docs: update the readme (#25)

This commit is contained in:
tomsun28 2025-07-27 14:38:00 +08:00 committed by GitHub
parent e2d042a41f
commit bcf3078474
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 0 additions and 137 deletions

View file

@ -6,8 +6,6 @@
[中文文档](README_CN.md) | English
**Not yet released.**
The official Java SDK for Z.ai platforms, providing a unified interface to access powerful AI capabilities including chat completion, embeddings, image generation, audio processing, and more.
## ✨ Features
@ -326,75 +324,10 @@ The ZaiClient provides access to comprehensive AI services:
| **Files** | File management and processing | Upload, download, batch processing |
| **Assistants** | AI assistant management | Create, configure, and manage assistants |
| **Agents** | Agent-based completions | Specialized agent interactions |
| **Knowledge** | Knowledge base operations | Document indexing and retrieval |
| **Batch** | Batch processing | Bulk operations |
| **Web Search** | Web search integration | Real-time web information |
| **Videos** | Video processing | Video analysis and generation |
## 🎯 Supported Models
### Text Generation
- `glm-4-plus` - Enhanced GLM-4 with improved capabilities
- `glm-4` - Standard GLM-4 model
- `glm-4-air` - Lightweight version for speed
- `glm-4-flash` - Ultra-fast response model
- `glm-4-0520` - GLM-4 model version 0520
- `glm-4-airx` - Extended Air model with additional features
- `glm-4-long` - Optimized for long-context conversations
- `glm-4-voice` - Specialized for voice interactions
- `glm-4.1v-thinking-flash` - Visual reasoning model with thinking capabilities
- `glm-z1-air` - Optimized for mathematical and logical reasoning
- `glm-z1-airx` - Fastest domestic inference model with 200 tokens/s
- `glm-z1-flash` - Completely free reasoning model service
- `glm-4-air-250414` - Enhanced with reinforcement learning optimization
- `glm-4-flash-250414` - Latest free language model
- `glm-4-flashx` - Enhanced Flash version with ultra-fast inference speed
- `glm-4-9b` - Open-source model with 9 billion parameters
- `glm-4-assistant` - AI assistant for various business scenarios
- `glm-4-alltools` - Agent model for complex task planning and execution
- `chatglm3-6b` - Open-source base model with 6 billion parameters
- `codegeex-4` - Code generation and completion model
### Audio Speech Recognition
- `glm-asr` - Context-aware audio transcription model
### Real-time Interaction
- `glm-realtime-air` - Real-time video call model with cross-modal reasoning
- `glm-realtime-flash` - Fast real-time video call model
### Vision Models
- `glm-4v-plus` - Enhanced vision model
- `glm-4v` - Standard vision model
- `glm-4v-plus-0111` - Variable resolution video and image understanding
- `glm-4v-flash` - Free and powerful image understanding model
### Image Generation
- `cogview-3-plus` - Enhanced image generation
- `cogview-3` - Standard image generation
- `cogview-3-flash` - Free image generation model
- `cogview-4-250304` - Advanced image generation with text capabilities
- `cogview-4` - Advanced image generation for precise and personalized AI image expression
### Video Generation
- `cogvideox` - Video generation from text or images
- `cogvideox-flash` - Free video generation model
- `cogvideox-2` - New video generation model
- `viduq1-text` - High-performance video generation from text input
- `viduq1-image` - Video generation from first frame image and text description
- `viduq1-start-end` - Video generation from first and last frame images
- `vidu2-image` - Enhanced video generation from first frame image and text description
- `vidu2-start-end` - Enhanced video generation from first and last frame images
- `vidu2-reference` - Video generation with reference images of people, objects, etc.
### Embeddings
- `embedding-3` - Latest embedding model
- `embedding-2` - Previous generation embedding
### Specialized
- `charglm-3` - Character interaction model
- `cogtts` - Text-to-speech model
- `rerank` - Text reordering and relevance scoring
## 📈 Release Notes
For detailed release notes and version history, please see [Release-Note.md](Release-Note.md).

View file

@ -348,81 +348,11 @@ public class AIController {
- 工作流管理
- 任务执行
### Knowledge 服务
- 知识库管理
- 文档处理
- 知识检索
### Batch 服务
- 批量处理
- 异步任务
- 结果管理
## 🤖 支持的模型
### 文本生成模型
- `glm-4-plus` - 增强版GLM-4具有更强的能力
- `glm-4` - 标准GLM-4模型
- `glm-4-air` - 轻量级版本,优化速度
- `glm-4-flash` - 超快响应模型
- `glm-4-0520` - GLM-4模型版本0520
- `glm-4-airx` - 扩展Air模型具有附加功能
- `glm-4-long` - 优化长上下文对话
- `glm-4-voice` - 专为语音交互设计
- `glm-4.1v-thinking-flash` - 具有思维能力的视觉推理模型
- `glm-z1-air` - 优化数学和逻辑推理
- `glm-z1-airx` - 国内最快推理模型200 tokens/s
- `glm-z1-flash` - 完全免费的推理模型服务
- `glm-4-air-250414` - 通过强化学习优化增强
- `glm-4-flash-250414` - 最新免费语言模型
- `glm-4-flashx` - 增强Flash版本具有超快推理速度
- `glm-4-9b` - 90亿参数开源模型
- `glm-4-assistant` - 面向各种业务场景的AI助手
- `glm-4-alltools` - 复杂任务规划和执行的代理模型
- `chatglm3-6b` - 60亿参数开源基础模型
- `codegeex-4` - 代码生成和补全模型
### 音频语音识别
- `glm-asr` - 上下文感知音频转录模型
### 实时交互
- `glm-realtime-air` - 具有跨模态推理的实时视频通话模型
- `glm-realtime-flash` - 快速实时视频通话模型
### 视觉模型
- `glm-4v-plus` - 增强视觉模型
- `glm-4v` - 标准视觉模型
- `glm-4v-plus-0111` - 可变分辨率视频和图像理解
- `glm-4v-flash` - 免费且强大的图像理解模型
### 图像生成模型
- `cogview-3-plus` - 增强图像生成
- `cogview-3` - 标准图像生成
- `cogview-3-flash` - 免费图像生成模型
- `cogview-4-250304` - 具有文本功能的高级图像生成
- `cogview-4` - 精确个性化AI图像表达的高级图像生成
### 视频生成模型
- `cogvideox` - 从文本或图像生成视频
- `cogvideox-flash` - 免费视频生成模型
- `cogvideox-2` - 新视频生成模型
- `viduq1-text` - 从文本输入的高性能视频生成
- `viduq1-image` - 从首帧图像和文本描述生成视频
- `viduq1-start-end` - 从首末帧图像生成视频
- `vidu2-image` - 从首帧图像和文本描述的增强视频生成
- `vidu2-start-end` - 从首末帧图像的增强视频生成
- `vidu2-reference` - 使用人物、物体等参考图像的视频生成
### 嵌入模型
- `embedding-3` - 最新嵌入模型
- `embedding-2` - 上一代嵌入模型
### 专业模型
- `charglm-3` - 角色交互模型
- `cogtts` - 文本转语音模型
- `rerank` - 文本重排序和相关性评分
- `emohaa` - 情感分析模型
## 📈 版本更新
详细的版本更新记录和历史信息,请查看 [Release-Note.md](Release-Note.md)。