llmstack-cli 0.1.0__tar.gz

llmstack_cli-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,31 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Lint
+        run: ruff check src/ tests/
+
+      - name: Test
+        run: pytest tests/ -v --tb=short

llmstack_cli-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,28 @@
+name: Release to PyPI
+
+on:
+  push:
+    tags: ["v*"]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

llmstack_cli-0.1.0/.gitignore

@@ -0,0 +1,19 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+dist/
+build/
+*.egg-info/
+.eggs/
+.venv/
+venv/
+env/
+.env
+*.session
+.DS_Store
+data/
+*.db
+.ruff_cache/
+.pytest_cache/
+llmstack.yaml

llmstack_cli-0.1.0/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+## [0.1.0] - 2026-05-07
+
+### Added
+- CLI with `init`, `up`, `down`, `status`, `logs`, `doctor` commands
+- Auto hardware detection (NVIDIA, Apple Silicon, CPU)
+- Smart backend resolver (auto-picks Ollama or vLLM)
+- Services: Ollama, vLLM, Qdrant, Redis, TEI (Text Embeddings Inference)
+- API Gateway: OpenAI-compatible proxy with auth, rate limiting, SSE streaming
+- Prometheus + Grafana observability with pre-provisioned dashboard
+- Plugin system via Python entry_points
+- Presets: `chat`, `rag`, `agent`
+- Pydantic v2 config schema (`llmstack.yaml`)
+- Docker SDK orchestration (no docker-compose dependency)
+- CI/CD: GitHub Actions for lint/test and PyPI release

llmstack_cli-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,64 @@
+# Contributing to llmstack
+
+Thanks for your interest in contributing! Here's how to get started.
+
+## Development setup
+
+```bash
+git clone https://github.com/mara-werils/llmstack.git
+cd llmstack
+pip install -e ".[dev]"
+```
+
+## Running tests
+
+```bash
+make test        # run all tests
+make lint        # check code style
+make format      # auto-format code
+```
+
+## Project structure
+
+```
+src/llmstack/
+├── cli/          # Typer CLI commands
+├── config/       # Pydantic config schema + presets
+├── core/         # Stack orchestrator, hardware detection, resolver
+├── services/     # Service implementations (Ollama, vLLM, Qdrant, Redis, etc.)
+├── gateway/      # FastAPI gateway (OpenAI-compatible proxy)
+├── docker/       # Docker SDK wrapper
+└── plugins/      # Plugin interface + loader
+```
+
+## Adding a new service
+
+1. Create a class extending `ServiceBase` in `services/`
+2. Implement `container_spec()`, `health_url()`
+3. Optionally implement `post_start()`, `openai_base_url()`
+4. Register in `services/registry.py` or as a plugin via `entry_points`
+5. Add tests in `tests/unit/`
+
+## Creating a plugin
+
+See [plugins/spec.py](src/llmstack/plugins/spec.py) for the plugin interface.
+
+```toml
+# In your plugin's pyproject.toml:
+[project.entry-points."llmstack.services"]
+my_service = "my_package:MyServiceClass"
+```
+
+## Pull requests
+
+- Keep PRs focused on a single change
+- Add tests for new functionality
+- Run `make lint` before submitting
+- Use conventional commit messages (`feat:`, `fix:`, `docs:`)
+
+## Code style
+
+- Python 3.11+
+- Ruff for linting and formatting
+- Type hints everywhere
+- Docstrings for public APIs

llmstack_cli-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

llmstack_cli-0.1.0/Makefile

@@ -0,0 +1,20 @@
+.PHONY: install dev test lint clean
+
+install:
+	pip install -e .
+
+dev:
+	pip install -e ".[dev]"
+
+test:
+	pytest tests/ -v
+
+lint:
+	ruff check src/ tests/
+
+format:
+	ruff format src/ tests/
+
+clean:
+	rm -rf build/ dist/ *.egg-info .pytest_cache .ruff_cache
+	find . -type d -name __pycache__ -exec rm -rf {} +

