llama-index packs deeplake_deepmemory_retriever integration
Project description
DeepLake DeepMemory Pack
This LlamaPack inserts your data into deeplake and insantiates a deepmemory retriever, which will use deepmemory during runtime to increase RAG's retrieval accuracy (recall).
CLI Usage
You can download llamapacks directly using llamaindex-cli
, which comes installed with the llama-index
python package:
llamaindex-cli download-llamapack DeepMemoryRetrieverPack --download-dir ./deepmemory_pack
You can then inspect the files at ./deepmemory_pack
and use them as a template for your own project!
Code Usage
You can download the pack to a ./deepmemory_pack
directory:
from llama_hub.llama_pack import download_llama_pack
# download and install dependencies
DeepMemoryRetriever = download_llama_pack(
"DeepMemoryRetrieverPack", "./deepmemory_pack"
)
From here, you can use the pack, or inspect and modify the pack in ./deepmemory_pack
.
Then, you can set up the pack like so:
# setup pack arguments
from llama_index.core.vector_stores.types import MetadataInfo, VectorStoreInfo
nodes = [...]
# create the pack
deepmemory_pack = DeepMemoryRetriever(
dataset_path="llama_index",
overwrite=False,
nodes=nodes,
)
The run()
function is a light wrapper around query_engine.query()
.
response = deepmemory_pack.run("Tell me a bout a Music celebritiy.")
You can also use modules individually.
# use the retreiver
retriever = deepmemory_pack.retriever
nodes = retriever.retrieve("query_str")
# use the query engine
query_engine = deepmemory_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_deeplake_deepmemory_retriever-0.1.2.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9faefbaf983533ee083df04044def6011ff7b1b20501679c02c5a25eb86ca753 |
|
MD5 | a744e6030bc9960b4bf1cf2f1936684c |
|
BLAKE2b-256 | 46cccd5b77a4ec8aced079c216f0e302e8a2f2872ecce66c2f68ed4899635103 |
Hashes for llama_index_packs_deeplake_deepmemory_retriever-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6c44ab82f8629500992bbf1999b8b07cb46e30c5bb8119412dd69c9edaf37d1f |
|
MD5 | 9c1a89233a347c8777653db46219cc00 |
|
BLAKE2b-256 | 5596e8f22b0b000c614edec2ec7ef02bc2bbf4a4ccbe8887ba5d5ccf30e9841d |