OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Flagembedding

FlagEmbedding is an open-source Python toolkit for building search and retrieval-augmented generation applications with BGE retrieval models and embedding tools.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Flagembedding — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use FlagEmbedding when developing the retrieval layer of a search or RAG application and you want to work with BGE models and Python tools.

Who it is for

  • Developers building semantic search over document collections.
  • Teams adding embedding-based retrieval or passage retrieval to an LLM application.

Documented uses

  • Create semantic search for a document collection.
  • Retrieve relevant passages to provide context to a language model.
  • Build embedding-based retrieval or text semantic similarity search.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed open-source software.

  • It is a developer library, so it serves as a component in a larger application rather than a ready-to-use hosted search product.
  • The repository identifies Python as its primary language.
  • The project covers BGE retrieval models and search and RAG use cases.
  • The repository lists an MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install FlagEmbedding and compute text similarity

Install the package without fine-tuning dependencies, create embeddings for two sentence lists, and compare them by inner product.

Before you start

  • Python package installation with pip.
  • For this recipe, no fine-tuning dependency is needed.

Steps

  1. Install FlagEmbedding with the command below.

    Documented command
    pip install -U FlagEmbedding

  2. Load the BGE model with from FlagEmbedding import FlagAutoModel and FlagAutoModel.from_finetuned('BAAI/bge-base-en-v1.5', query_instruction_for_retrieval="Represent this sentence for searching relevant passages:", use_fp16=True).

  3. Pass sentence lists to model.encode, for example sentences_1 = ["I love NLP", "I love machine learning"] and sentences_2 = ["I love BGE", "I love text retrieval"], then assign the outputs to embeddings_1 and embeddings_2.

  4. Compute pairwise similarity with similarity = embeddings_1 @ embeddings_2.T and print the result.

Expected outcome

Two sentence lists are represented as embeddings, and their pairwise inner-product similarity matrix is computed.

Guide limitations

  • This recipe demonstrates embedding and similarity computation, not a complete document-search or RAG pipeline.
  • The README does not specify hardware requirements or model-download details.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
FlagembeddingCreate semantic search for a document collection.Linux, macOS, Server, WindowsThe repository is public and identifies the project as MIT-licensed open-source software.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
FlagOpen/FlagEmbedding · Official homepage title · retained in its source language
How we review sourcesSuggest a correction