Starstruk Logo MarkStarstruk

v0.29.0

pathwaycom/pathwayv0.29.0Jan 22, 2026by github-actions[bot]

AI Summary

This major release introduces the Pathway Web Dashboard for real-time pipeline monitoring, adds native AWS Bedrock integrations for chat and embeddings, implements lazy loading of Python dependencies, and includes a breaking change regarding Kafka/NATS string header handling.

Key Highlights

  • New Pathway Web Dashboard for real-time monitoring with interactive graphs and metrics
  • Kafka read now includes message headers in parsed metadata
  • Native AWS Bedrock chat integration (BedrockChat) supporting Claude, Llama, Titan, Mistral
  • Native AWS Bedrock embedder integration supporting Titan and Cohere models
  • Most Python dependencies now imported lazily only when needed

Breaking Changes

  • Output connectors no longer wrap string header values in double quotes when sending to Kafka or NATS - values are forwarded as-is

New Features

  • Pathway Web Dashboard with interactive graph plotting and latency/memory metrics
  • Message headers in pw.io.kafka.read metadata (headers array with name/value pairs)
  • pw.xpacks.llm.llms.BedrockChat with Converse API support
  • pw.xpacks.llm.embedders.BedrockEmbedder with Titan and Cohere support

Full Release Notes

### Added
- Pathway Web Dashboard providing user-friendly interface for monitoring Pathway pipelines in real time with interactive graph plotting and latency/memory metrics.
- `pw.io.kafka.read` now includes message headers in the parsed metadata. The headers are available at the top level of the metadata in the `headers` array. Each element of the array is a pair consisting of a string header name and a base64-encoded header value. If the header is null, the corresponding value is also null.
- `pw.xpacks.llm.llms.BedrockChat` - Native AWS Bedrock chat integration using the Converse API. Supports Claude, Llama, Titan, Mistral, and other Bedrock models.
- `pw.xpacks.llm.embedders.BedrockEmbedder` - Native AWS Bedrock embedding integration supporting Amazon Titan and Cohere embedding models.

### Changed
- Most Python dependencies are now imported only if the related capabilities are used by a program.
- **BREAKING**: Output connectors no longer wrap string header values in double quotes when sending them to Kafka or NATS. The string values are forwarded as-is. The `None` value is handled differently: in Kafka, it is serialized as a header without a value, while in NATS it becomes the string `"None"`.