rnow 0.3.1__tar.gz

rnow-0.3.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 ReinforceNow
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

rnow-0.3.1/PKG-INFO

@@ -0,0 +1,147 @@
+Metadata-Version: 2.4
+Name: rnow
+Version: 0.3.1
+Summary: ReinforceNow CLI - Reinforcement Learning platform command-line interface
+Requires-Python: <3.15,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click>=8.0.0
+Requires-Dist: requests>=2.25.0
+Requires-Dist: httpx>=0.24.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pyyaml>=5.4.0
+Requires-Dist: packaging>=21.0
+Requires-Dist: prompt_toolkit>=3.0.0
+Requires-Dist: tokenizers>=0.15.0
+Requires-Dist: openai-harmony>=0.0.8
+Provides-Extra: test
+Requires-Dist: tinker-cookbook>=0.1.0; extra == "test"
+Provides-Extra: api
+Requires-Dist: fastapi>=0.68.0; extra == "api"
+Requires-Dist: uvicorn>=0.15.0; extra == "api"
+Provides-Extra: mcp
+Requires-Dist: fastmcp>=0.1.0; extra == "mcp"
+Provides-Extra: all
+Requires-Dist: tinker-cookbook>=0.1.0; extra == "all"
+Requires-Dist: fastapi>=0.68.0; extra == "all"
+Requires-Dist: uvicorn>=0.15.0; extra == "all"
+Requires-Dist: fastmcp>=0.1.0; extra == "all"
+Dynamic: license-file
+
+<div align="center">
+  <img
+    alt="ReinforceNow CLI"
+    src="./assets/header.png"
+    width="100%"
+  >
+  <br><br>
+
+[![PyPI version](https://img.shields.io/pypi/v/rnow?color=blue)](https://pypi.org/project/rnow/)
+[![Docs](https://img.shields.io/badge/docs-reinforcenow.ai-blue)](https://reinforcenow.ai/docs)
+[![Follow on X](https://img.shields.io/badge/Follow_on_X-@reinforcenow-black?labelColor=white)](https://x.com/reinforcenow)
+[![MIT License](https://img.shields.io/badge/license-MIT-green)](./LICENSE)
+
+</div>
+
+# Documentation
+
+See the [documentation](https://www.reinforcenow.ai/docs/getting-started/quickstart) for a technical overview of the platform and [train your first agent](https://www.reinforcenow.ai/docs/getting-started/first-agent)
+
+# Quick Start
+
+### 1. Install uv (Python package manager)
+
+```bash
+# macOS/Linux:
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Windows:
+PS> powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
+```
+
+### 2. Install ReinforceNow
+
+```bash
+uv init && uv venv --python 3.11
+source .venv/bin/activate  # Windows: .\.venv\Scripts\Activate.ps1
+uv pip install rnow
+```
+
+### 3. Authenticate
+
+```bash
+rnow login
+```
+
+### 4. Create & Run Your First Project
+
+```bash
+rnow init --template sft
+rnow run
+```
+
+That's it! Your training run will start on ReinforceNow's infrastructure. Monitor progress in the [dashboard](https://reinforcenow.ai/home).
+
+![ReinforceNow Graph](./assets/reinforcenow-graph.png)
+
+# Core Concepts
+
+Go from raw data to a reliable AI agent in production. ReinforceNow gives you the flexibility to define:
+
+### 1. Reward Functions
+
+Define how your model should be evaluated using the `@reward` decorator:
+
+```python
+from rnow.core import reward, RewardArgs
+
+@reward
+async def accuracy(args: RewardArgs, messages: list) -> float:
+    """Check if the model's answer matches ground truth."""
+    response = messages[-1]["content"]
+    expected = args.metadata["answer"]
+    return 1.0 if expected in response else 0.0
+```
+
+→ [Write your first reward function](https://www.reinforcenow.ai/docs/getting-started/first-reward)
+
+### 2. Tools (for Agents)
+
+Give your model the ability to call functions during training:
+
+```python
+from rnow.core import tool
+
+@tool
+def search(query: str, max_results: int = 5) -> dict:
+    """Search the web for information."""
+    # Your implementation here
+    return {"results": [...]}
+```
+
+→ [Train an agent with custom tools](https://www.reinforcenow.ai/docs/getting-started/first-agent)
+
+### 3. Training Data
+
+Create a `train.jsonl` file with your prompts and reward assignments:
+
+```json
+{"messages": [{"role": "user", "content": "Balance the equation: Fe + O2 → Fe2O3"}], "rewards": ["accuracy"], "metadata": {"answer": "4Fe + 3O2 → 2Fe2O3"}}
+{"messages": [{"role": "user", "content": "Balance the equation: H2 + O2 → H2O"}], "rewards": ["accuracy"], "metadata": {"answer": "2H2 + O2 → 2H2O"}}
+{"messages": [{"role": "user", "content": "Balance the equation: N2 + H2 → NH3"}], "rewards": ["accuracy"], "metadata": {"answer": "N2 + 3H2 → 2NH3"}}
+```
+
+→ [Learn about training data format](https://www.reinforcenow.ai/docs/cli-reference/train-data)
+
+# Contributing
+
+We welcome contributions! ❤️ Please open an issue to discuss your ideas before submitting a PR
+
+<br>
+<div align="center">
+  <img
+    alt="ReinforceNow"
+    src="./assets/footer.png"
+    width="100%"
+  >
+</div>

