llmstack-cli 0.1.0__py3-none-any.whl

llmstack/services/observe/prometheus.py

@@ -0,0 +1,168 @@
+"""Prometheus + Grafana observability services."""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+from llmstack.config.schema import ObserveConfig
+from llmstack.services.base import ServiceBase
+
+
+# Prometheus config that scrapes the gateway /metrics endpoint
+PROMETHEUS_CONFIG = """
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'llmstack-gateway'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['llmstack-gateway:8000']
+    scrape_interval: 5s
+
+  - job_name: 'qdrant'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['llmstack-qdrant:6333']
+    scrape_interval: 15s
+"""
+
+# Grafana datasource provisioning
+GRAFANA_DATASOURCE = {
+    "apiVersion": 1,
+    "datasources": [{
+        "name": "Prometheus",
+        "type": "prometheus",
+        "access": "proxy",
+        "url": "http://llmstack-prometheus:9090",
+        "isDefault": True,
+    }],
+}
+
+# Grafana dashboard provisioning config
+GRAFANA_DASHBOARD_PROVIDER = {
+    "apiVersion": 1,
+    "providers": [{
+        "name": "LLMStack",
+        "type": "file",
+        "options": {"path": "/var/lib/grafana/dashboards"},
+    }],
+}
+
+# Pre-built Grafana dashboard JSON
+GRAFANA_DASHBOARD = {
+    "dashboard": {
+        "title": "LLMStack Overview",
+        "uid": "llmstack-overview",
+        "timezone": "browser",
+        "refresh": "10s",
+        "panels": [
+            {
+                "title": "Request Rate",
+                "type": "timeseries",
+                "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
+                "targets": [{"expr": "rate(llmstack_requests_total[1m])", "legendFormat": "{{path}}"}],
+            },
+            {
+                "title": "Latency (p50 / p99)",
+                "type": "timeseries",
+                "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+                "targets": [
+                    {"expr": "histogram_quantile(0.5, rate(llmstack_request_duration_seconds_bucket[5m]))", "legendFormat": "p50"},
+                    {"expr": "histogram_quantile(0.99, rate(llmstack_request_duration_seconds_bucket[5m]))", "legendFormat": "p99"},
+                ],
+            },
+            {
+                "title": "Error Rate",
+                "type": "stat",
+                "gridPos": {"h": 4, "w": 6, "x": 0, "y": 8},
+                "targets": [{"expr": "sum(rate(llmstack_errors_total[5m]))"}],
+            },
+            {
+                "title": "Active Services",
+                "type": "stat",
+                "gridPos": {"h": 4, "w": 6, "x": 6, "y": 8},
+                "targets": [{"expr": "up"}],
+            },
+            {
+                "title": "Token Throughput",
+                "type": "timeseries",
+                "gridPos": {"h": 8, "w": 12, "x": 12, "y": 8},
+                "targets": [{"expr": "rate(llmstack_tokens_total[1m])", "legendFormat": "{{type}}"}],
+            },
+        ],
+    },
+}
+
+
+class PrometheusService(ServiceBase):
+    name = "prometheus"
+    category = "observe"
+
+    def __init__(self, config: ObserveConfig):
+        self.config = config
+        self.host_port = 9090
+
+    def container_spec(self) -> dict[str, Any]:
+        return {
+            "image": "prom/prometheus:latest",
+            "name": "llmstack-prometheus",
+            "ports": {"9090/tcp": self.host_port},
+            "command": [
+                "--config.file=/etc/prometheus/prometheus.yml",
+                f"--storage.tsdb.retention.time={self.config.retention}",
+                "--web.enable-lifecycle",
+            ],
+            "volumes": {
+                "llmstack_prometheus_config": {"bind": "/etc/prometheus", "mode": "rw"},
+                "llmstack_prometheus_data": {"bind": "/prometheus", "mode": "rw"},
+            },
+            "environment": {},
+        }
+
+    def health_url(self) -> str:
+        return f"http://localhost:{self.host_port}/-/healthy"
+
+    def get_config_yaml(self) -> str:
+        """Return the prometheus.yml content."""
+        return PROMETHEUS_CONFIG
+
+
+class GrafanaService(ServiceBase):
+    name = "grafana"
+    category = "observe"
+
+    def __init__(self, config: ObserveConfig):
+        self.config = config
+        self.host_port = config.dashboard_port
+
+    def container_spec(self) -> dict[str, Any]:
+        return {
+            "image": "grafana/grafana:latest",
+            "name": "llmstack-grafana",
+            "ports": {"3000/tcp": self.host_port},
+            "environment": {
+                "GF_SECURITY_ADMIN_USER": "admin",
+                "GF_SECURITY_ADMIN_PASSWORD": "llmstack",
+                "GF_AUTH_ANONYMOUS_ENABLED": "true",
+                "GF_AUTH_ANONYMOUS_ORG_ROLE": "Viewer",
+                "GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH": "/var/lib/grafana/dashboards/llmstack.json",
+            },
+            "volumes": {
+                "llmstack_grafana_data": {"bind": "/var/lib/grafana", "mode": "rw"},
+            },
+        }
+
+    def health_url(self) -> str:
+        return f"http://localhost:{self.host_port}/api/health"
+
+    def get_datasource_json(self) -> str:
+        return json.dumps(GRAFANA_DATASOURCE, indent=2)
+
+    def get_dashboard_provider_json(self) -> str:
+        return json.dumps(GRAFANA_DASHBOARD_PROVIDER, indent=2)
+
+    def get_dashboard_json(self) -> str:
+        return json.dumps(GRAFANA_DASHBOARD, indent=2)

