This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+6 more
Summary
AI summaryConfigurable embedding dtype via RAG_DTYPE with clearer error reporting.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds configurable embedding dtype via RAG_DTYPE environment variable. Adds configurable embedding dtype via RAG_DTYPE environment variable. Source: llm_adapter@2026-06-12 Confidence: high |
— |
| Bugfix | Medium |
Improves error reporting to show real cause instead of generic messages. Improves error reporting to show real cause instead of generic messages. Source: llm_adapter@2026-06-12 Confidence: high |
— |
| Bugfix | Medium |
Adds distinct error when re-ingest rollback fails, indicating possible data restoration issue. Adds distinct error when re-ingest rollback fails, indicating possible data restoration issue. Source: llm_adapter@2026-06-12 Confidence: high |
— |
Full changelog
Added
- Configurable embedding dtype via
RAG_DTYPE. Choose the embedding quantization (fp32,fp16,q8,int8, …) with an opt-in environment variable. The default isfp32, so existing setups are unchanged. If the chosen model does not provide the requested dtype, the server fails with an error that lists the dtypes the model does provide. ChangingRAG_DTYPE(orRAG_DEVICE) changes the embedding space, so re-ingest your documents after changing it.
Changed
- Clearer error reporting. Errors now keep their real cause instead of being masked. For example, a dtype/model misconfiguration during PDF ingestion now reports the actual problem rather than a generic “Failed to parse PDF”. Full diagnostic detail (cause chain) is written to stderr logs; MCP clients receive a clean, controlled message.
- A failed re-ingest whose rollback also fails now reports a distinct error stating that existing data may not have been restored.
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
About shinpr/mcp-local-rag
Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys or cloud services required.
Related context
Beta — feedback welcome: [email protected]