rnow-0.3.1/README.md

@@ -0,0 +1,117 @@
+<div align="center">
+  <img
+    alt="ReinforceNow CLI"
+    src="./assets/header.png"
+    width="100%"
+  >
+  <br><br>
+
+[![PyPI version](https://img.shields.io/pypi/v/rnow?color=blue)](https://pypi.org/project/rnow/)
+[![Docs](https://img.shields.io/badge/docs-reinforcenow.ai-blue)](https://reinforcenow.ai/docs)
+[![Follow on X](https://img.shields.io/badge/Follow_on_X-@reinforcenow-black?labelColor=white)](https://x.com/reinforcenow)
+[![MIT License](https://img.shields.io/badge/license-MIT-green)](./LICENSE)
+
+</div>
+
+# Documentation
+
+See the [documentation](https://www.reinforcenow.ai/docs/getting-started/quickstart) for a technical overview of the platform and [train your first agent](https://www.reinforcenow.ai/docs/getting-started/first-agent)
+
+# Quick Start
+
+### 1. Install uv (Python package manager)
+
+```bash
+# macOS/Linux:
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Windows:
+PS> powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
+```
+
+### 2. Install ReinforceNow
+
+```bash
+uv init && uv venv --python 3.11
+source .venv/bin/activate  # Windows: .\.venv\Scripts\Activate.ps1
+uv pip install rnow
+```
+
+### 3. Authenticate
+
+```bash
+rnow login
+```
+
+### 4. Create & Run Your First Project
+
+```bash
+rnow init --template sft
+rnow run
+```
+
+That's it! Your training run will start on ReinforceNow's infrastructure. Monitor progress in the [dashboard](https://reinforcenow.ai/home).
+
+![ReinforceNow Graph](./assets/reinforcenow-graph.png)
+
+# Core Concepts
+
+Go from raw data to a reliable AI agent in production. ReinforceNow gives you the flexibility to define:
+
+### 1. Reward Functions
+
+Define how your model should be evaluated using the `@reward` decorator:
+
+```python
+from rnow.core import reward, RewardArgs
+
+@reward
+async def accuracy(args: RewardArgs, messages: list) -> float:
+    """Check if the model's answer matches ground truth."""
+    response = messages[-1]["content"]
+    expected = args.metadata["answer"]
+    return 1.0 if expected in response else 0.0
+```
+
+→ [Write your first reward function](https://www.reinforcenow.ai/docs/getting-started/first-reward)
+
+### 2. Tools (for Agents)
+
+Give your model the ability to call functions during training:
+
+```python
+from rnow.core import tool
+
+@tool
+def search(query: str, max_results: int = 5) -> dict:
+    """Search the web for information."""
+    # Your implementation here
+    return {"results": [...]}
+```
+
+→ [Train an agent with custom tools](https://www.reinforcenow.ai/docs/getting-started/first-agent)
+
+### 3. Training Data
+
+Create a `train.jsonl` file with your prompts and reward assignments:
+
+```json
+{"messages": [{"role": "user", "content": "Balance the equation: Fe + O2 → Fe2O3"}], "rewards": ["accuracy"], "metadata": {"answer": "4Fe + 3O2 → 2Fe2O3"}}
+{"messages": [{"role": "user", "content": "Balance the equation: H2 + O2 → H2O"}], "rewards": ["accuracy"], "metadata": {"answer": "2H2 + O2 → 2H2O"}}
+{"messages": [{"role": "user", "content": "Balance the equation: N2 + H2 → NH3"}], "rewards": ["accuracy"], "metadata": {"answer": "N2 + 3H2 → 2NH3"}}
+```
+
+→ [Learn about training data format](https://www.reinforcenow.ai/docs/cli-reference/train-data)
+
+# Contributing
+
+We welcome contributions! ❤️ Please open an issue to discuss your ideas before submitting a PR
+
+<br>
+<div align="center">
+  <img
+    alt="ReinforceNow"
+    src="./assets/footer.png"
+    width="100%"
+  >
+</div>

