Chat Models 对比
此表格对比了 Spring AI 支持的各种 Chat Models，详细说明了它们的功能：
- Multimodality: 模型可以处理的输入类型（例如，text、image、audio、video）。
- Tools/Function Calling: 模型是否支持 function calling 或 tool use。
- Streaming: 模型是否提供 streaming 响应。
- Retry: 是否支持 retry 机制。
- Observability: 用于监控和调试的功能。
- Built-in JSON: 原生支持 JSON 输出。
- Local deployment: 模型是否可以在本地运行。
- OpenAI API Compatibility: 模型是否与 OpenAI 的 API 兼容。
| Provider | Multimodality | Tools/Functions | Streaming | Retry | Observability | Built-in JSON | Local | OpenAI API Compatible |
|---|---|---|---|---|---|---|---|---|
| DashScope | text, pdf, image | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ |
| Qwen | text, pdf, image | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | x |
| Anthropic Claude | text, pdf, image | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ |
| Azure OpenAI | text, image | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ |
| DeepSeek (OpenAI-proxy) | text | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Google GenAI | text, pdf, image, audio, video | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ |
| Google VertexAI Gemini | text, pdf, image, audio, video | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ |
| Groq (OpenAI-proxy) | text, image | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ |
| HuggingFace | text | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Mistral AI | text, image, audio | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ |
| MiniMax | text | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ |
| Moonshot AI | text | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | |
| NVIDIA (OpenAI-proxy) | text, image | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ |
| OCI GenAI/Cohere | text | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ |
| Ollama | text, image | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| OpenAI SDK (Official) | In: text, image, audio Out: text, audio | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ |
| OpenAI | In: text, image, audio Out: text, audio | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ |
| Perplexity (OpenAI-proxy) | text | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ |
| QianFan | text | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ |
| ZhiPu AI | text, image, docs | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ |
| Amazon Bedrock Converse | text, image, video, docs (pdf, html, md, docx ...) | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ |