integration source-backed
MemSearch: Jev memory reranking
MemSearch includes an optional Jev reranker for project-memory passages. Candidate excerpts are scored against the query before the application chooses which memories to return.
Notes
The hosted reranker accepts a TypeSafe credential and evaluates supplied candidate passages together.
source-backed — Public repository, docs or live artifact. About this label
Destinations
How to run
- Stack
- Python / Milvus / ONNX
- Requirements
- Python environment with pip; a folder of Markdown notes
- Keys / accounts
- Local ONNX embeddings need no API key; optional remote Jev reranking needs a TypeSafe key.
Install the ONNX extra, place your Markdown files in memory/, then index and search them. The first embedding run downloads a model. Use the linked configuration reference to enable optional remote reranking. Jev reranking is off by default. Enabling it in trusted global configuration sends queries and retrieved text to TypeSafe.
pip install "memsearch[onnx]"
memsearch index ./memory/
memsearch search "Redis caching"README review · · Documentation reviewed; project installation and live API not run.
Next: follow the practical guide → · compare projects for this task →
Try a walkthrough
- Select relevant context with Jev →
Score a small shortlist of passages, preserve their source IDs and pass selected evidence to your answering model.
Verification levels
- HTTP availability
- Link reachable ·
Method: bounded HTTP request with redirects. HTTP 200 · HTTP response only. Checked destination ↗ · Last reachable - Browser demo scenario
- Not checked
- Build
- Not checked
- Live API test
- Not checked