orbitals 0.1.2__tar.gz → 0.1.3__tar.gz

orbitals-0.1.3/.github/workflows/publish.yml

@@ -0,0 +1,26 @@
+name: "Publish"
+
+on:
+  release:
+    types:
+      - created
+
+jobs:
+  run:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write
+      contents: read
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+      - name: Install Python 3.13
+        run: uv python install 3.13
+      - name: Build
+        run: uv build
+      - name: Publish
+        run: uv publish

{orbitals-0.1.2 → orbitals-0.1.3}/AGENTS.md

@@ -20,15 +20,12 @@ This is done by prompting **local LLMs**.
     
 ## Project Structure
 
-The API implementation is entirely in Python, using `uv` as the package manager. We are adopting a mono-repo approach, with the `packages/` folder structured as follows:
-
-/src/transformers: 
-/models: 
+The API implementation is entirely in Python, using `uv` as the package manager. Project structure is as follows:
 
 * `src/orbitals/`: This contains the core source code for the library.
-    * `src/orbitals/cli`: code for root `orbitals` cli. It's a Typer app that imports and adds the apps defined by each orbital.
-    * `src/orbitals/scope_guard`:
-        * `src/orbitals/scope_guard/guards/`: Code for individual scope guards. Starting from the `BaseScopeGuard` root class, we find two subclasses, `ScopeGuard` (sync guard and batch-guard methods) and `AsyncScopeGuard` (async counterpart).
+    * `src/orbitals/cli`: Code for root `orbitals` cli. It's a Typer app that imports and adds the apps defined by each orbital.
+    * `src/orbitals/scope_guard`: This contains the code for the `ScopeGuard` orbital.
+        * `src/orbitals/scope_guard/guards/`: Code for individual scope guards. Starting from the `BaseScopeGuard` root class, we find two subclasses, `ScopeGuard` (sync validate and batch-validate methods) and `AsyncScopeGuard` (async counterpart).
         * `src/orbitals/scope_guard/cli/`: This contains the CLI commands of `scope-guard`.
         * `src/orbitals/scope_guard/serving/`: This contains the FastAPI serving implementation.
 

{orbitals-0.1.2 → orbitals-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orbitals
-Version: 0.1.2
+Version: 0.1.3
 Summary: LLM Guardrails tailored to your Principles
 Author-email: Luigi Procopio <luigi@principled-intelligence.com>, Edoardo Barba <edoardo@principled-intelligence.com>
 License: Apache-2.0

{orbitals-0.1.2 → orbitals-0.1.3}/README.scope-guard.md

@@ -5,9 +5,9 @@
             <a href="https://principled-intelligence.com/news/introducing-scope-guard">
                 <img src="https://img.shields.io/badge/Blog-Article-blue" />
             </a>
-            <a href="https://demo.halo.principled.app">
+            <!-- <a href="https://demo.halo.principled.app">
                 <img src="https://img.shields.io/badge/Live-Demo-green" />
-            </a>
+            </a> -->
             <a href="https://colab.research.google.com/drive/1iBJog8H4QpS3_Y2powR5tidUhWJNajw2">
                 <img src="https://colab.research.google.com/assets/colab-badge.svg" />
             </a>

{orbitals-0.1.2 → orbitals-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "orbitals"
-version = "0.1.2"
+version = "0.1.3"
 description = "LLM Guardrails tailored to your Principles"
 readme = "README.md"
 

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/scope_guard/cli/serve.py

@@ -38,7 +38,9 @@ def serve(
         "0.0.0.0", "-h", "--host", help="The host to use for the server"
     ),
     vllm_port: int = typer.Option(8001, help="The port to use for the vLLM server"),
-    vllm_max_model_len: int = typer.Option(15000, help="Maximum model length for vLLM"),
+    vllm_max_model_len: int = typer.Option(
+        30_000, help="Maximum model length for vLLM"
+    ),
     vllm_max_num_seqs: int = typer.Option(
         2, help="Maximum number of sequences for vLLM"
     ),

