# Neural RAG
Neural Rag is a LLM framework to build Vector RAG and Graph RAG knowledge base. It
provides the foundation to quickly build agents.
## What is RAG?
RAG stands for Retrieval Augmented Generation.
It was introduced in the paper [*Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks*](https://arxiv.org/abs/2005.11401).
Each step can be roughly broken down to:
* **Retrieval** - Seeking relevant information from a source given a query. For example, getting relevant passages of Wikipedia text from a database given a question.
* **Augmented** - Using the relevant retrieved information to modify an input to a generative model (e.g. an LLM).
* **Generation** - Generating an output given an input. For example, in the case of an LLM, generating a passage of text given an input prompt.
Raw data
{
"_id": null,
"home_page": "http://github.com/gigas64/hadron-nn",
"name": "neural-rag",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Gigas64",
"author_email": "gigas64@aistac.net",
"download_url": "https://files.pythonhosted.org/packages/22/78/df3ed5140501b88faa1610ba2c4c8b711d06529c72e42c6d7d3fe06693d3/neural_rag-0.5.27.tar.gz",
"platform": null,
"description": "# Neural RAG\n\nNeural Rag is a LLM framework to build Vector RAG and Graph RAG knowledge base. It \nprovides the foundation to quickly build agents.\n\n## What is RAG?\n\nRAG stands for Retrieval Augmented Generation.\n\nIt was introduced in the paper [*Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks*](https://arxiv.org/abs/2005.11401).\n\n\n\nEach step can be roughly broken down to:\n\n* **Retrieval** - Seeking relevant information from a source given a query. For example, getting relevant passages of Wikipedia text from a database given a question.\n* **Augmented** - Using the relevant retrieved information to modify an input to a generative model (e.g. an LLM).\n* **Generation** - Generating an output given an input. For example, in the case of an LLM, generating a passage of text given an input prompt.\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": null,
"version": "0.5.27",
"project_urls": {
"Homepage": "http://github.com/gigas64/hadron-nn"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "82fea3e06652c899913ecadfce7b931c92957ba45dd203f887f015eabec7d2ba",
"md5": "1fc8791000bb997523ba3f27254f7f0d",
"sha256": "508aefccc78f3c3b975e7f60dbab8f5f7162f71b82d9d5d0e79959ecb75db08a"
},
"downloads": -1,
"filename": "neural_rag-0.5.27-py310-none-any.whl",
"has_sig": false,
"md5_digest": "1fc8791000bb997523ba3f27254f7f0d",
"packagetype": "bdist_wheel",
"python_version": "py310",
"requires_python": null,
"size": 101944,
"upload_time": "2024-08-04T19:08:08",
"upload_time_iso_8601": "2024-08-04T19:08:08.203643Z",
"url": "https://files.pythonhosted.org/packages/82/fe/a3e06652c899913ecadfce7b931c92957ba45dd203f887f015eabec7d2ba/neural_rag-0.5.27-py310-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2278df3ed5140501b88faa1610ba2c4c8b711d06529c72e42c6d7d3fe06693d3",
"md5": "55432362dfce9c0774b0ba2f0860444d",
"sha256": "3b96f47f3270aeb20ced61b169254ae0c6027951f4858ccc36199c14f6ff9411"
},
"downloads": -1,
"filename": "neural_rag-0.5.27.tar.gz",
"has_sig": false,
"md5_digest": "55432362dfce9c0774b0ba2f0860444d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 58826,
"upload_time": "2024-08-04T19:08:10",
"upload_time_iso_8601": "2024-08-04T19:08:10.548748Z",
"url": "https://files.pythonhosted.org/packages/22/78/df3ed5140501b88faa1610ba2c4c8b711d06529c72e42c6d7d3fe06693d3/neural_rag-0.5.27.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-04 19:08:10",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "gigas64",
"github_project": "hadron-nn",
"github_not_found": true,
"lcname": "neural-rag"
}
JSON