llmstack_cli-0.1.0/PKG-INFO

@@ -0,0 +1,252 @@
+Metadata-Version: 2.4
+Name: llmstack-cli
+Version: 0.1.0
+Summary: One command. Full LLM stack. Zero config.
+Author: mara-werils
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: ai,cli,docker,inference,llm,openai,rag
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.11
+Requires-Dist: docker>=7.0
+Requires-Dist: httpx>=0.27
+Requires-Dist: psutil>=5.9
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0
+Requires-Dist: typer>=0.12
+Provides-Extra: dev
+Requires-Dist: fastapi>=0.115; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Requires-Dist: starlette>=0.40; extra == 'dev'
+Provides-Extra: gateway
+Requires-Dist: fastapi>=0.115; extra == 'gateway'
+Requires-Dist: starlette>=0.40; extra == 'gateway'
+Requires-Dist: uvicorn[standard]>=0.30; extra == 'gateway'
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <h1 align="center">llmstack</h1>
+  <p align="center"><strong>One command. Full LLM stack. Zero config.</strong></p>
+  <p align="center">Stop wiring Docker containers. Start building AI apps.</p>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/llmstack-cli/"><img src="https://img.shields.io/pypi/v/llmstack-cli?color=blue" alt="PyPI"></a>
+  <a href="https://github.com/mara-werils/llmstack/actions/workflows/ci.yml"><img src="https://github.com/mara-werils/llmstack/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
+  <a href="https://github.com/mara-werils/llmstack/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License"></a>
+  <a href="https://www.python.org/"><img src="https://img.shields.io/badge/python-3.11+-blue" alt="Python"></a>
+</p>
+
+---
+
+**llmstack** spins up a production-grade LLM stack locally with a single command. It auto-detects your hardware, picks the optimal inference backend, and wires everything together.
+
+```bash
+pip install llmstack-cli
+llmstack init
+llmstack up
+```
+
+That's it. You now have a full LLM API running locally.
+
+## Architecture
+
+```
+                         llmstack up
+                              |
+                    +---------v----------+
+                    |   Hardware Detect   |
+                    |  NVIDIA / Apple / CPU|
+                    +---------+----------+
+                              |
+              +-------+-------+-------+-------+
+              |       |       |       |       |
+         +----v--+ +--v---+ +v-----+ +v----+ +v--------+
+         |Qdrant | |Redis | |Ollama| | TEI | | Gateway  |
+         |Vector | |Cache | | or   | |Embed| | FastAPI  |
+         |  DB   | |      | | vLLM | |     | | OpenAI   |
+         +-------+ +------+ +------+ +-----+ |compatible|
+              :6333   :6379   :11434   :8002  +----+-----+
+                                                   |:8000
+                                              +----v-----+
+                                              |Prometheus |
+                                              | + Grafana |
+                                              +----------+
+                                                   :8080
+```
+
+## What you get
+
+| Layer | Service | Default | Port |
+|-------|---------|---------|------|
+| Inference | Ollama / vLLM (auto) | llama3.2 | 11434 |
+| Embeddings | TEI / Ollama (auto) | bge-m3 | 8002 |
+| Vector DB | Qdrant | - | 6333 |
+| Cache | Redis | 256MB LRU | 6379 |
+| API Gateway | FastAPI (OpenAI-compatible) | auth + rate limit | 8000 |
+| Dashboard | Grafana + Prometheus | pre-built panels | 8080 |
+
+## How it works
+
+```
+llmstack init       # Detects hardware, generates llmstack.yaml
+                    # Picks optimal backend: vLLM for NVIDIA 16GB+, Ollama otherwise
+
+llmstack up         # Boots services in order with health checks:
+                    # Qdrant -> Redis -> Inference -> Embeddings -> Gateway -> Metrics
+
+llmstack status     # Shows health of all running services