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/scope_guard/guards/api.py

@@ -106,7 +106,7 @@ class APIScopeGuard(ScopeGuard):
         skip_evidences: bool | None = None,
     ) -> ScopeGuardOutput:
         response = requests.post(
-            f"{self.api_url}/api/orbitals/scope-guard/validate",
+            f"{self.api_url}/orbitals/scope-guard/validate",
             json=_build_request_data(
                 conversation,
                 skip_evidences if skip_evidences is not None else self.skip_evidences,
@@ -134,7 +134,7 @@ class APIScopeGuard(ScopeGuard):
         skip_evidences: bool | None = None,
     ) -> list[ScopeGuardOutput]:
         response = requests.post(
-            f"{self.api_url}/api/orbitals/scope-guard/batch-validate",
+            f"{self.api_url}/orbitals/scope-guard/batch-validate",
             json=_build_batch_request_data(
                 conversations,
                 skip_evidences if skip_evidences is not None else self.skip_evidences,
@@ -185,7 +185,7 @@ class AsyncAPIScopeGuard(AsyncScopeGuard):
     ) -> ScopeGuardOutput:
         async with aiohttp.ClientSession() as session:
             response = await session.post(
-                f"{self.api_url}/api/in/scope-guard/validate",
+                f"{self.api_url}/in/scope-guard/validate",
                 json=_build_request_data(
                     conversation,
                     skip_evidences
@@ -216,7 +216,7 @@ class AsyncAPIScopeGuard(AsyncScopeGuard):
     ) -> list[ScopeGuardOutput]:
         async with aiohttp.ClientSession() as session:
             response = await session.post(
-                f"{self.api_url}/api/in/scope-guard/batch-validate",
+                f"{self.api_url}/in/scope-guard/batch-validate",
                 json=_build_batch_request_data(
                     conversations,
                     skip_evidences

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/scope_guard/guards/base.py

@@ -152,7 +152,7 @@ class ScopeGuard(BaseScopeGuard):
         skip_evidences: bool = False,
         temperature: float = 0.0,
         max_tokens: int = 3000,
-        max_model_len: int = 15_000,
+        max_model_len: int = 30_000,
         max_num_seqs: int = 2,
     ) -> VLLMScopeGuard: ...
 

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/scope_guard/guards/vllm.py

@@ -27,7 +27,7 @@ class VLLMScopeGuard(ScopeGuard):
         skip_evidences: bool = False,
         temperature: float = 0.0,
         max_tokens: int = 3000,
-        max_model_len: int = 15_000,
+        max_model_len: int = 30_000,
         max_num_seqs: int = 2,
         gpu_memory_utilization: float = 0.9,
     ):

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/scope_guard/modeling.py

@@ -1,7 +1,7 @@
 from enum import Enum
-from typing import Literal
+from typing import Annotated, Any, Literal
 
-from pydantic import BaseModel, TypeAdapter
+from pydantic import BaseModel, BeforeValidator, TypeAdapter
 
 from ..types import ConversationMessage, LLMUsage
 
@@ -66,6 +66,23 @@ class ConversationUserMessage(BaseModel):
     content: str
 
 
-ScopeGuardInput = str | ConversationUserMessage | list[ConversationMessage]
+def _select_model_based_on_fields(
+    v: Any,
+) -> str | ConversationUserMessage | list[ConversationMessage]:
+    if isinstance(v, str):
+        return TypeAdapter(str).validate_python(v)
+    elif isinstance(v, dict):
+        return TypeAdapter(ConversationUserMessage).validate_python(v)
+    elif isinstance(v, list):
+        return TypeAdapter(list[ConversationMessage]).validate_python(v)
+
+    # no matching model found, let's fall back to standard pydantic behavior
+    return v
+
+
+ScopeGuardInput = Annotated[
+    str | ConversationUserMessage | list[ConversationMessage],
+    BeforeValidator(_select_model_based_on_fields),
+]
 
 ScopeGuardInputTypeAdapter = TypeAdapter(ScopeGuardInput)

{orbitals-0.1.2 → orbitals-0.1.3}/src/orbitals/utils.py

@@ -17,7 +17,7 @@ def maybe_configure_gpu_usage():
         return
 
     try:
-        import pynvml  # ty: ignore[unresolved-import]  # provided by nvidia-ml-py
+        import pynvml  # ty: ignore[unresolved-import]
     except ModuleNotFoundError:
         logging.debug("nvidia-ml-py not available, skipping GPU auto-configuration")
         return

