Metadata-Version: 2.4
Name: ragpipe-lite
Version: 0.1.0
Summary: ragpipe-lite: unified RAG ingestion pipeline (loaders, chunking, embeddings, vector store export).
Author: Kubenew
License: MIT
Project-URL: Homepage, https://github.com/Kubenew/ragpipe
Project-URL: Repository, https://github.com/Kubenew/ragpipe
Keywords: rag,llm,embedding,vector,faiss,pipeline,ai
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.23.0
Requires-Dist: requests>=2.31.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: faiss
Requires-Dist: faiss-cpu>=1.7.4; extra == "faiss"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: build>=1.0.0; extra == "dev"
Requires-Dist: twine>=4.0.0; extra == "dev"
Dynamic: license-file

# ragpipe

`ragpipe` is a lightweight RAG ingestion pipeline toolkit.

It helps you go from documents → chunks → embeddings → vector store export.

## Features (v0.1.0)

- text chunking with overlap
- basic loaders (text files, URLs)
- embedding interface abstraction
- JSON export format
- optional FAISS dependency group

## Install

```bash
pip install ragpipe
```

Optional FAISS:

```bash
pip install ragpipe[faiss]
```

## CLI usage

```bash
ragpipe ingest ./docs --out out.json
ragpipe ingest-url https://example.com --out out.json
```

## Python usage

```python
from ragpipe import chunk_text, ingest_text

chunks = chunk_text("hello world " * 200, chunk_size=200, overlap=50)
print(len(chunks))

data = ingest_text("hello world " * 200)
print(data.keys())
```

## License
MIT
