# Simple self-RAG short form pack
This LlamaPack implements (\*in short form) the [self-RAG paper by Akari et al.](https://arxiv.org/pdf/2310.11511.pdf).
This paper presents a novel framework called Self-Reflective Retrieval-Augmented Generation (SELF-RAG). Which aims to enhance the quality and factuality of large language models (LLMs) by combining retrieval and self-reflection mechanisms.
The implementation is adapted from the author [implementation](https://github.com/AkariAsai/self-rag)
A full notebook guide can be found [here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/self_rag/self_rag.ipynb).
## CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack SelfRAGPack --download-dir ./self_rag_pack
```
You can then inspect the files at `./self_rag_pack` and use them as a template for your own project!
## Code Usage
We will show you how to import the agent from these files!
The implementation uses llama-cpp, to download the relevant models (be sure to replace DIR_PATH)
```bash
pip3 install -q huggingface-hub
huggingface-cli download m4r1/selfrag_llama2_7b-GGUF selfrag_llama2_7b.q4_k_m.gguf --local-dir "<DIR_PATH>" --local-dir-use-symlinks False
```
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
SelfRAGPack = download_llama_pack("SelfRAGPack", "./self_rag_pack")
```
From here, you can use the pack. You can import the relevant modules from the download folder (in the example below we assume it's a relative import or the directory
has been added to your system path).
```python
from self_rag_pack.base import SelfRAGQueryEngine
query_engine = SelfRAGQueryEngine(
model_path=model_path, retriever=retriever, verbose=True
)
response = query_engine.query(
"Who won best Director in the 1972 Academy Awards?"
)
```
You can also use/initialize the pack directly.
```python
from llm_compiler_agent_pack.base import SelfRAGPack
agent_pack = SelfRAGPack(
model_path=model_path, retriever=retriever, verbose=True
)
```
The `run()` function is a light wrapper around `agent.chat()`.
```python
response = pack.run("Who won best Director in the 1972 Academy Awards?")
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-self-rag",
"maintainer": "mmaatouk",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "llm, self-RAG, smart-retreiver",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/60/16/d97913dca8f54439d1b61a2cfccc41d262d65a947322c8f1b1eae84124e6/llama_index_packs_self_rag-0.3.0.tar.gz",
"platform": null,
"description": "# Simple self-RAG short form pack\n\nThis LlamaPack implements (\\*in short form) the [self-RAG paper by Akari et al.](https://arxiv.org/pdf/2310.11511.pdf).\n\nThis paper presents a novel framework called Self-Reflective Retrieval-Augmented Generation (SELF-RAG). Which aims to enhance the quality and factuality of large language models (LLMs) by combining retrieval and self-reflection mechanisms.\n\nThe implementation is adapted from the author [implementation](https://github.com/AkariAsai/self-rag)\nA full notebook guide can be found [here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/self_rag/self_rag.ipynb).\n\n## CLI Usage\n\nYou can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:\n\n```bash\nllamaindex-cli download-llamapack SelfRAGPack --download-dir ./self_rag_pack\n```\n\nYou can then inspect the files at `./self_rag_pack` and use them as a template for your own project!\n\n## Code Usage\n\nWe will show you how to import the agent from these files!\nThe implementation uses llama-cpp, to download the relevant models (be sure to replace DIR_PATH)\n\n```bash\npip3 install -q huggingface-hub\nhuggingface-cli download m4r1/selfrag_llama2_7b-GGUF selfrag_llama2_7b.q4_k_m.gguf --local-dir \"<DIR_PATH>\" --local-dir-use-symlinks False\n```\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nSelfRAGPack = download_llama_pack(\"SelfRAGPack\", \"./self_rag_pack\")\n```\n\nFrom here, you can use the pack. You can import the relevant modules from the download folder (in the example below we assume it's a relative import or the directory\nhas been added to your system path).\n\n```python\nfrom self_rag_pack.base import SelfRAGQueryEngine\n\nquery_engine = SelfRAGQueryEngine(\n model_path=model_path, retriever=retriever, verbose=True\n)\n\nresponse = query_engine.query(\n \"Who won best Director in the 1972 Academy Awards?\"\n)\n```\n\nYou can also use/initialize the pack directly.\n\n```python\nfrom llm_compiler_agent_pack.base import SelfRAGPack\n\nagent_pack = SelfRAGPack(\n model_path=model_path, retriever=retriever, verbose=True\n)\n```\n\nThe `run()` function is a light wrapper around `agent.chat()`.\n\n```python\nresponse = pack.run(\"Who won best Director in the 1972 Academy Awards?\")\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index packs self rag integration",
"version": "0.3.0",
"project_urls": null,
"split_keywords": [
"llm",
" self-rag",
" smart-retreiver"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "316b6d535a5b1c33f8b13a420db8de6c003e6b0d77b0e4e4692d5373762664b1",
"md5": "a747d84460be0e40bc3be268f083b81b",
"sha256": "97d8c547c9e3ecc7ef89055a438579cd02e406bc1ffe2ec87e0c62f8fcc7549f"
},
"downloads": -1,
"filename": "llama_index_packs_self_rag-0.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a747d84460be0e40bc3be268f083b81b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 5381,
"upload_time": "2024-11-17T22:42:54",
"upload_time_iso_8601": "2024-11-17T22:42:54.464838Z",
"url": "https://files.pythonhosted.org/packages/31/6b/6d535a5b1c33f8b13a420db8de6c003e6b0d77b0e4e4692d5373762664b1/llama_index_packs_self_rag-0.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6016d97913dca8f54439d1b61a2cfccc41d262d65a947322c8f1b1eae84124e6",
"md5": "91b4a26b6ee840371f75c06a8090ef68",
"sha256": "e83e4f49ae373a2f728650337ac4701ef83c4a00ba0b65a1a9648da97ffb31bb"
},
"downloads": -1,
"filename": "llama_index_packs_self_rag-0.3.0.tar.gz",
"has_sig": false,
"md5_digest": "91b4a26b6ee840371f75c06a8090ef68",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 5173,
"upload_time": "2024-11-17T22:42:56",
"upload_time_iso_8601": "2024-11-17T22:42:56.005890Z",
"url": "https://files.pythonhosted.org/packages/60/16/d97913dca8f54439d1b61a2cfccc41d262d65a947322c8f1b1eae84124e6/llama_index_packs_self_rag-0.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-17 22:42:56",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-self-rag"
}
JSON