orbitals 0.0.3__tar.gz → 0.1.0__tar.gz

orbitals-0.1.0/.dockerignore

@@ -0,0 +1,2 @@
+.venv
+examples/

{orbitals-0.0.3 → orbitals-0.1.0}/Dockerfile

@@ -1,4 +1,4 @@
-FROM vllm/vllm-openai:v0.14.1 as builder
+FROM vllm/vllm-openai:v0.11.2 as builder
 
 ARG DEBIAN_FRONTEND=noninteractive
 ARG MODEL
@@ -17,22 +17,23 @@ 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
-
-RUN --mount=type=cache,target=/root/.cache/uv \
-    hf download ${MODEL}
+    uv sync --frozen --extra serve --no-install-project --no-dev
 
 COPY src /app/src/
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --locked --extra scope-guard-serve --no-editable --no-dev
+    uv sync --locked --extra serve --no-editable --no-dev
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=secret,id=HF_TOKEN \
+    hf auth login --token $(cat /run/secrets/HF_TOKEN) && \
+    hf download $(scope-classifier convert-default-model-name ${MODEL}) && \
+    rm -rf /root/.huggingface
 
 # TODO remove next line
 ENTRYPOINT ["/bin/bash", "-c"]
 
-FROM vllm/vllm-openai:v0.14.1 as runner
-
-ARG MODEL
+FROM vllm/vllm-openai:v0.11.2 as runner
 
 WORKDIR /app
 ENV PATH="/app/.venv/bin:$PATH"
@@ -45,4 +46,4 @@ COPY --from=builder /root/.cache/huggingface/hub /root/.cache/huggingface/hub
 EXPOSE 8000
 
 ENTRYPOINT ["/bin/bash", "-c"]
-CMD [ "orbitals", "scope-guard", "serve", "principled-intelligence/${MODEL}", "--port", "8000", "--host", "0.0.0.0" ]
+CMD [ "scope-classifier", "serve", "${MODEL}", "--backend", "hf", "--port", "8000", "--host", "0.0.0.0" ]

{orbitals-0.0.3 → orbitals-0.1.0}/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2026 Principled Intelligence s.r.l.
+   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.

