RE-call

mentions 4 type Organization feed RSS

// recent coverage 4 mentions

12:07

2026-07-18

dev.to

machine-learning

Retrieval-Augmented Self-Recall — Part 6: The Fine-Tune That Did Nothing, and Shipping It as an MCP Server

A developer fine-tuned an embedding model on a personal domain corpus and found zero improvement in retrieval metrics (MRR and nDCG@10), concluding that off-the-shelf embeddings already saturated the …

12:06

2026-07-18

dev.to

machine-learning

Retrieval-Augmented Self-Recall — Part 4: Benchmarking Retrieval and Honesty

A developer building the RE-call system created a new benchmark harness that evaluates both retrieval quality and honesty, measuring whether a system correctly abstains when no answer exists. Testing …

12:06

2026-07-18

dev.to

artificial-intelligence

Retrieval-Augmented Self-Recall — Part 3: Teaching RAG to Say \"I Don't Know\

A developer building RE-call, a retrieval system for agent memory, introduces honesty guards to prevent agents from acting on hallucinated or irrelevant results. The gap_warning flag checks if the top…

12:05

2026-07-18

dev.to

artificial-intelligence

Retrieval-Augmented Self-Recall — Part 2: Hybrid RAG on Nothing but Postgres

A developer built RE-call, a hybrid retrieval system for agent memory that runs entirely on PostgreSQL using pgvector for dense vector search and built-in full-text search, avoiding dedicated vector d…

// co-occurs with top 8 entities

Postgres 2 pgvector 2 all-MiniLM-L6-v2 1 recall_mcp 1 Claude 1 HashingEmbedder 1 bge-small 1 voyage-3 1

RE-call

// recent coverage 4 mentions

Retrieval-Augmented Self-Recall — Part 6: The Fine-Tune That Did Nothing, and Shipping It as an MCP Server

Retrieval-Augmented Self-Recall — Part 4: Benchmarking Retrieval *and* Honesty

Retrieval-Augmented Self-Recall — Part 3: Teaching RAG to Say \"I Don't Know\

Retrieval-Augmented Self-Recall — Part 2: Hybrid RAG on Nothing but Postgres

Retrieval-Augmented Self-Recall — Part 4: Benchmarking Retrieval and Honesty