v0.4.6

What's Changed

• Add multi‑provider embedding support and converters

Full Changelog: v0.4.5...v0.4.6

v0.4.5

What's Changed

• Fix docstring formatting in OpenAIType
• Update defaults, add deps, simplify endpoint logic
• Add local Ollama config for gpt-oss-120b model
• refactor/providers
• Refactor streaming logic and clean up HttpRequestExecutor
• Add native LMStudio streaming support and refactor streaming
• Add native LMStudio streaming support and refactor handlers

Full Changelog: v0.4.4...v0.4.5

v0.4.4

What's Changed

• Validate unique provider identifiers.
• Store all hosts with keep‑alive configured in a Redis.
• UtilsPlugin pipeline with LangChain based simple RAG plugin (extending context to GenAI with locally built databse).
• Improve dev tooling and enforce request timeouts.
• Refactor API to use unified /v1/responses endpoint.

Full Changelog: https://github.com/radlab-dev-group/llm-router/commits/v0.4.4

v0.4.3

What's Changed

• Helm chart in #20
• Add sample auditor log file to logs/auditor/ directory in #21
• Add Prometheus metrics handler with multiprocess support in #22
• Add configurable monitoring intervals to services monitor in #25
• Skip FastMaskerPlugin in LLMRouterServicesMonitor host probing and clean up unused guard‑rail variables in #26
• Add V0 chat handler and integer timestamps to models endpoint in #28
• Add model config docs and tool calling support in #31
• Refactor monitor log prefixes to explicit [*-monitor] tags and comment out Engine del cleanup in #32
• Add fake model provider and fix guardrail streaming in #33

Full Changelog: v0.4.2...v0.4.3

v0.4.2

Full Changelog: v0.4.1...v0.4.2

v0.4.1

Full Changelog: v0.4.0...v0.4.1

v0.4.0

Full Changelog: v0.3.1...v0.4.0

v0.3.1

Full Changelog: v0.3.0...v0.3.1

v0.3.0

Full Changelog: v0.2.3...v0.3.0

v0.2.3

Full Changelog: v0.2.2...v0.2.3