llama-index packs vanna integration
Project description
Vanna AI LLamaPack
Vanna AI is an open-source RAG framework for SQL generation. It works in two steps:
- Train a RAG model on your data
- Ask questions (use reference corpus to generate SQL queries that can run on your db).
Check out the Github project and the 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:
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:
from llama_index.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:
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()
.
response = pack.run("List some sample albums")
You can also use modules individually.
query_engine = pack.get_modules()["vanna_query_engine"]
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for llama_index_packs_vanna-0.1.2.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | f9093701670ab816bcacf3cac3520a528f2fa4f995a743d23ee3c4435df15f4e |
|
MD5 | afa293b6def36a6a1b7e424096b3dfe6 |
|
BLAKE2b-256 | 6291db610d844944dcdaae48929111abe622ee645b7550c048c03e5a805ad4a1 |
Hashes for llama_index_packs_vanna-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7cfc04dc89b78258e67b3c071e5e2f0b5b10e06aacbbe0e993345d8bcf2b37fa |
|
MD5 | 99495163cf4cee761f47d490b984ef9b |
|
BLAKE2b-256 | 06a7749b0c5e2d33c0eea54b65cc16a4824de02550e3d5b35290f048ff381e02 |