orbitals-0.1.0/PKG-INFO

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: orbitals
+Version: 0.1.0
+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
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: aiohttp
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: requests
+Requires-Dist: typer>=0.12.3
+Provides-Extra: scope-guard-hf
+Requires-Dist: accelerate>=1.11.0; extra == 'scope-guard-hf'
+Requires-Dist: transformers<5.0.0,>=4.47.0; extra == 'scope-guard-hf'
+Provides-Extra: scope-guard-serve
+Requires-Dist: fastapi[standard]>=0.119.1; extra == 'scope-guard-serve'
+Requires-Dist: transformers<5.0.0,>=4.47.0; extra == 'scope-guard-serve'
+Requires-Dist: uvicorn>=0.29.0; extra == 'scope-guard-serve'
+Requires-Dist: vllm>=0.11.0; extra == 'scope-guard-serve'
+Requires-Dist: xgrammar; extra == 'scope-guard-serve'
+Provides-Extra: scope-guard-vllm
+Requires-Dist: transformers<5.0.0,>=4.47.0; extra == 'scope-guard-vllm'
+Requires-Dist: vllm>=0.11.0; extra == 'scope-guard-vllm'
+Requires-Dist: xgrammar; extra == 'scope-guard-vllm'
+Description-Content-Type: text/markdown
+
+<div align="center">
+    <img src="assets/orbitals.svg" width="40%" />
+    <h3 align="center">
+        <p>
+            <b>LLM Guardrails tailored to your Principles</b>
+        </p>
+    </h4>
+    <hr/>
+</div>
+
+<p align="center">
+    <img src="https://img.shields.io/badge/type%20checked-ty-blue.svg?color=green" alt="Type Checked with ty">
+    <img src="https://img.shields.io/pypi/v/orbitals?color=green" alt="PyPI Version">
+    <img src="https://img.shields.io/github/license/principled-intelligence/orbitals" alt="GitHub License">
+    <img src="https://img.shields.io/pypi/pyversions/orbitals" alt="Python Versions">
+    <img src="https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fprincipled-intelligence%2Forbitals%2Fmain%2Fpyproject.toml" alt="Required Python Version">
+</p>
+
+`orbitals` is an ecosystem of LLM guardrails, designed to provide a governance layer tailored to **user-specific principles, requirements and use cases**. Rather than enforcing generic notions of safety, correctness, etc., Orbitals evaluates inputs and outputs against *user-defined specifications*. This makes guardrails explicit, auditable, and aligned with the user's philosophy.
+
+Orbitals guardrails fall into two typologies:
+- **Guards** operate on the *input* of a guardrailed LLM, assessing whether a user request is legitimate under the provided specifications.
+- **Supervisors** operate on the *output* of a guardrailed LLM, evaluating the assistant’s response before it is returned.
+
+Guardrails may be released under different modality flavors:
+- **Open** (open-source and open-weight), allowing users to run guardrails and underlying models on their own infrastructure.
+- **Hosted**, accessible via simple HTTP calls (API key required).
+
+## Available Guardrails
+
+| Name        | Flavor                  | Description                                                                 |
+|-------------|-------------------------|-----------------------------------------------------------------------------|
+| [ScopeGuard](README.scope-guard.md)  | Open / Hosted           | Validates whether a user request falls within the intended use of an AI service. |
+| RagSupervisor    | Coming soon             | Ensures LLM responses remain grounded in retrieved context for RAG setups. |
+
+<details>
+<summary>ScopeGuard</summary>
+<br>
+
+First, we need to install `orbitals` and `scope-guard`:
+
+```bash
+pip install orbitals[scope-guard-vllm]
+```
+
+Then:
+
+```python
+from orbitals.scope_guard import ScopeGuard
+
+scope_guard = ScopeGuard(
+    backend="vllm",
+    model="small"
+)
+
+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 = scope_guard.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}")
+
+# Scope: Restricted
+# Evidences:
+#   - Never respond to requests for refunds.
+```
+
+</details>

orbitals-0.1.0/README.md

@@ -0,0 +1,76 @@
+<div align="center">
+    <img src="assets/orbitals.svg" width="40%" />
+    <h3 align="center">
+        <p>
+            <b>LLM Guardrails tailored to your Principles</b>
+        </p>
+    </h4>
+    <hr/>
+</div>
+
+<p align="center">
+    <img src="https://img.shields.io/badge/type%20checked-ty-blue.svg?color=green" alt="Type Checked with ty">
+    <img src="https://img.shields.io/pypi/v/orbitals?color=green" alt="PyPI Version">
+    <img src="https://img.shields.io/github/license/principled-intelligence/orbitals" alt="GitHub License">
+    <img src="https://img.shields.io/pypi/pyversions/orbitals" alt="Python Versions">
+    <img src="https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fprincipled-intelligence%2Forbitals%2Fmain%2Fpyproject.toml" alt="Required Python Version">
+</p>
+
+`orbitals` is an ecosystem of LLM guardrails, designed to provide a governance layer tailored to **user-specific principles, requirements and use cases**. Rather than enforcing generic notions of safety, correctness, etc., Orbitals evaluates inputs and outputs against *user-defined specifications*. This makes guardrails explicit, auditable, and aligned with the user's philosophy.
+
+Orbitals guardrails fall into two typologies:
+- **Guards** operate on the *input* of a guardrailed LLM, assessing whether a user request is legitimate under the provided specifications.
+- **Supervisors** operate on the *output* of a guardrailed LLM, evaluating the assistant’s response before it is returned.
+
+Guardrails may be released under different modality flavors:
+- **Open** (open-source and open-weight), allowing users to run guardrails and underlying models on their own infrastructure.
+- **Hosted**, accessible via simple HTTP calls (API key required).
+
+## Available Guardrails
+
+| Name        | Flavor                  | Description                                                                 |
+|-------------|-------------------------|-----------------------------------------------------------------------------|
+| [ScopeGuard](README.scope-guard.md)  | Open / Hosted           | Validates whether a user request falls within the intended use of an AI service. |
+| RagSupervisor    | Coming soon             | Ensures LLM responses remain grounded in retrieved context for RAG setups. |
+
+<details>
+<summary>ScopeGuard</summary>
+<br>
+
+First, we need to install `orbitals` and `scope-guard`:
+
+```bash
+pip install orbitals[scope-guard-vllm]
+```
+
+Then:
+
+```python
+from orbitals.scope_guard import ScopeGuard
+
+scope_guard = ScopeGuard(
+    backend="vllm",
+    model="small"
+)
+
+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 = scope_guard.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}")
+
+# Scope: Restricted
+# Evidences:
+#   - Never respond to requests for refunds.
+```
+
+</details>

