@ax-llm/ax 21.0.14 → 22.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -49,7 +49,7 @@ prompts automatically.
49
49
 
50
50
  Ax stays in the same latency class as direct provider calls while adding typed
51
51
  outputs, validation, retries, tracing, and tools. Streaming is the default so Ax
52
- can parse fields as they arrive, fail early on streaming assertions, cancel bad
52
+ can parse fields as they arrive, fail early on streaming guards, cancel bad
53
53
  outputs, and start correction without wasting tokens on completions that are
54
54
  already invalid.
55
55
 
@@ -153,15 +153,14 @@ console.log(result.translation); // "Hola mundo"
153
153
 
154
154
  ## Powerful Features, Zero Complexity
155
155
 
156
- - ✅ **15+ LLM Providers** - OpenAI, Anthropic, Google, Mistral, Ollama, and
157
- more
156
+ - ✅ **Model-Lab Providers** - OpenAI, Anthropic, Google, Mistral, DeepSeek,
157
+ Grok/xAI, and more
158
158
  - ✅ **Type-Safe Everything** - Full TypeScript support with auto-completion
159
159
  - ✅ **Streaming First** - Real-time responses with validation
160
160
  - ✅ **Multi-Modal** - Images, audio, text in the same signature
161
161
  - ✅ **Smart Optimization** - Automatic prompt tuning with GEPA and bootstrap demos
162
162
  - ✅ **Production Observability** - OpenTelemetry tracing built-in
163
163
  - ✅ **Advanced Workflows** - Compose complex pipelines with AxFlow
164
- - ✅ **Enterprise RAG** - Multi-hop retrieval with quality loops
165
164
  - ✅ **Agent Framework** - Agents that can use tools and call other agents
166
165
  - ✅ **Zero Dependencies** - Lightweight, fast, reliable
167
166