{orbitals-0.1.2 → orbitals-0.1.3}/uv.lock

@@ -2919,7 +2919,7 @@ wheels = [
 
 [[package]]
 name = "orbitals"
-version = "0.1.2"
+version = "0.1.3"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

orbitals-0.1.2/.dockerignore

@@ -1,5 +0,0 @@
-.venv
-dist
-__pycache__/
-.vscode/
-examples/

orbitals-0.1.2/Dockerfile

@@ -1,23 +0,0 @@
-FROM vllm/vllm-openai:v0.14.1
-
-ARG DEBIAN_FRONTEND=noninteractive
-
-COPY --from=ghcr.io/astral-sh/uv:0.9.8-debian-slim /usr/local/bin/uv /usr/local/bin/uvx /bin/
-
-WORKDIR /app
-ENV PATH="/app/.venv/bin:$PATH"
-ENV UV_COMPILE_BYTECODE=1
-
-ARG MODEL
-ENV MODEL=${MODEL}
-
-RUN hf download ${MODEL}
-
-COPY pyproject.toml uv.lock README.md src /app/src/
-
-RUN pip install -e .[serving]
-
-EXPOSE 8000
-
-ENTRYPOINT ["/bin/bash", "-c"]
-CMD ["orbitals scope-guard serve ${MODEL} --port 8000 --host 0.0.0.0"]

orbitals-0.1.2/Dockerfile copy

@@ -1,52 +0,0 @@
-FROM nvidia/cuda:13.1.1-cudnn-devel-ubuntu24.04 AS builder
-
-ARG DEBIAN_FRONTEND=noninteractive
-
-COPY --from=ghcr.io/astral-sh/uv:0.9.8-debian-slim /usr/local/bin/uv /usr/local/bin/uvx /bin/
-
-WORKDIR /app
-ENV PATH="/app/.venv/bin:$PATH"
-ENV UV_COMPILE_BYTECODE=1
-
-RUN \
-    apt-get update && \
-    apt-get install -y --no-install-recommends git python3.12
-
-COPY pyproject.toml uv.lock README.md /app/
-
-RUN --mount=type=cache,target=/root/.cache/uv \
-    uv venv -p 3.12 && \
-    uv sync --frozen --extra scope-guard-serve --no-install-project --no-dev
-
-ARG MODEL
-RUN hf download ${MODEL}
-
-COPY src /app/src/
-
-RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --locked --extra scope-guard-serve --no-editable --no-dev
-
-# TODO remove next line
-ENTRYPOINT ["/bin/bash", "-c"]
-
-FROM nvidia/cuda:13.1.1-cudnn-runtime-ubuntu24.04 AS runner
-
-WORKDIR /app
-ENV PATH="/app/.venv/bin:$PATH"
-
-RUN \
-    apt-get update && \
-    apt-get install -y --no-install-recommends python3.12
-
-COPY --from=builder /app/.venv/ /app/.venv/
-
-RUN mkdir -p /root/.cache/huggingface/hub
-COPY --from=builder /root/.cache/huggingface/hub /root/.cache/huggingface/hub
-
-EXPOSE 8000
-
-ARG MODEL
-ENV MODEL=${MODEL}
-
-ENTRYPOINT ["/bin/bash", "-c"]
-CMD ["orbitals scope-guard serve ${MODEL} --port 8000 --host 0.0.0.0"]

orbitals-0.1.2/examples/scope-guard/test.py

@@ -1,27 +0,0 @@
-def main():
-    from orbitals.scope_guard import ScopeGuard
-
-    sg = ScopeGuard(
-        backend="vllm",
-        model="scope-guard-q",  # for the Qwen-family model
-        # model="scope-guard-g",  # for the Gemma-family model
-    )
-
-    ai_service_description = """
-    You are a virtual assistant for a parcel delivery service.
-    You can only answer questions about package tracking.
-    Never respond to requests for refunds.
-    """
-
-    user_query = "If the package hasn't arrived by tomorrow, can I get my money back?"
-    result = sg.validate(user_query, ai_service_description)
-
-    print(f"Scope: {result.scope_class.value}")
-    if result.evidences:
-        print("Evidences:")
-        for evidence in result.evidences:
-            print(f"  - {evidence}")
-
-
-if __name__ == "__main__":
-    main()

