feat: BreakPilot PWA - Full codebase (clean push without large binaries)

All services: admin-v2, studio-v2, website, ai-compliance-sdk,
consent-service, klausur-service, voice-service, and infrastructure.
Large PDFs and compiled binaries excluded via .gitignore.

klausur-service/embedding-service/config.py

@@ -0,0 +1,86 @@
+"""
+Embedding Service Configuration
+
+Environment variables for embedding generation, re-ranking, and PDF extraction.
+"""
+
+import os
+
+# =============================================================================
+# Embedding Configuration
+# =============================================================================
+
+# Backend: "local" (sentence-transformers) or "openai"
+EMBEDDING_BACKEND = os.getenv("EMBEDDING_BACKEND", "local")
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "")
+OPENAI_EMBEDDING_MODEL = os.getenv("OPENAI_EMBEDDING_MODEL", "text-embedding-3-small")
+
+# Local embedding model
+# Recommended: BAAI/bge-m3 (MIT, 1024 dim, multilingual)
+LOCAL_EMBEDDING_MODEL = os.getenv("LOCAL_EMBEDDING_MODEL", "BAAI/bge-m3")
+
+# Chunking configuration
+CHUNK_SIZE = int(os.getenv("CHUNK_SIZE", "1000"))
+CHUNK_OVERLAP = int(os.getenv("CHUNK_OVERLAP", "200"))
+CHUNKING_STRATEGY = os.getenv("CHUNKING_STRATEGY", "semantic")
+
+# =============================================================================
+# Re-Ranker Configuration
+# =============================================================================
+
+# Backend: "local" (sentence-transformers CrossEncoder) or "cohere"
+RERANKER_BACKEND = os.getenv("RERANKER_BACKEND", "local")
+COHERE_API_KEY = os.getenv("COHERE_API_KEY", "")
+
+# Local re-ranker model
+# Recommended: BAAI/bge-reranker-v2-m3 (Apache 2.0, multilingual)
+LOCAL_RERANKER_MODEL = os.getenv("LOCAL_RERANKER_MODEL", "BAAI/bge-reranker-v2-m3")
+
+# =============================================================================
+# PDF Extraction Configuration
+# =============================================================================
+
+# Backend: "auto", "unstructured", "pypdf"
+PDF_EXTRACTION_BACKEND = os.getenv("PDF_EXTRACTION_BACKEND", "auto")
+UNSTRUCTURED_API_KEY = os.getenv("UNSTRUCTURED_API_KEY", "")
+UNSTRUCTURED_API_URL = os.getenv("UNSTRUCTURED_API_URL", "")
+
+# =============================================================================
+# Service Configuration
+# =============================================================================
+
+SERVICE_PORT = int(os.getenv("EMBEDDING_SERVICE_PORT", "8087"))
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO")
+
+# Model dimensions lookup
+MODEL_DIMENSIONS = {
+    # Multilingual / German-optimized
+    "BAAI/bge-m3": 1024,
+    "deepset/mxbai-embed-de-large-v1": 1024,
+    "jinaai/jina-embeddings-v2-base-de": 768,
+    "intfloat/multilingual-e5-large": 1024,
+    # English-focused (smaller, faster)
+    "all-MiniLM-L6-v2": 384,
+    "all-mpnet-base-v2": 768,
+    # OpenAI
+    "text-embedding-3-small": 1536,
+    "text-embedding-3-large": 3072,
+}
+
+
+def get_model_dimensions(model_name: str) -> int:
+    """Get embedding dimensions for a model."""
+    if model_name in MODEL_DIMENSIONS:
+        return MODEL_DIMENSIONS[model_name]
+    for key, dim in MODEL_DIMENSIONS.items():
+        if key in model_name or model_name in key:
+            return dim
+    return 384  # Default fallback
+
+
+def get_current_dimensions() -> int:
+    """Get dimensions for the currently configured model."""
+    if EMBEDDING_BACKEND == "local":
+        return get_model_dimensions(LOCAL_EMBEDDING_MODEL)
+    else:
+        return get_model_dimensions(OPENAI_EMBEDDING_MODEL)