Source: https://seerepo.com/r/datawhalechina/all-in-rag/built
Markdown source: https://seerepo.com/r/datawhalechina/all-in-rag/built.md
Description: all-in-rag is a Python repo. It stores its data in pymilvus and Neo4j. It has 17,394 written lines. Every service with the file and the line that prove it.

# What is all-in-rag built with?

all-in-rag is a Python repo. It stores its data in pymilvus and Neo4j, uses AI through accelerate, datasets, faiss-cpu, langchain-unstructured, librosa, and 27 more, makes its content with av, markdown, openpyxl, pypdf, pypdfium2, and 2 more, validates its data with Pydantic, and uses chromadb, pyarrow, and Hugging Face. It has 17,394 written lines.

Read on November 10, 2026, at commit cec956e.

Repository: https://github.com/datawhalechina/all-in-rag

## Backend

### Data

- **[chromadb](https://seerepo.com/uses/chromadb)**
- **[pyarrow](https://seerepo.com/uses/pyarrow)**
- **[pymilvus](https://seerepo.com/uses/pymilvus)**: 8 files
- **[Neo4j](https://seerepo.com/uses/neo4j)**: 3 files

### AI

- **[accelerate](https://seerepo.com/uses/accelerate)**
- **[datasets](https://seerepo.com/uses/datasets)**
- **[faiss-cpu](https://seerepo.com/uses/faiss-cpu)**
- **langchain-unstructured**
- **[librosa](https://seerepo.com/uses/librosa)**
- **llama-index-embeddings-openai**
- **llama-index-llms-openai**
- **[openai](https://seerepo.com/uses/openai)**
- **tavily-python**
- **[tiktoken](https://seerepo.com/uses/tiktoken)**
- **[tokenizers](https://seerepo.com/uses/tokenizers)**
- **[torchaudio](https://seerepo.com/uses/torchaudio)**
- **unstructured-client**
- **[torch](https://seerepo.com/uses/torch)**: 22 files
- **[LangChain](https://seerepo.com/uses/langchain)**: 20 files
- **[langchain-community](https://seerepo.com/uses/langchain-community)**: 14 files
- **langchain-deepseek**: 8 files
- **[transformers](https://seerepo.com/uses/transformers)**: 7 files
- **langchain-huggingface**: 6 files
- **llama-index-core**: 6 files
- **llama-index-embeddings-huggingface**: 6 files
- **[langchain-openai](https://seerepo.com/uses/langchain-openai)**: 4 files
- **[timm](https://seerepo.com/uses/timm)**: 4 files
- **langchain-text-splitters**: 2 files
- **[scikit-learn](https://seerepo.com/uses/scikit-learn)**: 2 files
- **[sentence-transformers](https://seerepo.com/uses/sentence-transformers)**: 2 files
- **[torchvision](https://seerepo.com/uses/torchvision)**: 2 files
- **[einops](https://seerepo.com/uses/einops)**: 1 file
- **langchain-experimental**: 1 file
- **[LangGraph](https://seerepo.com/uses/langgraph)**: 1 file
- **llama-index**: 1 file
- **[rank-bm25](https://seerepo.com/uses/rank-bm25)**: 1 file

### Services

- **[Hugging Face](https://seerepo.com/uses/hugging-face)**: 1 file · [code/C3/visual_bge/visual_bge/eva_clip/pretrained.py, line 11](https://github.com/datawhalechina/all-in-rag/blob/cec956e80ae28d6c0ca84c9d39dddcf61ad633fd/code/C3/visual_bge/visual_bge/eva_clip/pretrained.py#L11)

## Support

### Content

- **[av](https://seerepo.com/uses/av)**
- **[markdown](https://seerepo.com/uses/markdown)**
- **[openpyxl](https://seerepo.com/uses/openpyxl)**
- **[pypdf](https://seerepo.com/uses/pypdf)**
- **[pypdfium2](https://seerepo.com/uses/pypdfium2)**
- **[pillow](https://seerepo.com/uses/pillow)**: 4 files
- **unstructured**: 1 file

