# Vanna AI LLamaPack
Vanna AI is an open-source RAG framework for SQL generation. It works in two steps:
1. Train a RAG model on your data
2. Ask questions (use reference corpus to generate SQL queries that can run on your db).
Check out the [Github project](https://github.com/vanna-ai/vanna) and the [docs](https://vanna.ai/docs/) for more details.
This LlamaPack creates a simple `VannaQueryEngine` with vanna, ChromaDB and OpenAI, and allows you to train and ask questions over a SQL database.
## CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack VannaPack --download-dir ./vanna_pack
```
You can then inspect the files at `./vanna_pack` and use them as a template for your own project!
## Code Usage
You can download the pack to a `./vanna_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
VannaPack = download_llama_pack("VannaPack", "./vanna_pack")
```
From here, you can use the pack, or inspect and modify the pack in `./vanna_pack`.
Then, you can set up the pack like so:
```python
pack = VannaPack(
openai_api_key="<openai_api_key>",
sql_db_url="chinook.db",
openai_model="gpt-3.5-turbo",
)
```
The `run()` function is a light wrapper around `llm.complete()`.
```python
response = pack.run("List some sample albums")
```
You can also use modules individually.
```python
query_engine = pack.get_modules()["vanna_query_engine"]
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-vanna",
"maintainer": "jerryjliu",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "ai, sql, text-to-sql, vanna",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/22/f1/06637545908fa7f45756b9987a75c45929bf5b755c1ff1bfbd64fc645a8c/llama_index_packs_vanna-0.3.0.tar.gz",
"platform": null,
"description": "# Vanna AI LLamaPack\n\nVanna AI is an open-source RAG framework for SQL generation. It works in two steps:\n\n1. Train a RAG model on your data\n2. Ask questions (use reference corpus to generate SQL queries that can run on your db).\n\nCheck out the [Github project](https://github.com/vanna-ai/vanna) and the [docs](https://vanna.ai/docs/) for more details.\n\nThis LlamaPack creates a simple `VannaQueryEngine` with vanna, ChromaDB and OpenAI, and allows you to train and ask questions over a SQL database.\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 VannaPack --download-dir ./vanna_pack\n```\n\nYou can then inspect the files at `./vanna_pack` and use them as a template for your own project!\n\n## Code Usage\n\nYou can download the pack to a `./vanna_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nVannaPack = download_llama_pack(\"VannaPack\", \"./vanna_pack\")\n```\n\nFrom here, you can use the pack, or inspect and modify the pack in `./vanna_pack`.\n\nThen, you can set up the pack like so:\n\n```python\npack = VannaPack(\n openai_api_key=\"<openai_api_key>\",\n sql_db_url=\"chinook.db\",\n openai_model=\"gpt-3.5-turbo\",\n)\n```\n\nThe `run()` function is a light wrapper around `llm.complete()`.\n\n```python\nresponse = pack.run(\"List some sample albums\")\n```\n\nYou can also use modules individually.\n\n```python\nquery_engine = pack.get_modules()[\"vanna_query_engine\"]\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index packs vanna integration",
"version": "0.3.0",
"project_urls": null,
"split_keywords": [
"ai",
" sql",
" text-to-sql",
" vanna"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a84d00065668758f02beb53b932a02e63d43284a76b9385a95d8cb5d007c97cc",
"md5": "f4e88a7b073f89e69340c713df22f0d2",
"sha256": "316ffe9e3b0223d398d7f06c4e1893c0076eb2ad3c48ec7fe271998e79b94c0f"
},
"downloads": -1,
"filename": "llama_index_packs_vanna-0.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f4e88a7b073f89e69340c713df22f0d2",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 3603,
"upload_time": "2024-11-17T22:42:23",
"upload_time_iso_8601": "2024-11-17T22:42:23.333689Z",
"url": "https://files.pythonhosted.org/packages/a8/4d/00065668758f02beb53b932a02e63d43284a76b9385a95d8cb5d007c97cc/llama_index_packs_vanna-0.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "22f106637545908fa7f45756b9987a75c45929bf5b755c1ff1bfbd64fc645a8c",
"md5": "b2faaad0d057f27b1985bf62a9a501b1",
"sha256": "ef1d14c527ad7cf7423817c09ad336e0cbb8f174e056a72337f08ac2e5fa1995"
},
"downloads": -1,
"filename": "llama_index_packs_vanna-0.3.0.tar.gz",
"has_sig": false,
"md5_digest": "b2faaad0d057f27b1985bf62a9a501b1",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 3371,
"upload_time": "2024-11-17T22:42:24",
"upload_time_iso_8601": "2024-11-17T22:42:24.162825Z",
"url": "https://files.pythonhosted.org/packages/22/f1/06637545908fa7f45756b9987a75c45929bf5b755c1ff1bfbd64fc645a8c/llama_index_packs_vanna-0.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-17 22:42:24",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-vanna"
}
JSON