orbitals-0.1.2/examples/scope-guard/vllm_serve.py

@@ -1,55 +0,0 @@
-import argparse
-import asyncio
-import time
-
-from orbitals.scope_guard import AsyncScopeGuard
-
-
-async def main():
-    args = parse_args()
-
-    classifier = AsyncScopeGuard(
-        backend="vllm-api",
-        model=args.model,
-        skip_evidences=args.skip_evidences,
-        vllm_serving_url=args.vllm_serving_url,
-    )
-
-    user_question = (
-        "If the package hasn't arrived by tomorrow, can I get my money back?"
-    )
-    ai_service_description = (
-        "You are a virtual assistant for a parcel delivery service. "
-        "You can only answer questions about package tracking. "
-        "Never respond to requests for refunds."
-    )
-
-    start_time = time.time()
-    result = await classifier.validate(user_question, ai_service_description)
-    end_time = time.time()
-
-    print(f"# scope: {result.scope_class}")
-    if result.evidences:
-        print("# evidences:")
-        for evidence in result.evidences:
-            print(f"  * evidence: {evidence}")
-
-    print(f"# model: {result.model}")
-    print("# usage:")
-    print(f"  * prompt tokens: {result.usage.prompt_tokens}")
-    print(f"  * completion tokens: {result.usage.completion_tokens}")
-    print(f"  * total tokens: {result.usage.total_tokens}")
-
-    print(f"# time: {end_time - start_time:.2f} seconds")
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("model", type=str)
-    parser.add_argument("--vllm-serving-url", type=str)
-    parser.add_argument("-s", "--skip-evidences", action="store_true", default=False)
-    return parser.parse_args()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

