| Name | subquery JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | A package to generate subqueries and follow-up questions |
| upload_time | 2024-08-16 22:26:59 |
| maintainer | None |
| docs_url | None |
| author | andthattoo |
| requires_python | <4.0,>=3.9 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Subquery
`Subquery` generates subqueries and follow-up questions for a given input question.
Using the EXTREMELY SMOLL LLM [subquery-SmolLM](https://huggingface.co/andthattoo/subquery-SmolLM)
It's a finetuned model based on [nisten/Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base)
tiny as 150M (or 180M) parameters and thanks to wonderful work by Nisten and Huggingface's [SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M)
It can run both with `transformers` and `ollama` backends.
Ollama based GGUF model runs at 160 tps for 1 CPU.
yes.
It can do two things:
1. Generate subqueries for a given question.
2. Generate follow-up questions for a vague question.
This package wraps the model and provides a simple interface to generate subqueries and follow-up questions.
## Installation
You can install the package with
```
pip install subquery
```
## Usage
For Transformers
```python
from subquery import TransformersSubqueryGenerator
# Using the Transformers backend
generator = TransformersSubqueryGenerator()
result = generator.generate("What is this?")
print("Follow-up questions:", result.follow_up)
print("Subqueries:", result.subquery)
```
For Ollama
```python
from subquery import OllamaSubqueryGenerator
# Using the Ollama backend
generator = OllamaSubqueryGenerator()
result = generator.generate("Are the Indiana Harbor and Ship Canal and the Folsom South Canal in the same state?")
print("Follow-up questions:", result.follow_up)
print("Subqueries:", result.subquery)
```
Raw data
{
"_id": null,
"home_page": null,
"name": "subquery",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "andthattoo",
"author_email": "omer@firstbatch.xyz",
"download_url": "https://files.pythonhosted.org/packages/16/51/af2aaf6b4754a1e173248206863f0bb63c739bde37940ea1e32ae2a10c79/subquery-0.1.2.tar.gz",
"platform": null,
"description": "# Subquery\n\n`Subquery` generates subqueries and follow-up questions for a given input question.\nUsing the EXTREMELY SMOLL LLM [subquery-SmolLM](https://huggingface.co/andthattoo/subquery-SmolLM)\nIt's a finetuned model based on [nisten/Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base)\n\ntiny as 150M (or 180M) parameters and thanks to wonderful work by Nisten and Huggingface's [SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M)\n\nIt can run both with `transformers` and `ollama` backends.\nOllama based GGUF model runs at 160 tps for 1 CPU. \n\nyes.\n\nIt can do two things:\n\n1. Generate subqueries for a given question.\n\n2. Generate follow-up questions for a vague question.\n\n\nThis package wraps the model and provides a simple interface to generate subqueries and follow-up questions.\n\n## Installation\n\nYou can install the package with\n\n```\npip install subquery\n```\n\n## Usage\nFor Transformers\n```python\nfrom subquery import TransformersSubqueryGenerator\n\n# Using the Transformers backend\ngenerator = TransformersSubqueryGenerator()\nresult = generator.generate(\"What is this?\")\n\nprint(\"Follow-up questions:\", result.follow_up)\nprint(\"Subqueries:\", result.subquery)\n```\nFor Ollama\n```python\nfrom subquery import OllamaSubqueryGenerator\n# Using the Ollama backend\ngenerator = OllamaSubqueryGenerator()\nresult = generator.generate(\"Are the Indiana Harbor and Ship Canal and the Folsom South Canal in the same state?\")\n\nprint(\"Follow-up questions:\", result.follow_up)\nprint(\"Subqueries:\", result.subquery)\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A package to generate subqueries and follow-up questions",
"version": "0.1.2",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7f61225501d59fc5b0816b6be2a8bb01ce7c10e821503387de627d6db6e55bd0",
"md5": "85dcc4a4dc2988d9186e20c20ae21a5b",
"sha256": "fa5145bdc89cf9b3f4a5d50809753bf2a118ca648f29362c4e9062f4de2f8d56"
},
"downloads": -1,
"filename": "subquery-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "85dcc4a4dc2988d9186e20c20ae21a5b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 4265,
"upload_time": "2024-08-16T22:26:58",
"upload_time_iso_8601": "2024-08-16T22:26:58.497854Z",
"url": "https://files.pythonhosted.org/packages/7f/61/225501d59fc5b0816b6be2a8bb01ce7c10e821503387de627d6db6e55bd0/subquery-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1651af2aaf6b4754a1e173248206863f0bb63c739bde37940ea1e32ae2a10c79",
"md5": "c6cb61c6b6f54093fbedf608472ac80e",
"sha256": "5b89fc5bb4e76003734be9eed1847a34a39edc35317af2a3cff548d820e9f54c"
},
"downloads": -1,
"filename": "subquery-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "c6cb61c6b6f54093fbedf608472ac80e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 2895,
"upload_time": "2024-08-16T22:26:59",
"upload_time_iso_8601": "2024-08-16T22:26:59.895640Z",
"url": "https://files.pythonhosted.org/packages/16/51/af2aaf6b4754a1e173248206863f0bb63c739bde37940ea1e32ae2a10c79/subquery-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-16 22:26:59",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "subquery"
}