rnow-0.3.1/pyproject.toml

@@ -0,0 +1,81 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["rnow*"]
+
+[tool.setuptools.package-data]
+rnow = ["templates/**/*"]
+
+[project]
+name = "rnow"
+version = "0.3.1"
+description = "ReinforceNow CLI - Reinforcement Learning platform command-line interface"
+readme = "README.md"
+requires-python = ">=3.10,<3.15"
+dependencies = [
+    # Core CLI deps - lightweight, cross-platform
+    "click>=8.0.0",
+    "requests>=2.25.0",
+    "httpx>=0.24.0",
+    "pydantic>=2.0.0",
+    "pyyaml>=5.4.0",
+    "packaging>=21.0",
+    "prompt_toolkit>=3.0.0",
+    # Tokenizers for accurate token counting
+    "tokenizers>=0.15.0",
+    "openai-harmony>=0.0.8",
+]
+
+[project.optional-dependencies]
+# Local testing with ML inference (requires torch)
+test = ["tinker-cookbook>=0.1.0"]
+# API server mode
+api = ["fastapi>=0.68.0", "uvicorn>=0.15.0"]
+# MCP server support (for fetching tool schemas)
+mcp = ["fastmcp>=0.1.0"]
+# All optional features
+all = ["tinker-cookbook>=0.1.0", "fastapi>=0.68.0", "uvicorn>=0.15.0", "fastmcp>=0.1.0"]
+
+[project.scripts]
+rnow = "rnow.cli.main:main"
+
+# =============================================================================
+# Ruff configuration (linting + formatting)
+# =============================================================================
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = [
+    "E",      # pycodestyle errors
+    "F",      # pyflakes
+    "I",      # isort
+    "W",      # pycodestyle warnings
+    "UP",     # pyupgrade
+    "B",      # flake8-bugbear
+    "SIM",    # flake8-simplify
+]
+ignore = [
+    "E501",   # line too long (formatter handles)
+    "E402",   # imports not at top
+    "E722",   # bare except
+    "B008",   # function call in default arg
+    "B904",   # raise from err
+    "SIM115", # context manager for open
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["rnow"]
+
+# =============================================================================
+# Mypy configuration (type checking)
+# =============================================================================
+[tool.mypy]
+python_version = "3.10"
+warn_return_any = true
+warn_unused_ignores = true
+ignore_missing_imports = true

rnow-0.3.1/rnow/__init__.py

@@ -0,0 +1,5 @@
+"""
+ReinforceNow CLI - Command-line interface for ReinforceNow RLHF platform.
+"""
+
+__version__ = "0.8.2"

rnow-0.3.1/rnow/__main__.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python
+"""Entry point for running rnow as a module."""
+
+from rnow.cli.main import main
+
+if __name__ == "__main__":
+    main()

rnow-0.3.1/rnow/cli/__init__.py

@@ -0,0 +1,6 @@
+# reinforcenow/cli/__init__.py
+# CLI package exports
+
+from rnow.cli.main import cli
+
+__all__ = ["cli"]

