Generate And Evaluate Retrieval Embeddings With Flagembedding

---
name: "Generate and evaluate retrieval embeddings with FlagEmbedding"
slug: "generate-and-evaluate-retrieval-embeddings-with-flagembedding"
description: "Use FlagEmbedding to choose BGE embedding or reranking models, encode documents and queries, evaluate retrieval quality, and feed stronger context into RAG workflows."
github_stars: 11807
verification: "security_reviewed"
source: "https://github.com/FlagOpen/FlagEmbedding"
author: "FlagOpen"
publisher_type: "open_source"
category: "Data Extraction & Transformation"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "FlagOpen/FlagEmbedding"
  github_stars: 11807
---

# 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.

## Prerequisites

Python environment, FlagEmbedding package, selected BGE embedding or reranker model, local corpus, query set, and a downstream vector or RAG pipeline.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install -U FlagEmbedding
- pip install -U FlagEmbedding[finetune]
- git clone https://github.com/FlagOpen/FlagEmbedding.git
- pip install .

Basic usage or getting-started notes:
- <a href=#quick-start>Quick Start</a> |
- If you do not want to finetune the models, you can install the package without the finetune dependency:
- If you want to finetune the models, you can install the package with the finetune dependency:

- Source: https://github.com/FlagOpen/FlagEmbedding
- Extracted from upstream docs: https://raw.githubusercontent.com/FlagOpen/FlagEmbedding/HEAD/README.md

## Documentation

- https://github.com/FlagOpen/FlagEmbedding

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/generate-and-evaluate-retrieval-embeddings-with-flagembedding/)