llama-index packs sub_question_weaviate integration
Project description
Sub Question Query Engine
This LlamaPack inserts your data into Weaviate and uses the Sub-Question Query Engine for your RAG application.
CLI Usage
You can download llamapacks directly using llamaindex-cli
, which comes installed with the llama-index
python package:
llamaindex-cli download-llamapack WeaviateSubQuestionPack --download-dir ./weaviate_pack
You can then inspect the files at ./weaviate_pack
and use them as a template for your own project.
Code Usage
You can download the pack to a the ./weaviate_pack
directory:
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
WeaviateSubQuestionPack = download_llama_pack(
"WeaviateSubQuestionPack", "./weaviate_pack"
)
From here, you can use the pack, or inspect and modify the pack in ./weaviate_pack
.
Then, you can set up the pack like so:
# setup pack arguments
from llama_index.core.vector_stores import MetadataInfo, VectorStoreInfo
vector_store_info = VectorStoreInfo(
content_info="brief biography of celebrities",
metadata_info=[
MetadataInfo(
name="category",
type="str",
description=(
"Category of the celebrity, one of [Sports Entertainment, Business, Music]"
),
),
],
)
import weaviate
client = weaviate.Client()
nodes = [...]
# create the pack
weaviate_pack = WeaviateSubQuestion(
collection_name="test",
vector_store_info=vector_store_index,
nodes=nodes,
client=client,
)
The run()
function is a light wrapper around query_engine.query()
.
response = weaviate_pack.run("Tell me a bout a Music celebritiy.")
You can also use modules individually.
# use the retriever
retriever = weaviate_pack.retriever
nodes = retriever.retrieve("query_str")
# use the query engine
query_engine = weaviate_pack.query_engine
response = query_engine.query("query_str")
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_sub_question_weaviate-0.2.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | a7651ef7828fea197a155a0e55b78c240ca35676b74f5688aee52c8c1f9a8097 |
|
MD5 | f317599b12f08c2ed63c90c16e656ec1 |
|
BLAKE2b-256 | 3c6195779c28241c64694e3d26b3b65902562a7f79fa1ffa69f762344a6a5d78 |
Hashes for llama_index_packs_sub_question_weaviate-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 94aab4820d4eb2c3ffdfea3719677ff4374da7ae50e15ba046c93e0dac0a7f00 |
|
MD5 | 74bd3fdc1a86f8098f273e4e3d7ebca8 |
|
BLAKE2b-256 | 5be11f16008f5d2e908c3238b2e8ccca129c4d1797d3f0b11d4632c6c258764f |