Skip to main content

API Documentation

Gateway Layer

Bella-openapi

Released

Beyond chat completion, Bella-openapi integrates multiple AI capabilities including text vectorization, speech recognition, speech synthesis, text-to-image, and image-to-image generation, equipped with comprehensive billing, rate limiting, and resource management features. All capabilities have been thoroughly tested in large-scale production environments, ensuring stability and reliability.

View API Documentation

Capability Layer

Bella-knowledge

Upcoming

Focused on unified storage and management of knowledge, elegantly handling multiple knowledge sources such as files and Q&A pairs, providing powerful knowledge support for intelligent applications.

View API Documentation

Bella-assistants

Upcoming

An open-source implementation compatible with OpenAI Assistants API and Responses API, breaking through native ecosystem limitations, supporting flexible switching between various vendor models, truly achieving develop once, use everywhere.

View API Documentation

Bella-rag

Upcoming

Leveraging Bella-knowledge data sources, it provides unified retrieval question-answering generation capabilities, supports various retrieval methods and RAG implementation paradigms, making AI responses more accurate and reliable.

View API Documentation

Bella-workflow

Upcoming

Similar to DIFY but with many differentiated capabilities, such as callback mode, Groovy script support, batch processing capabilities, third-party data source registration, while delivering superior performance.

View API Documentation

Bella-job-queue

Upcoming

A centralized queue system that enables various basic capabilities to easily support batch processing mode, significantly improving processing efficiency and resource utilization.

View API Documentation

Bella-realtime

Upcoming

Known for ultra-low latency and high flexibility, it supports free combination of different ASR, LLM, and TTS components to create the best user experience, while supporting cutting-edge features like multi-agent collaboration.

View API Documentation

Inference Service Layer

Bella-general-infer

Upcoming

Supports multiple models including LLM, ASR, TTS, Embedding, Rerank, compatible with mainstream inference backends such as Transformers, vLLM, SGLang, Faster-Whisper, providing one-stop solution for various AI inference needs.

View API Documentation

Model Layer

Bella-whisper

Upcoming

A Whisper model carefully fine-tuned with domain data, possessing excellent Simplified Chinese recognition capabilities, providing more accurate support for voice applications.

View API Documentation