The best zero-config RAG interface yet.
quickstart.py 
from piragi import Ragi

kb = Ragi("./docs")
answer = kb.ask("How to deploy to production?")

print(answer.text)
print(answer.citations)
zero config
Works with free local models out of the box
all formats
PDF, Word, Excel, Markdown, code, URLs, images, audio
remote storage
Read from S3, GCS, Azure, HDFS with glob patterns
web crawling
Recursively crawl websites with /** syntax
auto-updates
Background refresh, queries never blocked
citations
Every answer includes scored sources
vector stores
Lance, Postgres, Qdrant, Pinecone, Supabase
retrieval
HyDE, hybrid search, cross-encoder reranking
chunking
Semantic, hierarchical, and contextual strategies
knowledge graph
Entity/relationship extraction for deeper answers
onnx
2-5x faster embeddings on CPU via ONNX Runtime
pipelines
Composable Ingestion & Retrieval pipelines
v1.2.1
connecting…
pip install piragi
Cells
1Basic RAG
2Embeddings
3Shared Model
4Qdrant Store
5Chunking
6Retrieval
7Knowledge Graph
8Async
9Config
10Remote FS
11Ask (LLM)
12Pipelines
13Filter & LLM
LLM Config
no LLM detected
docs . pypi
by @hemanth
Basic RAG python
demo mode — pip install piragi && piragi playground for live execution
Output