bge-base-en-v1.5

Converts variable-length text passages (queries, documents, sentences) into fixed-dimensional dense vector embeddings (768-dim) using a BERT-based transformer architecture with mean pooling over token representations. Implements the BGE (BAAI General Embedding) approach which fine-tunes on large-scale relevance datasets to optimize for semantic similarity tasks, enabling efficient nearest-neighbor search in vector space.

Processes multiple text inputs simultaneously through the transformer encoder, applies mean-pooling aggregation over the sequence dimension to collapse token-level representations into a single passage embedding, and returns batched outputs with optional L2 normalization. Supports variable-length inputs within the same batch through padding and attention masking, enabling efficient GPU utilization for throughput-optimized embedding generation.

Outputs L2-normalized embeddings (unit vectors with norm=1.0) that enable fast cosine similarity computation via simple dot product, eliminating the need for explicit normalization during retrieval. The model applies layer normalization in its final layers to ensure stable, normalized outputs suitable for approximate nearest neighbor (ANN) indexes like FAISS, Annoy, or HNSW that assume normalized vectors.

While this v1.5 model is English-only, it achieves strong cross-lingual retrieval performance when paired with translation pipelines or multilingual retrieval frameworks because its dense embedding space is trained on English relevance signals that generalize across languages. The model can embed English queries against documents translated to English, or be used as the backbone for multilingual systems that translate non-English inputs before embedding.

Model is available in ONNX (Open Neural Network Exchange) format, enabling inference on CPU and non-PyTorch runtimes (ONNX Runtime, TensorRT, CoreML) without requiring PyTorch installation. ONNX export preserves the full model architecture including layer normalization and mean pooling, enabling deployment in resource-constrained environments, edge devices, or production systems where PyTorch dependency is undesirable.

Model is evaluated on the MTEB (Massive Text Embedding Benchmark) suite covering 56 tasks across retrieval, clustering, reranking, and semantic similarity. Performance metrics are publicly reported and reproducible, providing transparency into model capabilities across diverse downstream tasks. The model ranks in the top tier for retrieval tasks, validating its effectiveness for RAG and semantic search applications without requiring custom evaluation.

Model weights are available in SafeTensors format, a secure serialization format that prevents arbitrary code execution during model loading (unlike pickle-based PyTorch .pt files). SafeTensors enables safe loading of untrusted model files and provides faster deserialization through memory-mapped file access, reducing model loading time and memory overhead during initialization.

Model is fully compatible with the Sentence-Transformers library, which provides high-level APIs for encoding, similarity computation, semantic search, and clustering without requiring manual tokenization or PyTorch boilerplate. Sentence-Transformers handles batching, device management (CPU/GPU), and provides utility functions for common embedding tasks, abstracting away low-level implementation details.

Model is compatible with Azure Machine Learning endpoints and Azure OpenAI services, enabling deployment through Azure's managed inference infrastructure. Azure compatibility includes support for auto-scaling, monitoring, and integration with Azure's MLOps pipelines, providing enterprise-grade deployment without managing infrastructure.

Model is compatible with Text Embeddings Inference (TEI), a high-performance inference server optimized for embedding models. TEI provides REST and gRPC APIs, automatic batching, GPU optimization, and horizontal scaling capabilities, enabling production-grade embedding serving without custom infrastructure.