llmstack/services/registry.py

@@ -0,0 +1,53 @@
+"""Service registry — discovers built-in and plugin services."""
+
+from __future__ import annotations
+
+from importlib.metadata import entry_points
+from typing import Type
+
+from llmstack.services.base import ServiceBase
+from llmstack.services.inference.ollama import OllamaService
+from llmstack.services.inference.vllm import VllmService
+from llmstack.services.vectordb.qdrant import QdrantService
+from llmstack.services.cache.redis import RedisService
+from llmstack.services.embeddings.tei import TEIService
+
+
+class ServiceRegistry:
+    """Discovers all built-in + plugin services."""
+
+    def __init__(self):
+        self._services: dict[str, Type[ServiceBase]] = {}
+        self._load_builtins()
+        self._load_plugins()
+
+    def _load_builtins(self) -> None:
+        for cls in [OllamaService, VllmService, QdrantService, RedisService, TEIService]:
+            self._services[cls.name] = cls
+
+    def _load_plugins(self) -> None:
+        try:
+            eps = entry_points(group="llmstack.services")
+        except TypeError:
+            # Python 3.11 compat
+            eps = entry_points().get("llmstack.services", [])
+
+        for ep in eps:
+            try:
+                cls = ep.load()
+                if hasattr(cls, "name"):
+                    self._services[cls.name] = cls
+            except Exception:
+                pass
+
+    def get(self, name: str) -> Type[ServiceBase]:
+        if name not in self._services:
+            available = ", ".join(sorted(self._services.keys()))
+            raise KeyError(f"Unknown service '{name}'. Available: {available}")
+        return self._services[name]
+
+    def list_by_category(self, category: str) -> list[Type[ServiceBase]]:
+        return [s for s in self._services.values() if s.category == category]
+
+    def all_names(self) -> list[str]:
+        return sorted(self._services.keys())

llmstack/services/vectordb/qdrant.py

@@ -0,0 +1,33 @@
+"""Qdrant vector database service."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from llmstack.config.schema import VectorDBConfig
+from llmstack.services.base import ServiceBase
+
+
+class QdrantService(ServiceBase):
+    name = "qdrant"
+    category = "vectordb"
+
+    def __init__(self, config: VectorDBConfig):
+        self.config = config
+
+    def container_spec(self) -> dict[str, Any]:
+        return {
+            "image": "qdrant/qdrant:latest",
+            "name": "llmstack-qdrant",
+            "ports": {
+                "6333/tcp": self.config.port,
+                "6334/tcp": self.config.port + 1,
+            },
+            "volumes": {
+                "llmstack_qdrant_data": {"bind": "/qdrant/storage", "mode": "rw"},
+            },
+            "environment": {},
+        }
+
+    def health_url(self) -> str:
+        return f"http://localhost:{self.config.port}/healthz"