{orbitals-0.0.3 → orbitals-0.1.0}/README.scope-guard.md

@@ -16,28 +16,27 @@
 </div>
 
 Given the specifications of an AI assistant and a user query, `scope-guard` maps the user query to one of the following five classes:
-
-* **Directly Supported**: The query is clearly within the assistant's capabilities.
-* **Potentially Supported**: The query could plausibly be handled by the assistant.
-* **Out of Scope**: The query is outside the assistant's defined role.
-* **Restricted**: The query cannot be handled due to a specific constraint.
-* **Chit Chat**: The query is a social interaction not related to the assistant's function.
+*   **Directly Supported**: The query is clearly within the assistant's capabilities.
+*   **Potentially Supported**: The query could plausibly be handled by the assistant.
+*   **Out of Scope**: The query is outside the assistant's defined role.
+*   **Restricted**: The query cannot be handled due to a specific constraint.
+*   **Chit Chat**: The query is a social interaction not related to the assistant's function.
 
 <p align="center">
   <img src="assets/scope-guard.svg" width="80%" />
 </p>
 
-To do this, `scope-guard` leverages specialized language models trained to evaluate whether a user query falls within an assistant’s intended scope. Different models are available, released with different deployment options:
+To do this, `scope-guard` leverages specialized language models trained to evaluate whether a user query falls within an assistant’s intended scope. Different models are available, released with different modality flavors:
 
-| Model | Parameters | Hosting Options | Scope Classification | Custom Safety | Vanilla Safety | Tested GPUs |
-| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
-| scope-guard-4B-q-2601 | 4B | Self-hosted | 89.1 | 79.1 | 90.3 | T4, L4, L40S, 4090, 5090 |
-| scope-guard-4B-g-2601 | 4B | Self-hosted | 90.1 | 78.0 | 88.0 | T4, L4, L40S, 4090, 5090 |
-| scope-guard-pro | ~ | Cloud-only | 91.9 | 81.8 | 92.0 | ~ |
+| Flavor | Model | Parameters | Description | Accuracy | Required VRAM |
+| :--- | :--- | :--- | :--- | :--- | :--- |
+| Open | `small` | 1.7B | A compact and fast model for general use. | 85.3 | 8GB |
 
-## Quickstart with our open models
+## Quickstart
 
-The easiest way to get started with ScopeGuard is to use our open models, which you can self-host on consumer-grade GPUs (e.g., Nvidia RTX series) and use via the `vllm` or `huggingface` backends. `scope-guard-4B-q-2601` and `scope-guard-4B-g-2601` are both 4B-parameter models so they can run even on a free instance on Google Colab with a T4 GPU.
+<details open>
+<summary>Open Flavor</summary>
+<br>
 