orbitals-0.1.2/src/scripts/playground.ipynb

@@ -1,267 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "f616f063",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from orbitals.scope_guard.prompting import ScopeClass"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "1ff6a768",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "**Name**: Directly Supported\n",
-      "**Description**: The user's query can be definitively handled by the AI Service given the functionalities, knowledge scope, and capabilities described in the AI Service Description.\n",
-      "\n",
-      "**Name**: Potentially Supported\n",
-      "**Description**: The user's query can be plausibly handled by the AI Service given the functionalities, knowledge scope, and capabilities described in the AI Service Description. The request is a reasonable extension or interpretation of the service's capabilities that might be within scope.\n",
-      "\n",
-      "**Name**: Out of Scope\n",
-      "**Description**: The user's query is outside the AI Service's role and functionalities. It's incompatible with the service's documented purpose.\n",
-      "\n",
-      "**Name**: Restricted\n",
-      "**Description**: The user's query cannot be handled by the AI Service due to either behavioral restrictions (content/advice the service must refuse to provide) or service limitations (technical constraints, access restrictions, or knowledge scope limitations).\n",
-      "**Examples**:\n",
-      "* Do not provide personalized financial advice. → User: Should I invest my savings in Bitcoin?\n",
-      "* The AI service does not have access to real-time data. → User: What's the current stock price of Apple?\n",
-      "* AI service cannot access external databases. → User: Look up my account balance in the system.\n",
-      "\n",
-      "**Name**: Chit Chat\n",
-      "**Description**: The user's query is a casual or social interaction that does not pertain to the AI Service's functionalities, knowledge scope, or operational capabilities.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ScopeClass.get_classes_manifest())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "ec2d936b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from orbitals.scope_guard.prompting import SYSTEM_PROMPT"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "991a9bf0",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "You are an expert AI classifier specialized in classifying user queries given the description of an AI service.\n",
-      "\n",
-      "Your task is to classify the LAST USER MESSAGE in a conversation between a user and an AI Service. Follow these steps:\n",
-      "\n",
-      "1. **Extract Evidence**: Identify and quote specific excerpts from the AI Service Description that are relevant to understanding whether and how the AI Service can handle the LAST USER MESSAGE. Look for:\n",
-      "   - Functionalities that might address the user's query\n",
-      "   - Explicit restrictions or limitations mentioned\n",
-      "   - Knowledge scope boundaries\n",
-      "   - Any relevant service capabilities or constraints\n",
-      "\n",
-      "2. **Classify**: Based on the evidence extracted, assign one of the classification classes below to the LAST USER MESSAGE.\n",
-      "\n",
-      "## Classification Classes\n",
-      "\n",
-      "**Name**: Directly Supported\n",
-      "**Description**: The user's query can be definitively handled by the AI Service given the functionalities, knowledge scope, and capabilities described in the AI Service Description.\n",
-      "\n",
-      "**Name**: Potentially Supported\n",
-      "**Description**: The user's query can be plausibly handled by the AI Service given the functionalities, knowledge scope, and capabilities described in the AI Service Description. The request is a reasonable extension or interpretation of the service's capabilities that might be within scope.\n",
-      "\n",
-      "**Name**: Out of Scope\n",
-      "**Description**: The user's query is outside the AI Service's role and functionalities. It's incompatible with the service's documented purpose.\n",
-      "\n",
-      "**Name**: Restricted\n",
-      "**Description**: The user's query cannot be handled by the AI Service due to either behavioral restrictions (content/advice the service must refuse to provide) or service limitations (technical constraints, access restrictions, or knowledge scope limitations).\n",
-      "**Examples**:\n",
-      "* Do not provide personalized financial advice. → User: Should I invest my savings in Bitcoin?\n",
-      "* The AI service does not have access to real-time data. → User: What's the current stock price of Apple?\n",
-      "* AI service cannot access external databases. → User: Look up my account balance in the system.\n",
-      "\n",
-      "**Name**: Chit Chat\n",
-      "**Description**: The user's query is a casual or social interaction that does not pertain to the AI Service's functionalities, knowledge scope, or operational capabilities.\n",
-      "\n",
-      "## Important Guidelines\n",
-      "* Base your classification EXCLUSIVELY on the AI Service Description provided.\n",
-      "* Pay special attention to RESTRICTIONS, CONSTRAINTS, and LIMITATIONS sections in the AI Service Description.\n",
-      "* Extract evidence first, then use it to inform your classification decision.\n",
-      "* Quote excerpts verbatim from the AI Service Description as evidence.\n",
-      "\n",
-      "Output the classification in the following JSON schema:\n",
-      "{\"$defs\": {\"ScopeClass\": {\"enum\": [\"Directly Supported\", \"Potentially Supported\", \"Out of Scope\", \"Restricted\", \"Chit Chat\"], \"title\": \"ScopeClass\", \"type\": \"string\"}}, \"properties\": {\"evidences\": {\"anyOf\": [{\"items\": {\"type\": \"string\"}, \"type\": \"array\"}, {\"type\": \"null\"}], \"default\": null, \"description\": \"Excerpts quoted directly from the AI Service Description that are relevant to understanding whether and how the AI Service can handle the LAST USER MESSAGE.\", \"title\": \"Evidences\"}, \"scope_class\": {\"$ref\": \"#/$defs/ScopeClass\", \"description\": \"The classification assigned to the LAST USER MESSAGE based on the evidence extracted from the AI Service Description.\"}}, \"required\": [\"scope_class\"], \"title\": \"ScopeGuardResponseModel\", \"type\": \"object\"}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(SYSTEM_PROMPT)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "7f850a8f",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/poccio/principled-intelligence/projects/orbitals/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<|im_start|>system\n",
-      "You are a friendly chatbot who always responds in the style of a pirate<|im_end|>\n",
-      "<|im_start|>user\n",
-      "How many helicopters can a human eat in one sitting?<|im_end|>\n",
-      "<|im_start|>assistant\n",
-      "<think>\n",
-      "\n",
-      "</think>\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import AutoTokenizer\n",
-    "\n",
-    "tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen3-4B\")\n",
-    "messages = [\n",
-    "    {\"role\": \"system\", \"content\": \"You are a friendly chatbot who always responds in the style of a pirate\",},\n",
-    "    {\"role\": \"user\", \"content\": \"How many helicopters can a human eat in one sitting?\"},\n",
-    "]\n",
-    "\n",
-    "prompt = tokenizer.apply_chat_template(\n",
-    "    messages, \n",
-    "        tokenize=False,\n",
-    "        add_generation_prompt=True,\n",
-    "        enable_thinking=False,)\n",
-    "\n",
-    "    \n",
-    "print(prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "475af9cc",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e803ba74",
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ValidationError",
-     "evalue": "3 validation errors for AIServiceDescription\nconduct_guidelines\n  Extra inputs are not permitted [type=extra_forbidden, input_value='Respond clearly and fact...ser clarity and safety.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden\nconstraints\n  Extra inputs are not permitted [type=extra_forbidden, input_value='Cannot modify shipments,...vailable tracking data.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden\nfallback\n  Extra inputs are not permitted [type=extra_forbidden, input_value='If tracking data is miss... inventing information.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[1], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01morbitals\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtypes\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AIServiceDescription\n\u001b[0;32m----> 3\u001b[0m ai_service_description_complete \u001b[38;5;241m=\u001b[39m \u001b[43mAIServiceDescription\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m    \u001b[49m\u001b[43midentity_role\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mYou are PackAssist, a virtual assistant designed to help users understand and \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      6\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtrack their parcel shipments. Your objective is to interpret tracking data and \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      7\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mguide users through delivery-related questions.