Skill Detail

Generate and evaluate retrieval embeddings with FlagEmbedding

Use FlagEmbedding to choose BGE embedding or reranking models, encode documents and queries, evaluate retrieval quality, and feed stronger context into RAG workflows.

Data Extraction & TransformationMulti-Framework
Data Extraction & Transformation Multi-Framework Security Reviewed
⭐ 11.8k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill generate-and-evaluate-retrieval-embeddings-with-flagembedding Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python environment, FlagEmbedding package, selected BGE embedding or reranker model, local corpus, query set, and a downstream vector or RAG pipeline.
Install & setup
Install the FlagEmbedding Python package from the upstream instructions, select the required BGE model, run encoding or reranking on representative documents and queries, then connect the output to the retrieval store or evaluation harness.
Author
FlagOpen
Publisher
Open Source
Last updated
Jun 11, 2026
Quick brief

Invoke this workflow when an agent or RAG system needs a stronger retrieval layer before answers, search results, or memory recalls are trusted. The operator selects a BGE embedding or reranker model from FlagEmbedding, installs the Python package, encodes documents and queries, tests similarity or reranking behavior, and exports vectors or relevance scores to the surrounding retrieval stack. Reviewable inputs include the corpus, query set, selected model, chunking rules, batch settings, and evaluation questions. Reviewable outputs include embeddings, ranked results, retrieval metrics, and examples of improved or failed recall.

How it works

What this skill actually does

Use this instead of treating retrieval as a black-box vector database setting when the quality problem is model choice, reranking, multilingual coverage, multimodal search, or evaluation. The scope boundary is embedding and reranking preparation for retrieval pipelines. It is not a general model catalog or library listing; the skill is specifically about using FlagEmbedding’s documented BGE toolkit to generate, test, and hand off retrieval signals that another agent workflow can inspect.