> ## 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-Prem - moorcheh-client, local API server, CLI, and Python client.

## Moorcheh On-Prem Changelog

Track releases of the self-hosted Moorcheh stack: `moorcheh-client` on PyPI, the `moorcheh/server` Docker image, REST API, `moorcheh` CLI, and `MoorchehClient`.

<Update label="Version 0.1.6" description="Upcoming release">
  ### Ollama LLM: Qwen 2.5 1.5B option

  Adds **`qwen2.5:1.5b`** (\~1.5B parameters, \~986 MB) to the Ollama LLM menu in `moorcheh configure`. Default stays **`qwen2.5`** (\~7B).

  * **Client** - configure menu lists 7B (recommended) and 1.5B Qwen tags with parameter counts
  * **Configure** - pull prompts distinguish **LLM** vs **embedding** models

  Pick **`qwen2.5:1.5b`** in configure when you want a smaller local model; otherwise keep the default **`qwen2.5`**.

  #### Upgrade notes

  ```bash theme={null}
  pip install -U moorcheh-client==0.1.6
  moorcheh down && moorcheh up
  ```
</Update>

<Update label="Version 0.1.5" description="Released July 20, 2026">
  ### Moorcheh Community Edition - source available

  **Moorcheh Community Edition** is now **source-available** on GitHub: [github.com/moorcheh-ai/moorcheh-on-prem](https://github.com/moorcheh-ai/moorcheh-on-prem). **Free for single-node and non-commercial deployments.** Moorcheh server binary is available on Docker Hub: [moorcheh/server](https://hub.docker.com/repository/docker/moorcheh/server/general). This release refreshes the README and adds a live endpoint test script. **No breaking changes** to the public SDK: `from moorcheh import MoorchehClient, MoorchehApiClient` and all CLI commands work as before.

  #### Install and upgrade

  ```bash theme={null}
  pip install moorcheh-client==0.1.5
  # or
  pip install -U moorcheh-client
  ```

  #### What's new

  * **GitHub** - [moorcheh-ai/moorcheh-on-prem](https://github.com/moorcheh-ai/moorcheh-on-prem) (source-available)
  * **Docker Hub** - Moorcheh server binary at [hub.docker.com/r/moorcheh/server](https://hub.docker.com/repository/docker/moorcheh/server/general)
  * **Community Edition license** (`LICENSE`) - free for single-node and non-commercial deployments
  * **`CONTRIBUTING.md`** - dev setup, tests, PR guidelines
  * **README** - logo, tagline, shorter quick start; full API/CLI docs linked to [docs.moorcheh.ai](https://docs.moorcheh.ai/on-prem)
  * **`test.py`** - live integration test for all API endpoints (run with `moorcheh up`)
  * Single package on PyPI: **`moorcheh-client`** (unchanged install name)

  #### Upgrade notes

  ```bash theme={null}
  pip install -U moorcheh-client
  moorcheh down && moorcheh up
  ```

  * **SDK imports unchanged** - keep using `from moorcheh import MoorchehClient`
  * **CLI unchanged** - `moorcheh up`, `moorcheh search`, `moorcheh answer`, etc.

  Optional smoke test after upgrade:

  ```bash theme={null}
  python test.py
  ```

  <Info>
    **Requirements:** Python 3.10+, Docker, and the **`moorcheh/server`** image from [Docker Hub](https://hub.docker.com/repository/docker/moorcheh/server/general) (unchanged for this release).
  </Info>
</Update>

<Update label="Version 0.1.4" description="Released July 14 2026">
  ### Multi-arch Docker image

  `moorcheh/server` on Docker Hub is published as a **multi-architecture** manifest:

  * `linux/amd64` - Windows, Linux, Intel Mac
  * `linux/arm64` - Apple Silicon Mac, ARM Linux

  Users keep the same install flow (`pip install moorcheh-client` → `moorcheh up`). Docker pulls the matching architecture for `moorcheh/server:latest`.

  Maintainers: build and push with `moorcheh/scripts/build-multiarch.ps1 -Version X.Y.Z` (tags normalize to `vX.Y.Z`). See `moorcheh/README.md`.

