Add speakleash guardrails: Flask API (sojka_guard_app.py), SojkaModelConfig, and run_sojka_guardrail.sh launch script.

Author: Paweł Kędzia

llm_router_services/guardrails/speakleash/__init__.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from llm_router_services.guardrails.inference.config import GuardrailModelConfig
+
+
+@dataclass(frozen=True)
+class SojkaModelConfig(GuardrailModelConfig):
+    pipeline_batch_size: int = 64
+    min_score_for_safe: float = 0.5
+    min_score_for_not_safe: float = 0.5

llm_router_services/guardrails/speakleash/config.py

@@ -0,0 +1,65 @@
+import os
+from typing import Any, Dict
+
+from flask import Flask, request, jsonify
+
+from llm_router_services.guardrails.constants import SERVICES_API_PREFIX
+from llm_router_services.guardrails.inference.factory import (
+    GuardrailClassifierModelFactory,
+)
+from llm_router_services.guardrails.speakleash.config import SojkaModelConfig
+
+# -----------------------------------------------------------------------
+# Environment prefix – all configuration keys start with this value
+# -----------------------------------------------------------------------
+_ENV_PREFIX = "LLM_ROUTER_SOJKA_GUARD_"
+
+app = Flask(__name__)
+
+MODEL_PATH = os.getenv(f"{_ENV_PREFIX}MODEL_PATH", None)
+if not MODEL_PATH:
+    raise Exception(
+        f"Sojka guardrail model path is not set! "
+        f"Export {_ENV_PREFIX}MODEL_PATH with proper model path"
+    )
+
+# Keep only a single constant for the device (CPU by default)
+DEFAULT_DEVICE = int(os.getenv(f"{_ENV_PREFIX}DEVICE", "-1"))
+
+# -----------------------------------------------------------------------
+# Build the guardrail object via the factory, passing the Sojka‑specific config
+# -----------------------------------------------------------------------
+guardrail = GuardrailClassifierModelFactory(
+    model_type="text_classification",
+    model_path=MODEL_PATH,
+    device=DEFAULT_DEVICE,
+    config=SojkaModelConfig(),
+)
+
+
+# -----------------------------------------------------------------------
+# Endpoint: POST /api/guardrails/sojka_guard
+# -----------------------------------------------------------------------
+@app.route(f"{SERVICES_API_PREFIX}/sojka_guard", methods=["POST"])
+def sojka_guardrail():
+    """
+    Accepts a JSON payload, classifies the content and returns the aggregated results.
+    """
+    if not request.is_json:
+        return jsonify({"error": "Request body must be JSON"}), 400
+
+    payload: Dict[str, Any] = request.get_json()
+    try:
+        results = guardrail.classify_chunks(payload)
+        return jsonify({"results": results}), 200
+    except Exception as exc:  # pragma: no cover – safety net
+        return jsonify({"error": str(exc)}), 500
+
+
+# -----------------------------------------------------------------------
+# Run the Flask server (only when executed directly)
+# -----------------------------------------------------------------------
+if __name__ == "__main__":
+    host = os.getenv(f"{_ENV_PREFIX}FLASK_HOST", "0.0.0.0")
+    port = int(os.getenv(f"{_ENV_PREFIX}FLASK_PORT", "5000"))
+    app.run(host=host, port=port, debug=False)

llm_router_services/guardrails/speakleash/sojka_guard_app.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# ------------------------------------------------------------------
+# Launch the NASK‑PIB Guardrail API using Gunicorn (2 workers)
+# ------------------------------------------------------------------
+# Required environment variables (can be overridden when invoking the script):
+#   LLM_ROUTER_SOJKA_GUARD_FLASK_HOST – bind address (default: 0.0.0.0)
+#   LLM_ROUTER_SOJKA_GUARD_FLASK_PORT – port (default: 5000)
+#   LLM_ROUTER_SOJKA_GUARD_MODEL_PATH – model path / hub identifier
+#   LLM_ROUTER_SOJKA_GUARD_DEVICE – device for the transformer pipeline
+#                                           (-1 → CPU, 0/1 → GPU) (default: -1)
+# ---------------------------------------------------------------
+
+# Set defaults if they are not already defined in the environment
+: "${LLM_ROUTER_SOJKA_GUARD_FLASK_HOST:=0.0.0.0}"
+: "${LLM_ROUTER_SOJKA_GUARD_FLASK_PORT:=5001}"
+: "${LLM_ROUTER_SOJKA_GUARD_MODEL_PATH:=speakleash/Bielik-Guard-0.1B-v1.0}"
+: "${LLM_ROUTER_SOJKA_GUARD_DEVICE:=0}"
+
+# Export them so the Python process can read them
+export LLM_ROUTER_SOJKA_GUARD_FLASK_HOST
+export LLM_ROUTER_SOJKA_GUARD_FLASK_PORT
+export LLM_ROUTER_SOJKA_GUARD_MODEL_PATH
+export LLM_ROUTER_SOJKA_GUARD_DEVICE
+
+# Show the configuration that will be used
+echo "Starting Sojka Guardrail API with Gunicorn (2 workers):"
+echo "  HOST   = $LLM_ROUTER_SOJKA_GUARD_FLASK_HOST"
+echo "  PORT   = $LLM_ROUTER_SOJKA_GUARD_FLASK_PORT"
+echo "  MODEL  = $LLM_ROUTER_SOJKA_GUARD_MODEL_PATH"
+echo "  DEVICE = $LLM_ROUTER_SOJKA_GUARD_DEVICE"
+echo
+
+# ---------------------------------------------------------------
+# Run Gunicorn
+#   -w 2               → 2 worker processes
+#   -b host:port       → bind address
+#   guardrails.speakleash.sojka_guard_app  → import the Flask app object
+# ---------------------------------------------------------------
+gunicorn -w 1 -b \
+  "${LLM_ROUTER_SOJKA_GUARD_FLASK_HOST}:${LLM_ROUTER_SOJKA_GUARD_FLASK_PORT}" \
+  llm_router_services.guardrails.speakleash.sojka_guard_app:app