Skip to main content

llama-index packs auto_merging_retriever integration

Project description

Auto Merging Retriever Pack

This LlamaPack provides an example of our auto-merging retriever.

This specific template shows the e2e process of building this. It loads a document, builds a hierarchical node graph (with bigger parent nodes and smaller child nodes).

Check out the notebook here.

CLI Usage

You can download llamapacks directly using llamaindex-cli, which comes installed with the llama-index python package:

llamaindex-cli download-llamapack AutoMergingRetrieverPack --download-dir ./auto_merging_retriever_pack

You can then inspect the files at ./auto_merging_retriever_pack and use them as a template for your own project.

Code Usage

You can download the pack to a the ./auto_merging_retriever_pack directory:

from llama_index.core.llama_pack import download_llama_pack

# download and install dependencies
AutoMergingRetrieverPack = download_llama_pack(
    "AutoMergingRetrieverPack", "./auto_merging_retriever_pack"
)

From here, you can use the pack, or inspect and modify the pack in ./auto_merging_retriever_pack.

Then, you can set up the pack like so:

# create the pack
# get documents from any data loader
auto_merging_retriever_pack = AutoMergingRetrieverPack(
    documents,
)

The run() function is a light wrapper around query_engine.query().

response = auto_merging_retriever_pack.run(
    "Tell me about what the author did growing up."
)

You can also use modules individually.

# get the node parser
node_parser = auto_merging_retriever_pack.node_parser

# get the retriever
retriever = auto_merging_retriever_pack.retriever

# get the query engine
query_engine = auto_merging_retriever_pack.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

File details

Details for the file llama_index_packs_auto_merging_retriever-0.4.0.tar.gz.

File metadata

File hashes

Hashes for llama_index_packs_auto_merging_retriever-0.4.0.tar.gz
Algorithm Hash digest
SHA256 80cb293b795ab2e0cb60d2f31542d8dfc7b3d874d8e044fc071e0a593f9b329d
MD5 a8375623fc2b3e08eee2fd5a6c99795c
BLAKE2b-256 158cd4318b6ee6d9c60cf9af6e5dd278be4334c901bcd3479516589db60769e3

See more details on using hashes here.

File details

Details for the file llama_index_packs_auto_merging_retriever-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_packs_auto_merging_retriever-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4d3c3b42bf7a65abeb2b5b7af72c0b10874b7e0e0db96ae81f9f46ce317c27b6
MD5 ccf37d7001269fca6feda26750f28854
BLAKE2b-256 c603ed38270c10ab9d4ce970f6ed38a313ff4d7c854a0f84e0ad2070eb9e94c6

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page