  ### Namespace delete reliability

  * **Python client / CLI** - `namespaces.delete()` and `moorcheh namespace-delete` **wait for the async delete job by default** before returning, so recreate-after-delete works reliably
  * **`--no-wait`** on CLI to return immediately with `job_id` (legacy behavior)
  * **Server** - persistence and namespace registry fixes for delete-then-recreate on Windows bind mounts

  #### Upgrade notes

  ```bash theme={null}
  pip install -U moorcheh-client
  moorcheh down && moorcheh up   # pull moorcheh/server:latest (multi-arch)
  ```
</Update>

<Update label="Version 0.1.3" description="Released June 3, 2026">
  ### File upload (path-based)

  Upload and index PDF, DOCX, XLSX, PPTX, TXT, CSV, MD, and JSON from `~/.moorcheh/uploads` (mounted as `/uploads` in the server).

  **REST API**

  * File upload - async ingest with chunking, batch summaries (every 100 chunks), and embedding
  * List files, get file by id, delete file index
  * File job status - poll upload and delete jobs (`file_ingest` or `file_delete`)
  * Fetch text data - cursor pagination, up to 100 items per page

  **CLI**

  * `upload-file`, `list-files`, `file-get`, `delete-file`, `file-job-status`, `fetch-text-data`

  **Python client**

  * `client.files.upload`, `list`, `get`, `delete`, `job_status`
  * `client.documents.fetch_text_data` for paginated text chunks
  * `MoorchehClient` resource layout (`namespaces`, `documents`, `files`, `similarity_search`, `answer`) - `MoorchehApiClient` kept as legacy wrapper

  **Search**

  * `namespace` on each result; `summary_text` on top hit via bare `summary_chunk_id`
  * `#key:value` metadata filters and `#keyword` text filters in the query string (cloud parity)

  **Persistence**

  * `file_registry.json` under `~/.moorcheh/data`

  API paths use **container** paths (`/uploads/...`). CLI accepts host paths under `~/.moorcheh/uploads`. Delete file index or delete namespace removes **indexed data only** - disk files in `uploads/` are kept.

  Docs: [Upload file](/on-prem/api-references/files/upload), [CLI upload-file](/on-prem/cli/files/upload-file), [Python upload files](/on-prem/python-client/files/upload-files)

  ### AI Answer generation

  Generate contextual answers from your text namespaces (RAG) or call the LLM directly with an empty namespace - using **Ollama**, **OpenAI**, or **Cohere**.

  #### What's new

  * Answer endpoint - Search Mode (namespace + RAG) and Direct AI Mode (`namespace: ""`)
  * LLM configuration saved under `llm` in `~/.moorcheh/config.json`; prompted during `moorcheh configure`
  * `moorcheh answer` CLI command and `client.answer.generate()`
  * Health and status include `llm_provider` and `llm_model`
  * Structured output - optional `structured_response: { "enabled": true }` with default JSON schema
  * Docs: [Generate AI Answer](/on-prem/api-references/ai/generate), [Python client](/on-prem/python-client/ai/generate), [CLI](/on-prem/cli/ai/generate)

  #### Supported LLM models (examples)

  | Provider | Models |
  | - | - |
  | Ollama | `qwen2.5:1.5b`, `qwen2.5`, `llama3.2`, `mistral` |
  | OpenAI | `gpt-5.5`, `gpt-5`, `gpt-4o-mini` |
  | Cohere | `command-a-plus-05-2026`, `command-r-plus-08-2024`, `command-r-08-2024` |

  #### Upgrade notes

  * Re-run `moorcheh configure --force` to set LLM provider and model, or add a `llm` block to `config.json` manually.
  * Rebuild or pull an updated `moorcheh/server` image that includes the answer endpoint.
</Update>

<Update label="Version 0.1.2" description="Released June 2, 2026">
  ### Multi-provider text embeddings

  Choose how Moorcheh embeds text documents and search queries: **Ollama** (local), **OpenAI**, or **Cohere**. Settings are saved to `~/.moorcheh/config.json` and applied on every `moorcheh up`.

  #### Install and upgrade

  ```bash theme={null}
  pip install moorcheh-client==0.1.2
  # or
  pip install -U moorcheh-client
  ```

  Publish a matching **`moorcheh/server`** image (or use your tested build) so the server supports `EMBEDDING_PROVIDER` / `EMBEDDING_MODEL` / `EMBEDDING_API_KEY`.