llmstack_cli-0.1.0.dist-info/METADATA

@@ -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

llmstack_cli-0.1.0.dist-info/RECORD

@@ -0,0 +1,62 @@
+llmstack/__init__.py,sha256=eeHMsyABNyNRnVgYQqyU_R4RZpbJ7Kz3HzPWsisW5zo,84
+llmstack/__main__.py,sha256=XhknKG6tlsgyslTC57MpF3IGUu_cIo6G5rSIz4kxuyc,86
+llmstack/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/cli/app.py,sha256=qcrUcYkJApyX2JYVCFsu2wXZx81b0ma5aBXRNVNukSw,2378
+llmstack/cli/console.py,sha256=qnwJ2g39BwXhA_WhGtJW5E1ZdbTau4npG9j9mBo2zX0,259
+llmstack/cli/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/cli/commands/doctor.py,sha256=71PM5uG-a8A4nNf4ywMXmVIL8w6W5MwLgLco9DxbnG8,2440
+llmstack/cli/commands/down.py,sha256=51XiP8n_Nq3oX4gbeLd_vCvXB1OP7dZEi3392eYgSJM,752
+llmstack/cli/commands/init.py,sha256=1olPvaPLapdSkuSBVIum4kzXh2BMtkRw-HNZKs1slKc,2311
+llmstack/cli/commands/logs.py,sha256=CGZO9kFiqc224LtpYH22uf0k5E26sCmAucrozjtb7BQ,840
+llmstack/cli/commands/status.py,sha256=ahnhKsw0C6-x2umOVUNsCnTU5XQS-nGIjKOFxEZVjdA,1382
+llmstack/cli/commands/up.py,sha256=plZvcqZfA5eIVIDu8n6iMIum3jN-QAhhHfLR4JRFomg,854
+llmstack/config/__init__.py,sha256=7D4wkOUIE-BmuMJPBUg_d_g3QRpSKEvHC3mfdxBb_Zw,136
+llmstack/config/loader.py,sha256=d4XnRBMoGGF7tvQRMlbFQE-8za2SBkElEdrjTXvLAVk,1375
+llmstack/config/schema.py,sha256=p9dwVFSoE0tECuUzvtAoRKv3aLPY8bdpT1ouf5hsTCg,2133
+llmstack/config/presets/__init__.py,sha256=Z1JX3ZGvQHWZLYbY7yb-ntcg9_-wB4AMmYiXO1epzZs,317
+llmstack/config/presets/agent.py,sha256=VOIg088i_CR9Dv7JXPgQvQ84xSUE0IJ1V-38XyJ1r0Q,449
+llmstack/config/presets/chat.py,sha256=OoJ_MqSFlbPa_nUeAvyUU3O1OsrfBW95Gw9bXjvoV38,385
+llmstack/config/presets/rag.py,sha256=_aisSEegOHDCaieNKamoHJxdW7CG2N9T48qEWQjiG4I,340
+llmstack/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/core/hardware.py,sha256=dO2VRD2OZ4BnDETkHBRw1YeTERz6XhFByQpy8z7-jWc,3844
+llmstack/core/health.py,sha256=BxH-Y1DsoDFc0zNxYVTdYEmKTC1dIWiBxhCLDLbUyr0,706
+llmstack/core/resolver.py,sha256=MPUNLAoe0U_htLtMy789RbBir6xljWnw9p0AGOHYrAc,1633
+llmstack/core/stack.py,sha256=v9kPijvUm5IF-B608b0fUw71wDv14vg0K1ovffSuHf4,8310
+llmstack/docker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/docker/manager.py,sha256=OzfY8H46dEw7acSe8sUglayo4hgxO0tj3SxEC47Xmmg,4728
+llmstack/gateway/Dockerfile,sha256=Mtiy9fcfK1DikZ6v-I4zBI_Op1pABVm1nYZ-LT8J9fg,308
+llmstack/gateway/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/gateway/main.py,sha256=PYT48w4MuBNCqJ3YTq27OF_yC0dRRpnC61bpos1aveY,1483
+llmstack/gateway/proxy.py,sha256=WLErhSUICVK1XWu6Qt9v5gBWYtwalP3LKJE_D5Dj6C4,2077
+llmstack/gateway/middleware/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/gateway/middleware/auth.py,sha256=k49XxcGuoZEEf_upkvrbhev5K0Y9ZZiyvJU8ibx_-Sw,1088