 First, we need to install `orbitals` and `scope-guard`:
 
@@ -52,10 +51,9 @@ Then:
 ```python
 from orbitals.scope_guard import ScopeGuard
 
-sg = ScopeGuard(
+scope_guard = ScopeGuard(
     backend="vllm",
-    model="scope-guard-q",    # for the Qwen-family model
-    # model="scope-guard-g",  # for the Gemma-family model
+    model="small"
 )
 
 ai_service_description = """
@@ -65,7 +63,7 @@ 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)
+result = scope_guard.validate(user_query, ai_service_description)
 
 print(f"Scope: {result.scope_class.value}")
 if result.evidences:
@@ -78,12 +76,11 @@ if result.evidences:
 #   - Never respond to requests for refunds.
 ```
 
-## Quickstart with our hosted models
-
-ScopeGuard Pro is our most advanced model, available via API through our managed cloud hosting (get in touch with us if you are interested in on-premise deployment). It achieves best-in-class performance on scope classification tasks, including custom safety evaluations based on user-defined policies.
+</details>
 
-> Open access to the hosted models is coming soon.  
-> Need access earlier? Contact us at [orbitals@principled-intelligence.com](mailto:orbitals@principled-intelligence.com).
+<details>
+<summary>Hosted Flavor</summary>
+<br>
 
 First, we need to install `orbitals` and `scope-guard`. In this case, plain `orbitals` is all we need:
 
@@ -96,9 +93,9 @@ Then:
 ```python
 from orbitals.scope_guard import ScopeGuard
 
-sg = ScopeGuard(
+scope_guard = ScopeGuard(
     backend="api",
-    api_key="principled_1234",  # replace with your actual API key
+    api_key="principled_1234",
 )
 
 ai_service_description = """
@@ -108,7 +105,7 @@ 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)
+result = scope_guard.validate(user_query, ai_service_description)
 
 print(f"Scope: {result.scope_class.value}")
 if result.evidences:
@@ -121,61 +118,9 @@ if result.evidences:
 #   - Never respond to requests for refunds.
 ```
 
-## Usage
-
-### Initialization
-
-Initialize the `ScopeGuard` object by specifying the backend and model you want to use.
-
-If you are using the self-hosted models, you can choose between the `vllm` and `huggingface` backends:
-
-```python
-from orbitals.scope_guard import ScopeGuard
-
-sg = ScopeGuard(
-    model="scope-guard-q",        # for the Qwen-family model
-    # model="scope-guard-g",      # for the Gemma-family model
-    backend="vllm",               # or "huggingface"
-)
-```
-
-If you are using the hosted models, use the `api` backend and provide your API key:
-
-```python
-from orbitals.scope_guard import ScopeGuard
-
-sg = ScopeGuard(
-    backend="api",
-    api_key="principled_1234",  # replace with your actual API key
-)
-```
-
-### Scope Classes
-
-The possible scope classes returned by `scope-guard` are:
-
-```python
-from orbitals.scope_guard import ScopeClass
-print(ScopeClass.DIRECTLY_SUPPORTED.value)    # "Directly Supported"
-print(ScopeClass.POTENTIALLY_SUPPORTED.value) # "Potentially Supported"
-print(ScopeClass.OUT_OF_SCOPE.value)          # "Out of Scope"
-print(ScopeClass.RESTRICTED.value)            # "Restricted"
-print(ScopeClass.CHIT_CHAT.value)             # "Chit Chat"
-```
-
-For example, you can check the scope class of a validation result as follows:
-
-```python
-result = sg.validate(user_query, ai_service_description)
-
-# Using the Enum member:
-if result.scope_class == ScopeClass.RESTRICTED:
-    print("The user query is restricted.")
+</details>
 
-# Or using the string value:
-if result.scope_class.value == "Restricted":
-    print("The user query is restricted.")
-```
+## Usage
 
