, RAG answer, and client-side embeddings

  Major update: **single flat store** per container with **text** or **vector** mode. Text documents are embedded client-side with BGE-base-en-v1.5 (768 dimensions). **RAG answer** via local Ollama and **`llama3.2:1b-instruct-q4_K_M`** (\~808 MB).

  #### Breaking changes

  * **Upload payload** - use `{"store_mode": "text"|"vector", "items": [...]}` instead of `{"vectors": [...]}`
  * **Delete route** - `DELETE /items` (was `DELETE /delete`)
  * **New route** - `DELETE /store` to wipe all data ([API](/api-references/clear-store), [CLI](/cli/clear-store), [Python](/python-client/clear-store))
  * **Health fields** - `dimension`, `store_mode`, `embedding_model` replace `vector_dimension`
  * **Text search** - CLI `--query-text` and SDK `search_text()` embed locally; server accepts float vectors only

  #### What's new

  * **`upload-documents`** CLI - embed text locally and upload to a text store
  * **`clear-store`** CLI - wipe store with confirmation prompt (`-y` to skip)
  * **SDK** - `upload_documents()`, `upload_vectors()`, `search_text()`, `clear_store()`
  * **Text store** - BGE-base-en-v1.5, 768 dimensions, optional `text` on each item
  * **Vector store** - dimensions **128, 256, 384, 768, 1024, 1536** on first upload
  * **`POST /answer`** - search + prompt + Ollama LLM response (RAG)
  * **`POST /answer/stream`** - same RAG flow, streamed as SSE (`meta`, `token`, `done`, `error`)
  * **`moorcheh-edge answer`** - embed query locally, call `/answer`
  * **SDK** - `answer_text()`, `answer()`; **`MoorchehEdgeApiClient.answer_stream()`** for streaming
  * **`moorcheh-edge voice`** - STT (Whisper), TTS (Piper), local `voice ask`, and **`voice serve`** HTTP API on `:8766` for edge kiosk hardware
  * **Docs: [Retail Kiosk example](/examples/retail-kiosk)** - PC + Arduino UNO Q in-store demo (Admin/Customer UI, voice proxy, catalog upload)
  * **Ollama bootstrap** - `moorcheh-edge up` installs Ollama on Linux and pulls **`llama3.2:1b-instruct-q4_K_M`** (\~808 MB)
  * **`--skip-ollama`** on `up` - search-only without LLM setup

  #### Upgrade notes

  Clear existing stores and re-upload data. Old namespace-based JSON files are not compatible.

  ```bash theme={null}
  moorcheh-edge clear-store -y
  moorcheh-edge upload-documents --documents-file documents.json
  ```
</Update>

<Update label="Version 0.1.1" description="Released June 1, 2026">
  ### CI, release pipeline, and multi-arch Docker

  Patch release for **Moorcheh On-Edge** with automated CI and publish workflows, plus a multi-architecture Docker image. **No breaking changes** to the REST API, CLI, or `MoorchehEdge` client.

  #### Install and upgrade

  ```bash theme={null}
  pip install moorcheh-edge==0.1.1
  # or
  pip install -U moorcheh-edge
  ```

  #### What's new

  * **CI pipeline** - automated tests and checks on pull requests and pushes
  * **Publish pipeline** - automated PyPI and Docker image releases for `moorcheh-edge` and `moorcheh/moorcheh-edge`
  * **Multi-arch Docker image** - `moorcheh/moorcheh-edge:0.1.1` and `:latest` ship **`linux/amd64`** and **`linux/arm64`**
</Update>

<Update label="Version 0.1.0" description="Released May 26, 2026">
  ### Initial release

  First public release of **Moorcheh On-Edge** - on-device vector upload, similarity search, and delete.

  #### Install

  ```bash theme={null}
  pip install moorcheh-edge
  moorcheh-edge up
  moorcheh-edge status
  ```

  #### Runtime

  * **`moorcheh-edge up` / `down` / `status`** - Docker container lifecycle
  * **Local data** - `~/.moorcheh-edge/data` (`moorcheh_edge_store.json`)
  * **Default API** - `http://localhost:8080`

  <Info>
    **Getting started:** See [Introduction](/introduction), [Prerequisites](/prerequisites), and [Quickstart](/quickstart).
  </Info>
</Update>