  #### What's new

  * **`moorcheh configure`** - Interactive setup for provider, model, and API key (cloud providers)
  * **`moorcheh up`** - Reads saved config; runs the embedding wizard on first start if config is missing
  * **Ollama (optional)** - Bundled `moorcheh-ollama` starts only when provider is `ollama` and host Ollama is not running; embedding model is **pulled automatically** when missing
  * **OpenAI / Cohere** - Server container only; no Ollama required; API keys stored locally in `config.json`
  * **Health** - `GET /health` and `moorcheh status` include `embedding_provider` and `model`
  * **CLI flags** - `--embedding-provider`, `--embedding-model`, `--embedding-api-key`, `--no-configure`, `--skip-ollama-model-pull`
  * **Docs** - [Embedding providers](/on-prem/guides/embedding-providers), [moorcheh configure](/on-prem/cli/runtime/configure), updated [Prerequisites](/on-prem/prerequisites) and [moorcheh up](/on-prem/cli/runtime/up)
  * **Tests** - Coverage for config, Ollama setup, Docker runtime, and CLI embedding flows

  #### Supported embedding models

  | Provider | Models (examples) |
  | - | - |
  | Ollama | `nomic-embed-text`, `mxbai-embed-large`, `all-minilm` |
  | OpenAI | `text-embedding-3-small`, `text-embedding-3-large`, `text-embedding-ada-002` |
  | Cohere | `embed-v4.0`, `embed-english-v3.0`, `embed-multilingual-v3.0` |

  See [Embedding providers](/on-prem/guides/embedding-providers) for dimensions and configuration file format.

  #### Upgrade notes

  * Run **`moorcheh configure`** once after upgrading the client (or answer prompts on the next **`moorcheh up`**).
  * Existing data under `~/.moorcheh/data` is unchanged.
  * If you previously relied on Ollama-only defaults, pick **ollama** in configure to keep the same behavior, or switch to a cloud provider.

  <Info>
    **Requirements:** Python 3.10+, Docker. **Ollama** is required only when the embedding provider is `ollama`. OpenAI/Cohere need a provider API key and outbound HTTPS from the server container.
  </Info>
</Update>

<Update label="Version 0.1.1" description="Released May 25, 2026">
  ### Client improvements

  Patch release for **`moorcheh-client`** with improved reliability and broader Python support. **No breaking changes** to the REST API, CLI, or `MoorchehApiClient`.

  #### Install and upgrade

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

  #### What's new

  * **Python 3.10–3.13** - client package tested across supported Python versions
  * **Quality** - expanded automated tests for the API client, CLI, and Docker runtime helpers
  * **Packaging** - more consistent PyPI releases for `moorcheh-client`

  #### Upgrade notes

  No code changes are required if you already use `MoorchehApiClient` or the `moorcheh` CLI from v0.1.0. Your existing `moorcheh up` workflows and data under `~/.moorcheh/data` are unchanged.

  <Info>
    **Requirements:** Python 3.10+, Docker (for `moorcheh up`), and Ollama for embeddings (host or bundled).
  </Info>
</Update>

<Update label="Version 0.1.0" description="Released May 22, 2026">
  ### Initial release

  First public release of **Moorcheh On-Prem** - semantic search and vector storage that runs locally with Docker and Ollama. No cloud API keys required.

  #### Runtime

  * **`moorcheh up` / `down` / `status`** - Start and stop the Moorcheh API server (`moorcheh/server:latest`) via Docker Compose
  * **Ollama integration** - Host Ollama or bundled `moorcheh-ollama` container for embeddings (default model: `nomic-embed-text`)
  * **Local data** - Persistent storage under `~/.moorcheh/data`

  #### REST API

  * **Health** - Server status, embedding model, and global item quota (`GET /health`)
  * **Namespaces** - Create, list, and async delete text or vector namespaces
  * **Data** - Async upload of documents (text) and precomputed vectors, with job polling
  * **Items** - Get and delete items by id (up to 100 ids per request)
  * **Search** - Semantic search with text or vector queries across one or more namespaces

  #### CLI and Python client

  * **`moorcheh-client` on PyPI** - Installs the `moorcheh` CLI and `MoorchehApiClient` in one package
  * **Full parity** - CLI and Python SDK cover the same API surface (namespaces, uploads, items, search)

  #### Limits

  * **Unlimited namespaces** - no cloud-tier namespace count limit; only the global item cap applies
  * **100,000 items** global cap across all namespaces
  * Item ids unique per namespace

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


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.