# Self-Discover LlamaPack
This LlamaPack implements [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://arxiv.org/abs/2402.03620) paper.
It has two stages for the given task:
1. STAGE-1:
a. SELECT: Selects subset of reasoning Modules.
b. ADAPT: Adapts selected reasoning modules to the task.
c. IMPLEMENT: It gives reasoning structure for the task.
2. STAGE-2: Uses the generated reasoning structure for the task to generate an answer.
The implementation is inspired from the [codebase](https://github.com/catid/self-discover)
## CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack SelfDiscoverPack --download-dir ./self_discover_pack
```
You can then inspect the files at `./self_discover_pack` and use them as a template for your own project!
## Code Usage
There are two ways using LlamaPack:
1. Do `download_llama_pack` to load the Self-Discover LlamaPack.
2. Directly use `SelfDiscoverPack`
### Using `download_llama_pack`
```python
from llama_index.llama_pack import download_llama_pack
# download and install dependencies
SelfDiscoverPack = download_llama_pack(
"SelfDiscoverPack", "./self_discover_pack"
)
self_discover_pack = SelfDiscoverPack(verbose=True, llm=llm)
```
### Directly use `SelfRAGPack`
```python
from llama_index.packs.self_discover import SelfDiscoverPack
self_discover_pack = SelfRAGPack(llm=llm, verbose=True)
```
The run() function serves as a concise wrapper that implements the logic outlined in the "self-discover" paper, applying it to a sample task as illustrated below.
`Emma needs to prepare 50 invitations for her upcoming birthday party. She can handwrite 10 invitations in an hour. After working for 2 hours, she takes a break for 30 minutes. If she resumes writing at the same pace, how long will it take her to complete all 50 invitations?`
```python
output = pack.run("<task>")
```
Raw data
{
"_id": null,
"home_page": "",
"name": "llama-index-packs-self-discover",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.1,<4.0",
"maintainer_email": "",
"keywords": "discover,self,self-discover,task",
"author": "Ravi Theja",
"author_email": "ravi03071991@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/08/df/66996350dca26db88edd678e6371c9107bd108b1d35a3f23958299864e22/llama_index_packs_self_discover-0.1.1.tar.gz",
"platform": null,
"description": "# Self-Discover LlamaPack\n\nThis LlamaPack implements [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://arxiv.org/abs/2402.03620) paper.\n\nIt has two stages for the given task:\n\n1. STAGE-1:\n\n a. SELECT: Selects subset of reasoning Modules.\n\n b. ADAPT: Adapts selected reasoning modules to the task.\n\n c. IMPLEMENT: It gives reasoning structure for the task.\n\n2. STAGE-2: Uses the generated reasoning structure for the task to generate an answer.\n\nThe implementation is inspired from the [codebase](https://github.com/catid/self-discover)\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 SelfDiscoverPack --download-dir ./self_discover_pack\n```\n\nYou can then inspect the files at `./self_discover_pack` and use them as a template for your own project!\n\n## Code Usage\n\nThere are two ways using LlamaPack:\n\n1. Do `download_llama_pack` to load the Self-Discover LlamaPack.\n2. Directly use `SelfDiscoverPack`\n\n### Using `download_llama_pack`\n\n```python\nfrom llama_index.llama_pack import download_llama_pack\n\n# download and install dependencies\nSelfDiscoverPack = download_llama_pack(\n \"SelfDiscoverPack\", \"./self_discover_pack\"\n)\n\nself_discover_pack = SelfDiscoverPack(verbose=True, llm=llm)\n```\n\n### Directly use `SelfRAGPack`\n\n```python\nfrom llama_index.packs.self_discover import SelfDiscoverPack\n\nself_discover_pack = SelfRAGPack(llm=llm, verbose=True)\n```\n\nThe run() function serves as a concise wrapper that implements the logic outlined in the \"self-discover\" paper, applying it to a sample task as illustrated below.\n\n`Emma needs to prepare 50 invitations for her upcoming birthday party. She can handwrite 10 invitations in an hour. After working for 2 hours, she takes a break for 30 minutes. If she resumes writing at the same pace, how long will it take her to complete all 50 invitations?`\n\n```python\noutput = pack.run(\"<task>\")\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index packs self_discover paper implementation",
"version": "0.1.1",
"project_urls": null,
"split_keywords": [
"discover",
"self",
"self-discover",
"task"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "55b6fd7d4c42c79f3037f6ae16486f71888c882c9398f3a742d540217b18f609",
"md5": "6110e552be4cae6523389459e17caf11",
"sha256": "042f96835ffd106a24aae0f62563d8b3fc2d5ad6ead5f4c1e1342b6722c8d8af"
},
"downloads": -1,
"filename": "llama_index_packs_self_discover-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6110e552be4cae6523389459e17caf11",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.1,<4.0",
"size": 5847,
"upload_time": "2024-02-22T01:35:55",
"upload_time_iso_8601": "2024-02-22T01:35:55.139688Z",
"url": "https://files.pythonhosted.org/packages/55/b6/fd7d4c42c79f3037f6ae16486f71888c882c9398f3a742d540217b18f609/llama_index_packs_self_discover-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "08df66996350dca26db88edd678e6371c9107bd108b1d35a3f23958299864e22",
"md5": "b39e247837cf8f9af0f5d38c3145c44d",
"sha256": "7eadd35f4db327c3c8b157b1fda2d6cb74e7a8af93ba08015f59a6c99bb13e1b"
},
"downloads": -1,
"filename": "llama_index_packs_self_discover-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "b39e247837cf8f9af0f5d38c3145c44d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.1,<4.0",
"size": 5524,
"upload_time": "2024-02-22T01:35:56",
"upload_time_iso_8601": "2024-02-22T01:35:56.547174Z",
"url": "https://files.pythonhosted.org/packages/08/df/66996350dca26db88edd678e6371c9107bd108b1d35a3f23958299864e22/llama_index_packs_self_discover-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-22 01:35:56",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-self-discover"
}