Self-hosted reaches feature parity with Seekr-managed
This release brings self-hosted SeekrFlow to feature parity with Seekr-managed deployments, adding explainability, agent, fine-tuning, and ingestion capabilities to self-hosted environments.Explainability- Context attribution traces model responses to the retrieved context that informed them.
- Data attribution links inference outputs to contributing training data.
Logfire-based tracing is not available in self-hosted deployments.
- Tool Library v2 with expanded tool management.
- Multi-agent orchestration is now generally available for coordinating agents across tools and tasks.
- Vision-language fine-tuning for supported vision models.
- Reinforcement-tuning reward functions for controlling which behaviors are reinforced during training.
- Ingestion insights surface job status and failure diagnostics for ingestion pipelines.
- vLLM upgrade (0.19.0) on ROCm for improved inference on AMD GPUs.
- Chainguard-based container images for a hardened, minimal-CVE deployment footprint.
Initial self-hosted release of SeekrFlow
First self-hosted release of SeekrFlow, bringing the platform to customer-managed environments with fine-tuning, inference, agent, and ingestion capabilities.Agents- Docstring validation for improved agent runtime performance.
- Reinforcement tuning (GRPO).
- Faster ingestion with pipeline performance improvements.
- Quality improvements to principle alignment.
- vLLM upgrade (0.11.1).
- Expanded selection of supported models.
- Authentication support for custom solutions.