lyonzin/knowledge-rag

v4.0.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo MCP Developer Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

antigravity claude claude-code claude-code-cli codex cursor-ai

+14 more

document-search hybrid-search inteligencia-artificial knowledge-base local-ai mcp mcp-server llm rag-chatbot rag-pipeline reranking retrieval-augmented-generation semantic-search vector-db

Affected surfaces

breaking_upgrade

ReleasePort's take

Light signal

editorial:auto 1mo

Release v4.0.0 introduces SSE and streamable‑http transports, auto‑enables ChromaDB WAL mode for these transports, adds optional sliding‑window rate limiting and a Prometheus /metrics endpoint (both disabled by default), expands config paths to support `~`, debounces the file watcher, batches ChromaDB writes, and adds a concurrency lock for reindex.

Why it matters: New SSE/HTTP transport modes expand server capabilities; automatic ChromaDB WAL mode improves durability without extra config. Optional sliding‑window rate limiting (disabled) lets you throttle traffic as needed, while the Prometheus /metrics endpoint (also disabled) enables observability when enabled.

Summary

AI summary

Updates New Features, Also includes v3.9.1 fixes, and uvicorn across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds SSE and streamable‑http transport modes to server. Adds SSE and streamable‑http transport modes to server. Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Low	Enables ChromaDB WAL mode automatically in SSE/HTTP transport. Enables ChromaDB WAL mode automatically in SSE/HTTP transport. Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Low	Adds optional sliding‑window rate limiting (disabled by default). Adds optional sliding‑window rate limiting (disabled by default). Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Low	Adds optional Prometheus /metrics endpoint on separate port (disabled by default). Adds optional Prometheus /metrics endpoint on separate port (disabled by default). Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Low	Adds optional dependency knowledge‑rag[server] for SSE/HTTP (requires uvicorn). Adds optional dependency knowledge‑rag[server] for SSE/HTTP (requires uvicorn). Source: llm_adapter@2026-06-09 Confidence: high	—
Performance	Medium	Batches ChromaDB writes to 500 chunks per call. Batches ChromaDB writes to 500 chunks per call. Source: llm_adapter@2026-06-09 Confidence: high	—
Bugfix
Bugfix	Medium	Expands `~` in config file paths. Expands `~` in config file paths. Source: llm_adapter@2026-06-09 Confidence: high	—
Bugfix	Medium	Debounces accumulate‑mode file watcher. Debounces accumulate‑mode file watcher. Source: llm_adapter@2026-06-09 Confidence: high	—
Bugfix	Medium	Adds concurrency lock for reindex operation. Adds concurrency lock for reindex operation. Source: llm_adapter@2026-06-09 Confidence: high	—

Full changelog

Enterprise Concurrent Access — SSE/HTTP Transport

The server now supports SSE and streamable-http transport modes. A single server process serves all clients with shared resources — 1 embedding model, 1 ChromaDB, 1 query cache.

New Features

SSE/HTTP transport: server.transport: "sse" in config.yaml or --transport sse CLI
Thread-safe shared state: QueryCache locking, BM25 build lock, orchestrator double-checked locking
ChromaDB WAL mode: Enabled automatically in SSE/HTTP mode for concurrent read performance
Rate limiting: Optional sliding-window counter (disabled by default)
Prometheus metrics: Optional /metrics endpoint on separate port (disabled by default)
All 12 tools instrumented: @rate_limited + @instrument decorators (zero-cost when disabled)
--transport CLI override: For Docker/systemd deployments
pip install knowledge-rag[server]: Optional dependency for SSE/HTTP (uvicorn)

Migration

Default transport remains stdio — existing users need zero changes. To enable SSE:

# config.yaml
server:
  transport: "sse"
  host: "127.0.0.1"
  port: 8179

MCP client config:

{"mcpServers": {"knowledge-rag": {"type": "sse", "url": "http://127.0.0.1:8179/sse"}}}

Also includes v3.9.1 fixes

Expand ~ in config paths (#86)
Accumulate-mode file watcher debounce
Batched ChromaDB writes (500 chunks/call)
Reindex concurrency lock

Acknowledgements

Thanks to @noahcoad for #86.

Full Changelog: https://github.com/lyonzin/knowledge-rag/compare/v3.9.0...v4.0.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track lyonzin/knowledge-rag

Get notified when new releases ship.

About lyonzin/knowledge-rag

Local RAG system for Claude Code with hybrid search (BM25 + semantic), cross-encoder reranking, markdown-aware chunking, query expansion, and 12 MCP tools. Runs entirely offline with zero external servers.

All releases →