ragway
The way to build RAG.
Install
pip install ragway
Quickstart
from ragway import RAG
import asyncio, pathlib
pathlib.Path("example_docs").mkdir(exist_ok=True); pathlib.Path("example_docs/intro.md").write_text("# RAG\nRetrieval-Augmented Generation combines retrieval with generation.", encoding="utf-8")
rag = RAG(llm="openai", api_key="YOUR_OPENAI_KEY")
print(asyncio.run(rag.ingest("example_docs")), asyncio.run(rag.query("What is RAG?")))
Why ragway
- Compared to LangChain: smaller public surface, fewer framework abstractions, explicit config and component wiring.
- Compared to LlamaIndex: direct control over retrieval/rerank/vectorstore choices without committing to one indexing model.
- For production code: you can start simple with
RAG(...), then move to YAML config and provider-specific tuning without rewriting app code.
What You Can Swap
| Component | Options |
|---|---|
| LLM | anthropic, openai, mistral, groq, llama, local |
| Vectorstore | faiss, chroma, pinecone, weaviate |
| Retrieval | vector, bm25, hybrid, multi_query, parent_document |
| Reranker | cohere, bge, cross_encoder (or None) |
| Chunking | fixed, recursive, semantic, sliding_window, hierarchical |
| Pipeline | naive, hybrid, self, long_context, agentic |
Install Options
# Base package
pip install ragway
# Provider extras
pip install ragway[anthropic]
pip install ragway[openai]
pip install ragway[mistral]
pip install ragway[groq]
pip install ragway[cohere]
pip install ragway[pinecone]
pip install ragway[weaviate]
pip install ragway[faiss]
pip install ragway[chroma]
pip install ragway[llama]
pip install ragway[bge]
# Bundles
pip install ragway[all-cloud]
pip install ragway[all-local]
pip install ragway[all]
pip install ragway[dev]
Config File Example
version: "1.0"
pipeline: hybrid
plugins:
llm:
provider: groq
model: llama-3.1-8b-instant
api_key: ${GROQ_API_KEY}
temperature: 0.2
max_tokens: 512
embedding:
provider: openai
model: text-embedding-3-small
api_key: ${OPENAI_API_KEY}
batch_size: 32
vectorstore:
provider: faiss
index_name: rag-lab
top_k: 5
retrieval:
strategy: hybrid
top_k: 5
rrf_k: 60
reranker:
enabled: true
provider: cohere
api_key: ${COHERE_API_KEY}
top_k: 3
chunking:
strategy: recursive
chunk_size: 512
overlap: 50
from ragway import RAG
import asyncio
rag = RAG.from_config("rag.yaml")
print(asyncio.run(rag.query("Summarize the key idea.")))
Links
Metadata
Release files for ragway 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ragway-0.1.0.tar.gz | 2.4 MB | Without provenance | Details for ragway-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ragway-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ragway-0.1.0-py3-none-any.whl |
Total release size: 2.5 MB
Release files / ragway-0.1.0.tar.gz
| Download URL | ragway-0.1.0.tar.gz |
|---|---|
| Size | 2.4 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
072aba6b134aecce9df0d05cbcd1dae4615f91b16fd78ec3ef05a6b8bdb38167
|
|
BLAKE2b-256 checksum How to use checksums |
328b189bfbe9d870a9b3effe5edf197c8f48bdb47bb8a8a642f162f2ff9897d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / ragway-0.1.0-py3-none-any.whl
| Download URL | ragway-0.1.0-py3-none-any.whl |
|---|---|
| Size | 114.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e5a9d1fe5002c2872c986102f297b79a23a1e19fe3894e3abe575f93da0657b9
|
|
BLAKE2b-256 checksum How to use checksums |
b7359df8cf9e1ac2c4ffc1320de0e3fca674eaac8e3cb74fa64bbb34cdf93e6e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for ragway 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.