Qwentext

• 

  example session with Qwentext, showing the background updates thanks to Tair custom data types

• 

  Comparison to naive RAG implementation

• 

  Evolution of context size and baseline tests

• 

Qwentext

Qwentext is not a bigger prompt and not a vector scrapbook. It is compact durable memory state where newer evidence can supersede stale facts while preserving the audit trail that explains why the current branch is trusted.

The core idea is event-sourced durable memory. User interactions are treated as dataclass-backed events, and background workers consolidate those events into a structured, persistent memory tree. The agent uses only the relevant branches of that memory state at answer time, while the background worker resolves contradictions, asks the configured model to connect related branches, ranks evidence by confidence and importance, and lowers uncertainty in high-entropy memory branches.

Features

• Stale facts are superseded instead of duplicated.
• Current memory remains compact enough to send only relevant branches to Qwen.
• Previous values and superseded event ids remain auditable in branch metadata.
• Background consolidation links related memories and adjusts branch importance.
• Qwen answer generation receives relevant branch context, and chat also exposes the same answer request without memory context for comparison.
• Tair stores durable memory, events, search metadata, vector routing hints, and metrics.
• JSONL traces expose every memory mutation.

Built With

• alicloud
• qwen
• tair