mpashkovskiy/ru-rag
RAG pipeline implementation example for the Russian language
Combines semantic search over CSV datasets with generative summarization using paraphrase-multilingual-mpnet-base-v2 embeddings and the Saiga 13B LLaMA model for Russian-language QA. Provides CLI commands for document retrieval and answer generation, with support for both GPU acceleration and CPU inference through llama.cpp. Accepts tab-separated CSV files and populates a searchable vector database to ground LLM responses in retrieved context.
No commits in the last 6 months.
Stars
24
Forks
2
Language
Python
License
CC-BY-4.0
Category
Last pushed
Jun 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/mpashkovskiy/ru-rag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vitali87/code-graph-rag
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with...
stevereiner/flexible-graphrag
Flexible GraphRAG: Python, LlamaIndex, Docker Compose: 8 Graph dbs, 10 Vector dbs, OpenSearch,...
christopherkarani/Wax
Lightening fast RAG on Apple Silicon. On-Device. No Server. No API. One File. Pure Swift
dmayboroda/minima
On-premises conversational RAG with configurable containers
shredEngineer/Archive-Agent
Find your files with natural language and ask questions.