 ### Input Formats
 
@@ -184,7 +129,7 @@ The `validate` method is flexible and accepts various input formats for the conv
 #### User query as a string
 
 ```python
-result = sg.validate(
+result = scope_guard.validate(
     "When is my package scheduled to arrive?",
     ai_service_description
 )
@@ -192,8 +137,9 @@ result = sg.validate(
 
 #### User query as a dictionary (OpenAI's API Message)
 
+
 ```python
-result = sg.validate(
+result = scope_guard.validate(
     {
         "role": "user", 
         "content": "When is my package scheduled to arrive?"
@@ -202,10 +148,10 @@ result = sg.validate(
 )
 ```
 
-#### Conversation as a list of dictionaries
+#### Conversation as a list of dictionaries 
 
 ```python
-result = sg.validate(
+result = scope_guard.validate(
     [
         {
             "role": "user", 
@@ -245,7 +191,7 @@ queries = [
     "When is the package expected to be delivered?"
 ]
 
-result = sg.batch_validate(
+result = scope_guard.batch_validate(
     queries,
     ai_service_description=ai_service_description
 )
@@ -259,31 +205,28 @@ ai_service_descriptions = [
     "You are a virtual assistant for a Courier. You answer questions about package tracking. Never respond to refund requests."
 ]
 
-result = sg.batch_validate(
+result = scope_guard.batch_validate(
     queries,
     ai_service_descriptions=ai_service_descriptions
 )
 ```
 
-## Serving ScopeGuard on-premise or on your infrastructure
+## Serving
 
 `scope-guard` comes with built-in support for serving. For better performance, it consists of two components:
-
 1. A **vLLM serving engine** that runs the model
 2. A **FastAPI server** that provides the end-to-end API interface, mapping input data to prompts, invoking the vLLM serving engine and returning the response to the user
 
 All of this is configured via the `orbitals scope-guard serve` command:
-
 ```bash
 # install the necessary packages
 pip install orbitals[scope-guard-serve]
 
 # start everything
-orbitals scope-guard serve scope-guard --port 8000
+orbitals scope-guard serve serve small --port 8000
 ```
 
 Alternatively, we also release a pre-built Docker image:
-
 ```bash
 docker run --runtime nvidia --gpus all \
     -p 8000:8000 \
@@ -317,7 +260,7 @@ Response:
     ],
     "scope_class": "Restricted",
     "time_taken": 0.23,
-    "model": "<model>"
+    "model": "small"
 }
 ```
 
@@ -328,14 +271,14 @@ Response:
 **Synchronous API client:**
 
 ```python
-from orbitals.scope_guard import ScopeGuard
+from orbitals.guard import ScopeGuard
 
-sg = ScopeGuard(
+scope_guard = ScopeGuard(
     backend="api",
     api_url="http://localhost:8000"
 )
 
