Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
GitHub / arjbingly / grag
GRAG is a simple python package that provides an easy end-to-end solution for implementing Retrieval Augmented Generation (RAG). The package offers an easy way for running various LLMs locally, Thanks to LlamaCpp and also supports vector stores like Chroma and DeepLake.
JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arjbingly%2Fgrag
Stars: 4
Forks: 0
Open Issues: 3
License: agpl-3.0
Language: Python
Repo Size: 53.1 MB
Dependencies:
26
Created: 4 months ago
Updated: 20 days ago
Last pushed: 20 days ago
Last synced: 19 days ago
Topics: llm, quantization, rag, retrieval, retrieval-augmented-generation
Files
Dependencies
- chromadb >=0.4.13
- huggingface_hub >=0.20.2
- instructorembedding >=1.0.1
- langchain >=0.1.5
- llama-cpp-python >=0.2.43
- pdfplumber >=0.10.3
- pydantic >=2.5.0
- rouge-score >=0.1.2
- sentence-transformers ==2.2.2
- streamlit >=1.31.1
- torch >=2.2.0
- tqdm >=4.65.0
- transformers >=4.37.1
- unstructured >=0.12.3
- actions/checkout v4 composite
- actions/setup-python v5 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- stefanzweifel/git-auto-commit-action v4 composite
- actions/checkout v4 composite
- actions/configure-pages v5 composite
- actions/deploy-pages v4 composite
- actions/setup-python v5 composite
- actions/upload-pages-artifact v3 composite