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      8\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      9\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mThe service operates within a parcel-delivery environment where users interact \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     11\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mto check the status of shipments sent domestically or internationally. Typical \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     12\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43musers are customers awaiting deliveries or sending parcels.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     13\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfunctionalities\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     15\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mRetrieve tracking updates; explain the meaning of tracking events; provide \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     16\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mestimated delivery windows; assist users in understanding delays or routing steps.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     17\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     18\u001b[0m \u001b[43m    \u001b[49m\u001b[43mknowledge_scope\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     19\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mPublic tracking information, standard logistics workflows, typical transit times, \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     20\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mand general procedures for parcel movement. No access to payment, refund, or claim \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     21\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprocessing systems.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     22\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     23\u001b[0m \u001b[43m    \u001b[49m\u001b[43mconduct_guidelines\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     24\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mRespond clearly and factually; do not speculate on unavailable data; avoid any \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     25\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrefund-related discussion; do not provide financial, legal, or compensation advice; \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     26\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprioritize user clarity and safety.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     27\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     28\u001b[0m \u001b[43m    \u001b[49m\u001b[43mconstraints\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     29\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCannot modify shipments, initiate refunds, open claims, contact drivers, or view \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     30\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minternal logistics notes. Limited strictly to interpreting publicly available \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     31\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtracking data.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     32\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     33\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfallback\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m     34\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mIf tracking data is missing or the request is outside the allowed scope, inform \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     35\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mthe user clearly and redirect them to alternative support channels without \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     36\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minventing information.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     37\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     38\u001b[0m \u001b[43m    \u001b[49m\u001b[43mwebsite_url\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhttps://www.trackmate-delivery.com\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     39\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m     41\u001b[0m \u001b[38;5;28mprint\u001b[39m(ai_service_description_complete\u001b[38;5;241m.\u001b[39mmodel_dump_json(indent\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m4\u001b[39m))\n",
-      "File \u001b[0;32m~/principled-intelligence/projects/orbitals/.venv/lib/python3.10/site-packages/pydantic/main.py:250\u001b[0m, in \u001b[0;36mBaseModel.__init__\u001b[0;34m(self, **data)\u001b[0m\n\u001b[1;32m    248\u001b[0m \u001b[38;5;66;03m# `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks\u001b[39;00m\n\u001b[1;32m    249\u001b[0m __tracebackhide__ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m--> 250\u001b[0m validated_self \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__pydantic_validator__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalidate_python\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mself_instance\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    251\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m validated_self:\n\u001b[1;32m    252\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m    253\u001b[0m         \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mA custom validator is returning a value other than `self`.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    254\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mReturning anything other than `self` from a top level model validator isn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt supported when validating via `__init__`.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    255\u001b[0m         \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSee the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m    256\u001b[0m         stacklevel\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m,\n\u001b[1;32m    257\u001b[0m     )\n",
-      "\u001b[0;31mValidationError\u001b[0m: 3 validation errors for AIServiceDescription\nconduct_guidelines\n  Extra inputs are not permitted [type=extra_forbidden, input_value='Respond clearly and fact...ser clarity and safety.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden\nconstraints\n  Extra inputs are not permitted [type=extra_forbidden, input_value='Cannot modify shipments,...vailable tracking data.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden\nfallback\n  Extra inputs are not permitted [type=extra_forbidden, input_value='If tracking data is miss... inventing information.', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/extra_forbidden"
-     ]
-    }
-   ],
-   "source": [
-    "from orbitals.types import AIServiceDescription\n",
-    "\n",
-    "ai_service_description_complete = AIServiceDescription(\n",
-    "    identity_role=(\n",
-    "        \"You are PackAssist, a virtual assistant designed to help users understand and \"\n",
-    "        \"track their parcel shipments. Your objective is to interpret tracking data and \"\n",
-    "        \"guide users through delivery-related questions.\"\n",
-    "    ),\n",
-    "    context=(\n",
-    "        \"The service operates within a parcel-delivery environment where users interact \"\n",
-    "        \"to check the status of shipments sent domestically or internationally. Typical \"\n",
-    "        \"users are customers awaiting deliveries or sending parcels.\"\n",
-    "    ),\n",
-    "    functionalities=(\n",
-    "        \"Retrieve tracking updates; explain the meaning of tracking events; provide \"\n",
-    "        \"estimated delivery windows; assist users in understanding delays or routing steps.\"\n",
-    "    ),\n",
-    "    knowledge_scope=(\n",
-    "        \"Public tracking information, standard logistics workflows, typical transit times, \"\n",
-    "        \"and general procedures for parcel movement. No access to payment, refund, or claim \"\n",
-    "        \"processing systems.\"\n",
-    "    ),\n",
-    "    conduct_guidelines=(\n",
-    "        \"Respond clearly and factually; do not speculate on unavailable data; avoid any \"\n",
-    "        \"refund-related discussion; do not provide financial, legal, or compensation advice; \"\n",
-    "        \"prioritize user clarity and safety.\"\n",
-    "    ),\n",
-    "    constraints=(\n",
-    "        \"Cannot modify shipments, initiate refunds, open claims, contact drivers, or view \"\n",
-    "        \"internal logistics notes. Limited strictly to interpreting publicly available \"\n",
-    "        \"tracking data.\"\n",
-    "    ),\n",
-    "    fallback=(\n",
-    "        \"If tracking data is missing or the request is outside the allowed scope, inform \"\n",
-    "        \"the user clearly and redirect them to alternative support channels without \"\n",
-    "        \"inventing information.\"\n",
-    "    ),\n",
-    "    website_url=\"https://www.trackmate-delivery.com\",\n",
-    ")\n",
-    "\n",
-    "print(ai_service_description_complete.model_dump_json(indent=4))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ba983336",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "orbitals",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