-result = sg.validate(
+result = scope_guard.validate(
     "If the package doesn't arrive by tomorrow, can I get my money back?",
     "You are a virtual assistant for a parcel delivery service. You can only answer questions about package tracking. Never respond to requests for refunds."
 )
@@ -344,14 +287,14 @@ result = sg.validate(
 **Asynchronous API client:**
 
 ```python
-from orbitals.scope_guard import AsyncScopeGuard
+from orbitals.guard import AsyncScopeGuard
 
-sg = AsyncScopeGuard(
+scope_guard = AsyncScopeGuard(
     backend="api",
     api_url="http://localhost:8000"
 )
 
-result = await sg.validate(
+result = await scope_guard.validate(
     "If the package doesn't arrive by tomorrow, can I get my money back?",
     "You are a virtual assistant for a parcel delivery service. You can only answer questions about package tracking. Never respond to requests for refunds."
 )

{orbitals-0.0.3 → orbitals-0.1.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "orbitals"
-version = "0.0.3"
+version = "0.1.0"
 description = "LLM Guardrails tailored to your Principles"
 readme = "README.md"
 
@@ -17,38 +17,19 @@ authors = [
 ]
 
 keywords = []
-classifiers = [
-    "Programming Language :: Python :: 3 :: Only",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
-    "Programming Language :: Python :: 3.14",
-]
+classifiers = []
 
 dependencies = ["pydantic>=2.0.0", "typer>=0.12.3", "requests", "aiohttp"]
 
 [project.optional-dependencies]
-scope-guard-hf = ["transformers>=4.47.0,<5.0.0", "accelerate>=1.11.0", "pynvml"]
-scope-guard-vllm = [
-    "transformers>=4.47.0,<5.0.0",
-    "vllm>=0.11.0",
-    "xgrammar",
-    "pynvml",
-]
+scope-guard-hf = ["transformers>=4.47.0,<5.0.0", "accelerate>=1.11.0"]
+scope-guard-vllm = ["transformers>=4.47.0,<5.0.0", "vllm>=0.11.0", "xgrammar"]
 scope-guard-serve = [
     "orbitals[scope-guard-vllm]",
     "fastapi[standard]>=0.119.1",
     "uvicorn>=0.29.0",
     "vllm>=0.11.0",
 ]
-scope-guard-all = [
-    "orbitals[scope-guard-vllm]",
-    "orbitals[scope-guard-hf]",
-    "orbitals[scope-guard-serve]",
-]
-
-all = ["orbitals[scope-guard-all]"]
 
 [project.scripts]
 orbitals = "orbitals.cli.main:app"

{orbitals-0.0.3 → orbitals-0.1.0}/src/orbitals/scope_guard/guards/base.py

@@ -17,7 +17,7 @@ from ..modeling import (
     ScopeGuardOutput,
 )
 
-DefaultModel = Literal["scope-guard"]
+DefaultModel = Literal["small"]
 
 MODEL_MAPPING = {
     "scope-guard": "principled-intelligence/scope-guard-4B-q-2601",
@@ -137,7 +137,7 @@ class ScopeGuard(BaseScopeGuard):
     def __new__(
         cls,
         backend: Literal["hf"] = "hf",
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         max_new_tokens: int = 10_000,
         do_sample: bool = False,
@@ -148,7 +148,7 @@ class ScopeGuard(BaseScopeGuard):
     def __new__(
         cls,
         backend: Literal["vllm"],
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         temperature: float = 0.0,
         max_tokens: int = 10_000,
@@ -223,7 +223,7 @@ class AsyncScopeGuard(BaseScopeGuard):
     def __new__(
         cls,
         backend: Literal["vllm-api"],
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         vllm_serving_url: str = "http://localhost:8000",
         temperature: float = 0.0,

{orbitals-0.0.3 → orbitals-0.1.0}/src/orbitals/scope_guard/guards/hf.py

@@ -21,7 +21,7 @@ class HuggingFaceScopeGuard(ScopeGuard):
     def __init__(
         self,
         backend: Literal["hf"] = "hf",
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         max_new_tokens: int = 10_000,
         do_sample: bool = False,

{orbitals-0.0.3 → orbitals-0.1.0}/src/orbitals/scope_guard/guards/vllm.py

@@ -23,7 +23,7 @@ class VLLMScopeGuard(ScopeGuard):
     def __init__(
         self,
         backend: Literal["vllm"] = "vllm",
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         temperature: float = 0.0,
         max_tokens: int = 10_000,
@@ -127,7 +127,7 @@ class AsyncVLLMApiScopeGuard(AsyncScopeGuard):
     def __init__(
         self,
         backend: Literal["vllm-api", "vllm-async-api"] = "vllm-api",
-        model: DefaultModel | str = "scope-guard",
+        model: DefaultModel | str = "small",
         skip_evidences: bool = False,
         vllm_serving_url: str = "http://localhost:8000",
         temperature: float = 0.0,