+llmstack logs ollama # Stream inference logs
+llmstack down       # Stops everything
+```
+
+### Use the API
+
+```bash
+curl http://localhost:8000/v1/chat/completions \
+  -H "Authorization: Bearer YOUR_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"llama3.2","messages":[{"role":"user","content":"Hello!"}]}'
+```
+
+Works with **any OpenAI-compatible client**: LangChain, LlamaIndex, Vercel AI SDK, openai-python.
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="YOUR_KEY")
+response = client.chat.completions.create(
+    model="llama3.2",
+    messages=[{"role": "user", "content": "Explain quantum computing"}]
+)
+```
+
+## Auto hardware detection
+
+| Your hardware | Backend | Why |
+|---|---|---|
+| NVIDIA GPU 16GB+ VRAM | vLLM | Max throughput, PagedAttention |
+| NVIDIA GPU <16GB | Ollama | Lower memory overhead |
+| Apple Silicon (M1-M4) | Ollama | Metal acceleration |
+| CPU only | Ollama | GGUF quantized models |
+
+## Presets
+
+```bash
+llmstack init --preset chat    # Minimal: inference + cache + gateway
+llmstack init --preset rag     # + Qdrant + embeddings for RAG apps
+llmstack init --preset agent   # 70B model + 16K context + longer timeouts
+```
+
+## Configuration
+
+One file: `llmstack.yaml`
+
+```yaml
+version: "1"
+
+models:
+  chat:
+    name: llama3.2
+    backend: auto              # auto | ollama | vllm
+    context_length: 8192
+  embeddings:
+    name: bge-m3
+
+services:
+  vectors:
+    provider: qdrant
+    port: 6333
+  cache:
+    provider: redis
+    max_memory: 256mb
+
+gateway:
+  port: 8000
+  auth: api_key
+  rate_limit: 100/min
+  cors: ["*"]
+
+observe:
+  metrics: true
+  dashboard_port: 8080
+```
+
+## CLI
+
+| Command | Description |
+|---------|-------------|
+| `llmstack init [--preset]` | Create config with smart defaults |
+| `llmstack up [--attach]` | Start all services |
+| `llmstack down [--volumes]` | Stop and clean up |
+| `llmstack status` | Health check all services |
+| `llmstack logs <service>` | Stream service logs |
+| `llmstack doctor` | Diagnose system issues |
+
+## Observability
+
+When `observe.metrics: true`, llmstack boots Prometheus + Grafana with a pre-built dashboard:
+
+- **Request rate** per endpoint
+- **Latency** p50 / p99 histograms
+- **Token throughput** (input + output)
+- **Error rate** (4xx / 5xx)
+- **Service health** (up/down)
+
+Access at `http://localhost:8080` (login: admin / llmstack)
+
+## Plugins
+
+Extend llmstack with new backends via pip:
+
+```bash
+pip install llmstack-cli-plugin-chromadb
+# Now: vectors.provider: chromadb in llmstack.yaml
+```
+
+Create your own: implement `ServiceBase`, register via entry_points. See [CONTRIBUTING.md](CONTRIBUTING.md).
+
+## Why llmstack?
+
+| | llmstack | Ollama | Harbor | AnythingLLM | LiteLLM |
+|---|---|---|---|---|---|
+| One-command full stack | Yes | No (inference only) | Partial | Partial | No (proxy only) |
+| Auto hardware detection | Yes | No | No | No | No |
+| OpenAI-compatible API | Yes | Yes | Varies | No | Yes |
+| Built-in vector DB | Yes | No | Config needed | Bundled | No |
+| Built-in embeddings | Yes | No | No | Bundled | No |
+| Caching (Redis) | Yes | No | No | No | No |
+| Auth + rate limiting | Yes | No | No | Yes | Yes |
+| Observability dashboard | Yes | No | Partial | No | Partial |
+| Plugin ecosystem | Yes | No | No | No | No |
+| SSE streaming | Yes | Yes | Yes | Yes | Yes |
+
+## Tech stack
+
+- **CLI**: [Typer](https://typer.tiangolo.com/) + [Rich](https://rich.readthedocs.io/)
+- **Config**: [Pydantic v2](https://docs.pydantic.dev/)
+- **Gateway**: [FastAPI](https://fastapi.tiangolo.com/)
+- **Containers**: [Docker SDK for Python](https://docker-py.readthedocs.io/)
+- **Metrics**: Prometheus + Grafana
+
+## Requirements
+
+- Python 3.11+
+- Docker
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.
+
+## License
+
+Apache-2.0