### Validation

- **[Pydantic](https://seerepo.com/uses/pydantic)**: 1 file

### Other

- **dataclasses**
- **lark**
- **lazy-loader**
- **pathlib2**
- **soundfile**
- **NumPy**: 12 files
- **python-dotenv**: 7 files
- **pandas**: 4 files
- **tqdm**: 4 files
- **opencv-python-headless**: 3 files
- **ftfy**: 1 file
- **jieba**: 1 file
- **requests**: 1 file
- **SciPy**: 1 file

## Other repos with a similar stack

- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): chromadb, pyarrow, pymilvus, Neo4j, datasets, llama-index-embeddings-openai, llama-index-llms-openai, OpenAI, tavily-python, tiktoken, tokenizers, torch, LangChain, transformers, llama-index-core, llama-index-embeddings-huggingface, scikit-learn, sentence-transformers, einops, pypdf, pillow, unstructured, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/all-in-rag/vs/run-llama/llama_index)
- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/built): chromadb, pymilvus, Hugging Face, accelerate, datasets, OpenAI, tavily-python, tiktoken, tokenizers, torch, transformers, langchain-openai, scikit-learn, sentence-transformers, LangGraph, rank-bm25, markdown, openpyxl, pypdf, pillow, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/all-in-rag/vs/datawhalechina/hello-agents)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): chromadb, pyarrow, Hugging Face, accelerate, datasets, faiss-cpu, librosa, OpenAI, tiktoken, torchaudio, torch, transformers, langchain-openai, scikit-learn, sentence-transformers, rank-bm25, markdown, openpyxl, pypdf, pillow, Pydantic · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/datawhalechina/all-in-rag)
- [open-webui/open-webui](https://seerepo.com/r/open-webui/open-webui/built): chromadb, pyarrow, pymilvus, Hugging Face, accelerate, OpenAI, tiktoken, LangChain, transformers, langchain-text-splitters, sentence-transformers, einops, rank-bm25, av, markdown, openpyxl, pypdf, pillow, unstructured, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/all-in-rag/vs/open-webui/open-webui)
- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI/built): chromadb, Hugging Face, accelerate, datasets, OpenAI, tiktoken, tokenizers, torchaudio, torch, LangChain, transformers, timm, scikit-learn, sentence-transformers, torchvision, einops, pypdf, pillow, unstructured, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/all-in-rag/vs/hpcaitech/ColossalAI)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): pyarrow, Hugging Face, accelerate, datasets, tiktoken, tokenizers, torchaudio, torch, LangChain, transformers, timm, scikit-learn, torchvision, einops, av, markdown, openpyxl, pillow, Pydantic · [Compare](https://seerepo.com/compare/datawhalechina/all-in-rag/vs/ray-project/ray)

## Frequently asked questions

### What language is all-in-rag written in?

all-in-rag is written in Python, with 17,394 written lines.

### What database does all-in-rag use?

all-in-rag stores its data in pymilvus and Neo4j.

### Does all-in-rag use AI?

Yes. all-in-rag uses AI through accelerate, datasets, faiss-cpu, langchain-unstructured, librosa, llama-index-embeddings-openai, llama-index-llms-openai, openai, tavily-python, tiktoken, tokenizers, torchaudio, unstructured-client, torch, LangChain, langchain-community, langchain-deepseek, transformers, langchain-huggingface, llama-index-core, llama-index-embeddings-huggingface, langchain-openai, timm, langchain-text-splitters, scikit-learn, sentence-transformers, torchvision, einops, langchain-experimental, LangGraph, llama-index, and rank-bm25.

### What services does all-in-rag use?

all-in-rag uses chromadb, pyarrow, and Hugging Face.

### Which repos have a stack like all-in-rag's?

The ones that share most of its stack: run-llama/llama_index, datawhalechina/hello-agents, and bojieli/ai-agent-book.

## 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.