rnow-0.3.1/rnow/cli/auth.py

@@ -0,0 +1,67 @@
+# reinforcenow/cli/auth.py
+
+import json
+from pathlib import Path
+
+import click
+
+# Simple home directory paths
+DATA_DIR = Path.home() / ".reinforcenow"
+CREDS_FILE = DATA_DIR / "credentials.json"
+CONFIG_FILE = DATA_DIR / "config.json"
+
+
+def is_authenticated() -> bool:
+    """Check if authenticated."""
+    try:
+        with open(CREDS_FILE) as f:
+            return "api_key" in json.load(f)
+    except (FileNotFoundError, json.JSONDecodeError, KeyError):
+        return False
+
+
+def get_auth_headers() -> dict[str, str]:
+    """Get auth headers."""
+    try:
+        with open(CREDS_FILE) as f:
+            creds = json.load(f)
+            return {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {creds['api_key']}",
+            }
+    except (FileNotFoundError, json.JSONDecodeError, KeyError):
+        raise click.ClickException("Not authenticated. Run 'reinforcenow login'")
+
+
+def get_active_org_from_config() -> str | None:
+    """Get active organization."""
+    try:
+        with open(CONFIG_FILE) as f:
+            return json.load(f).get("active_organization_id")
+    except (FileNotFoundError, json.JSONDecodeError):
+        return None
+
+
+def set_active_organization(org_id: str) -> None:
+    """Set active organization."""
+    DATA_DIR.mkdir(parents=True, exist_ok=True)
+
+    try:
+        with open(CONFIG_FILE) as f:
+            config = json.load(f)
+    except (FileNotFoundError, json.JSONDecodeError):
+        config = {}
+
+    config["active_organization_id"] = org_id
+
+    with open(CONFIG_FILE, "w") as f:
+        json.dump(config, f, indent=2)
+
+
+def logout() -> None:
+    """Remove credentials."""
+    if CREDS_FILE.exists():
+        CREDS_FILE.unlink()
+        click.echo("✓ Logged out")
+    else:
+        click.echo("Not logged in")

rnow-0.3.1/rnow/cli/blob.py

@@ -0,0 +1,98 @@
+# reinforcenow/cli/blob.py
+"""Vercel Blob upload support for large files."""
+
+from pathlib import Path
+
+import requests
+
+from rnow.cli import auth
+
+# Size threshold for blob uploads (4MB to stay under 4.5MB limit)
+MAX_INLINE_BYTES = 4 * 1024 * 1024
+
+BLOB_API_URL = "https://blob.vercel-storage.com"
+BLOB_API_VERSION = "7"
+
+
+def request_blob_client_token(base_url: str, pathname: str) -> str:
+    """
+    Request a client upload token from the backend.
+    This token allows direct upload to Vercel Blob.
+    """
+    headers = auth.get_auth_headers()
+    headers["Content-Type"] = "application/json"
+
+    payload = {
+        "type": "blob.generate-client-token",
+        "payload": {
+            "pathname": pathname,
+            "callbackUrl": f"{base_url}/dataset/upload",
+        },
+    }
+
+    resp = requests.post(
+        f"{base_url}/dataset/upload",
+        headers=headers,
+        json=payload,
+        timeout=30,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    if data.get("type") != "blob.generate-client-token":
+        raise RuntimeError(f"Unexpected response from blob token endpoint: {data}")
+
+    client_token = data.get("clientToken")
+    if not client_token:
+        raise RuntimeError("No clientToken returned from blob token endpoint")
+
+    return client_token
+
+
+def upload_file_to_blob(base_url: str, local_path: Path, blob_pathname: str) -> dict:
+    """
+    Upload a file directly to Vercel Blob using a client token.
+    Returns the blob JSON (contains url, pathname, etc).
+    """
+    client_token = request_blob_client_token(base_url, blob_pathname)
+
+    url = f"{BLOB_API_URL}/{blob_pathname.lstrip('/')}"
+    headers = {
+        "Authorization": f"Bearer {client_token}",
+        "x-api-version": BLOB_API_VERSION,
+        "x-content-type": "application/jsonl",
+    }
+
+    with open(local_path, "rb") as f:
+        resp = requests.put(url, headers=headers, data=f, timeout=300)
+
+    resp.raise_for_status()
+    return resp.json()
+
+
+def maybe_upload_to_blob(
+    base_url: str,
+    file_path: Path,
+    dataset_id: str,
+) -> tuple[str | None, dict | None]:
+    """
+    Check if file needs blob upload and handle it.
+
+    Returns:
+        (inline_contents, blob_info)
+        - If small: inline_contents is file content, blob_info is None
+        - If large: inline_contents is None, blob_info has url/pathname
+    """
+    size = file_path.stat().st_size
+
+    if size <= MAX_INLINE_BYTES:
+        # Small file - return contents for inline upload
+        return None, None
+
+    # Large file - upload to blob
+    import uuid
+
+    blob_pathname = f"datasets/{dataset_id}/{uuid.uuid4().hex[:8]}-{file_path.name}"
+
+    blob = upload_file_to_blob(base_url, file_path, blob_pathname)
+    return None, blob