saravanakumardb1
|
151e07207b
|
feat(llm): add vision, streaming, and embedding support
- ContentPart types (TextContentPart, ImageUrlContentPart) for multipart messages
- ChatMessage.content now accepts string | ContentPart[] for vision
- EmbeddingRequest/Response types + optional embed() on LLMProvider
- chatCompletionStream() implemented in OpenAI + Azure providers (SSE parsing)
- embed() implemented in OpenAI + Azure providers
- Vision helpers: isVisionMessage, hasVisionContent, buildVisionMessage, getMessageText
- MockLLMProvider: streaming, embedding, vision content support
- 27 tests passing (up from 7)
|
2026-04-06 07:42:30 -07:00 |
|
|
|
43bf51a290
|
feat(llm): add Perplexity, Gemini providers and createFallbackChain
- Add PerplexityProvider (OpenAI-compatible, reads PERPLEXITY_API_KEY)
- Add GeminiProvider (Google Generative Language API adapter, reads GEMINI_API_KEY)
- Add createFallbackChain() — ordered provider chain, skips unconfigured,
aggregates errors; allows any app to replace custom LLM fallback loops
- Extend LLMProviderType with 'perplexity' | 'gemini'
- Update factory to resolve and instantiate new provider types
- Add PAID_PROVIDERS to llm-router registry (OpenAI, Perplexity) for apps
using round-robin routing alongside free-tier providers
- 27 tests covering fallback chain, new providers, error/edge cases
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-04-05 12:50:08 -07:00 |
|
