NewAI Enhanced
v0.29.0
Breaking Changes
- Output connectors: String header values to Kafka/NATS no longer wrapped in quotes;
Noneserializes differently (no value in Kafka,"None"string in NATS)
Features
- Pathway Web Dashboard for real-time pipeline monitoring with interactive graphs and latency/memory metrics
pw.io.kafka.readnow exposes message headers in metadata as base64-encoded pairs inheadersarraypw.xpacks.llm.llms.BedrockChat- AWS Bedrock integration for Claude, Llama, Titan, Mistral via Converse APIpw.xpacks.llm.embedders.BedrockEmbedder- AWS Bedrock embeddings (Titan, Cohere)
Improvements
- Lazy imports for Python dependencies — only loaded when capabilities are actually used
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.readnow includes message headers in the parsed metadata. The headers are available at the top level of the metadata in theheadersarray. 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
Nonevalue is handled differently: in Kafka, it is serialized as a header without a value, while in NATS it becomes the string"None".