Source: https://seerepo.com/r/FlagOpen/FlagEmbedding/built
Markdown source: https://seerepo.com/r/FlagOpen/FlagEmbedding/built.md
Description: FlagEmbedding is a Python repo built with tornado. It reaches its data with sqlglot. It has 97,836 written lines, with 22 test files.

# What is FlagEmbedding built with?

FlagEmbedding is a Python repo built with tornado. It reaches its data with sqlglot, uses AI through bitsandbytes, ir-datasets, ModelScope, rank-bm25, sentencepiece, and 16 more, and makes its content with jinja2. It has 97,836 written lines, with 22 test files.

Read on November 11, 2026, at commit 897baa6.

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

## Backend

### Data access

- **[sqlglot](https://seerepo.com/uses/sqlglot)**

### AI

- **[bitsandbytes](https://seerepo.com/uses/bitsandbytes)**
- **ir-datasets**
- **[ModelScope](https://seerepo.com/uses/modelscope)**
- **[rank-bm25](https://seerepo.com/uses/rank-bm25)**
- **[sentencepiece](https://seerepo.com/uses/sentencepiece)**
- **[transformers](https://seerepo.com/uses/transformers)**: 248 files
- **[torch](https://seerepo.com/uses/torch)**: 169 files
- **flagembedding**: 119 files
- **[datasets](https://seerepo.com/uses/datasets)**: 79 files
- **[accelerate](https://seerepo.com/uses/accelerate)**: 35 files
- **[peft](https://seerepo.com/uses/peft)**: 30 files
- **flash-attn**: 13 files
- **mteb**: 12 files
- **[torchvision](https://seerepo.com/uses/torchvision)**: 8 files
- **deepspeed**: 5 files
- **vLLM**: 5 files
- **[timm](https://seerepo.com/uses/timm)**: 4 files
- **[sentence-transformers](https://seerepo.com/uses/sentence-transformers)**: 3 files
- **[einops](https://seerepo.com/uses/einops)**: 2 files
- **[tiktoken](https://seerepo.com/uses/tiktoken)**: 2 files
- **[langchain-openai](https://seerepo.com/uses/langchain-openai)**: 1 file

## Support

### The base

- **[tornado](https://seerepo.com/uses/tornado)**

### Content

- **[jinja2](https://seerepo.com/uses/jinja2)**

### Other

- **func-timeout**
- **protobuf**
- **rapidfuzz**
- **pandas**: 19 files
- **ftfy**: 1 file

## Other repos with a similar stack

- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI/built): bitsandbytes, ModelScope, sentencepiece, transformers, torch, datasets, accelerate, peft, flash-attn, torchvision, vLLM, timm, sentence-transformers, einops, tiktoken, jinja2 · [Compare](https://seerepo.com/compare/FlagOpen/FlagEmbedding/vs/hpcaitech/ColossalAI)
- [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/built): bitsandbytes, ModelScope, sentencepiece, transformers, torch, datasets, accelerate, peft, flash-attn, torchvision, vLLM, sentence-transformers, einops, tiktoken, jinja2 · [Compare](https://seerepo.com/compare/FlagOpen/FlagEmbedding/vs/mudler/LocalAI)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): tornado, sqlglot, bitsandbytes, sentencepiece, transformers, torch, datasets, accelerate, peft, torchvision, deepspeed, timm, einops, tiktoken, jinja2 · [Compare](https://seerepo.com/compare/FlagOpen/FlagEmbedding/vs/ray-project/ray)
- [hiyouga/LlamaFactory](https://seerepo.com/r/hiyouga/LlamaFactory/built): bitsandbytes, ModelScope, sentencepiece, transformers, torch, datasets, accelerate, peft, torchvision, deepspeed, vLLM, einops, tiktoken · [Compare](https://seerepo.com/compare/FlagOpen/FlagEmbedding/vs/hiyouga/LlamaFactory)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): bitsandbytes, rank-bm25, sentencepiece, transformers, torch, flagembedding, datasets, accelerate, peft, vLLM, sentence-transformers, tiktoken, langchain-openai · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/FlagOpen/FlagEmbedding)
- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): tornado, ModelScope, sentencepiece, transformers, torch, flagembedding, datasets, peft, vLLM, sentence-transformers, einops, tiktoken, jinja2 · [Compare](https://seerepo.com/compare/FlagOpen/FlagEmbedding/vs/run-llama/llama_index)

## Frequently asked questions

### What language is FlagEmbedding written in?

FlagEmbedding is written in Python, with 97,836 written lines.

### What framework does FlagEmbedding use?

FlagEmbedding is built with tornado.

### Does FlagEmbedding use AI?

Yes. FlagEmbedding uses AI through bitsandbytes, ir-datasets, ModelScope, rank-bm25, sentencepiece, transformers, torch, flagembedding, datasets, accelerate, peft, flash-attn, mteb, torchvision, deepspeed, vLLM, timm, sentence-transformers, einops, tiktoken, and langchain-openai.

### Does FlagEmbedding have tests?

Yes. FlagEmbedding has 22 test files.

### Which repos have a stack like FlagEmbedding's?

The ones that share most of its stack: hpcaitech/ColossalAI, mudler/LocalAI, and ray-project/ray.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.