+llmstack/gateway/middleware/metrics.py,sha256=nFeEyF5kBDbd9PCgMrt1-FAPZxXiLS4WMvP8tEnq-io,4387
+llmstack/gateway/routes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/gateway/routes/chat.py,sha256=qVbXYRdiQihawMF0qxzVeL7Ud5O-UyPjQjmOwEbN4H8,837
+llmstack/gateway/routes/embeddings.py,sha256=H8FCv0cPsgwAMejC6ytCHXwy88vGktIMH_sKimEMoUk,453
+llmstack/gateway/routes/health.py,sha256=K4EGOMVVMvOfAJDGEOFrVOvnT5OiZkH2U_u1WqdWP08,1449
+llmstack/gateway/routes/models.py,sha256=0jBHyop_HJyArvKXKOZKZwzj6rVCeuLZhj6AdIR8Hwc,353
+llmstack/plugins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/plugins/loader.py,sha256=cg_aldCDSNJWM_Es7iUI-1ycwJwhzNLf9G0CYJrw8Ow,152
+llmstack/plugins/spec.py,sha256=nteKuPgDjok8b1rSKsN6rFVXGjhYwwfuRpiubKEIfqc,546
+llmstack/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/base.py,sha256=qe2c6uZbSwaaItvkEq4T9kxujOGEgS2KL0giKrea1g8,1888
+llmstack/services/registry.py,sha256=pbDscM_YezzKMikuHqbO7cuekmiP84IyOKmwctkeAow,1855
+llmstack/services/cache/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/cache/redis.py,sha256=_6_JlFxFEvVutkmFwo-qzola6heODG_fxrfGVt0x-1k,898
+llmstack/services/embeddings/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/embeddings/tei.py,sha256=GNJL6PxQVUu7FQEzR0jj1N2jDCkhZoO1ezKLcEdo5EI,1502
+llmstack/services/gateway/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/gateway/service.py,sha256=4PSED82DHUlkqP4FxL-lNxY5kO1E-ODTN-x6msEY3HE,1580
+llmstack/services/inference/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/inference/ollama.py,sha256=0A-4V3Ks3fiyQwnJkBhLtj9oIvKAYPK-QgsbcAsuqFI,1814
+llmstack/services/inference/vllm.py,sha256=fhi7xa2RitNG0FNnhypUYfjEemvylnnxOIksRfBzJcE,1607
+llmstack/services/observe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/observe/prometheus.py,sha256=6NG8yDY2JQqYCWtSldb6LEKbOqLdHiPB9u9G0c2dJpw,5343
+llmstack/services/vectordb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+llmstack/services/vectordb/qdrant.py,sha256=zIOqf5km-4pItXOW8Y-qdxHLiU9lFfhDz33nBrTgPhM,900
+llmstack_cli-0.1.0.dist-info/METADATA,sha256=aWalxTiNMqv0lz5GjICnaOhTC1QgYXRR8Tq7Jyk4LQE,8128
+llmstack_cli-0.1.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+llmstack_cli-0.1.0.dist-info/entry_points.txt,sha256=i2BIacwqAqUaN1yAe-MaJZ22unHqAAUkTopk9M_iZPo,50
+llmstack_cli-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+llmstack_cli-0.1.0.dist-info/RECORD,,

llmstack_cli-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.29.0
+Root-Is-Purelib: true
+Tag: py3-none-any

llmstack_cli-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+llmstack = llmstack.cli.app:app