orbitals-0.1.2/src/scripts/push_hf_pipeline.py

@@ -1,20 +0,0 @@
-from transformers import AutoModelForSequenceClassification, pipeline
-from transformers.pipelines import PIPELINE_REGISTRY
-
-from hf_pipeline.scope_guard import ScopeGuardPipeline
-
-
-def main():
-    PIPELINE_REGISTRY.register_pipeline(
-        "scope-guard",
-        pipeline_class=ScopeGuardPipeline,
-        pt_model=AutoModelForSequenceClassification,
-        default={"pt": ("principled-intelligence/scope-guard-4B-q-2601", "631addd")},
-    )
-
-    p = pipeline(task="scope-guard")
-    p.push_to_hub("principled-intelligence/scope-guard", private=False)
-
-
-if __name__ == "__main__":
-    main()

orbitals-0.1.2/src/scripts/push_model.py

@@ -1,32 +0,0 @@
-import os
-
-from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
-from transformers.pipelines import PIPELINE_REGISTRY
-
-
-def main():
-    config = AutoConfig.from_pretrained(
-        "principled-intelligence/scope-classifier-Qwen3-1.7B-v0.4"
-    )
-    config.custom_pipelines = {
-        "scope-classification": {
-            "impl": "principled-intelligence/scope-guard--scope_guard.ScopeGuardPipeline",
-            "pt": "AutoModelForCausalLM",
-        }
-    }
-
-    model = AutoModelForCausalLM.from_pretrained(
-        "principled-intelligence/scope-classifier-Qwen3-1.7B-v0.4",
-        config=config,
-    )
-
-    tokenizer = AutoTokenizer.from_pretrained(
-        "principled-intelligence/scope-classifier-Qwen3-1.7B-v0.4",
-    )
-
-    model.push_to_hub("poccio/scope-classifier-Qwen3-1.7B-v0.4", private=True)
-    tokenizer.push_to_hub("poccio/scope-classifier-Qwen3-1.7B-v0.4", private=True)
-
-
-if __name__ == "__main__":
-    main()