llama-index packs neo4j_query_engine integration
Project description
Neo4j Query Engine Pack
This LlamaPack creates a Neo4j query engine, and executes its query
function. This pack offers the option of creating multiple types of query engines, namely:
- Knowledge graph vector-based entity retrieval (default if no query engine type option is provided)
- Knowledge graph keyword-based entity retrieval
- Knowledge graph hybrid entity retrieval
- Raw vector index retrieval
- Custom combo query engine (vector similarity + KG entity retrieval)
- KnowledgeGraphQueryEngine
- KnowledgeGraphRAGRetriever
CLI Usage
You can download llamapacks directly using llamaindex-cli
, which comes installed with the llama-index
python package:
llamaindex-cli download-llamapack Neo4jQueryEnginePack --download-dir ./neo4j_pack
You can then inspect the files at ./neo4j_pack
and use them as a template for your own project!
Code Usage
You can download the pack to a ./neo4j_pack
directory:
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
Neo4jQueryEnginePack = download_llama_pack(
"Neo4jQueryEnginePack", "./neo4j_pack"
)
From here, you can use the pack, or inspect and modify the pack in ./neo4j_pack
.
Then, you can set up the pack like so:
# Load the docs (example of Paleo diet from Wikipedia)
from llama_index import download_loader
WikipediaReader = download_loader("WikipediaReader")
loader = WikipediaReader()
docs = loader.load_data(pages=["Paleolithic diet"], auto_suggest=False)
print(f"Loaded {len(docs)} documents")
# get Neo4j credentials (assume it's stored in credentials.json)
with open("credentials.json") as f:
neo4j_connection_params = json.load(f)
username = neo4j_connection_params["username"]
password = neo4j_connection_params["password"]
url = neo4j_connection_params["url"]
database = neo4j_connection_params["database"]
# create the pack
neo4j_pack = Neo4jQueryEnginePack(
username=username, password=password, url=url, database=database, docs=docs
)
Optionally, you can pass in the query_engine_type
from Neo4jQueryEngineType
to construct Neo4jQueryEnginePack
. If query_engine_type
is not defined, it defaults to Knowledge Graph vector based entity retrieval.
from llama_index.packs.neo4j_query_engine.base import Neo4jQueryEngineType
# create the pack
neo4j_pack = Neo4jQueryEnginePack(
username=username,
password=password,
url=url,
database=database,
docs=docs,
query_engine_type=Neo4jQueryEngineType.KG_HYBRID,
)
Neo4jQueryEnginePack
is a enum defined as follows:
class Neo4jQueryEngineType(str, Enum):
"""Neo4j query engine type"""
KG_KEYWORD = "keyword"
KG_HYBRID = "hybrid"
RAW_VECTOR = "vector"
RAW_VECTOR_KG_COMBO = "vector_kg"
KG_QE = "KnowledgeGraphQueryEngine"
KG_RAG_RETRIEVER = "KnowledgeGraphRAGRetriever"
The run()
function is a light wrapper around query_engine.query()
, see a sample query below.
response = neo4j_pack.run("Tell me about the benefits of paleo diet.")
You can also use modules individually.
# call the query_engine.query()
query_engine = neo4j_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_neo4j_query_engine-0.1.3.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6056439961324e4f2e7840744e492135fe7a4ee720a233f456a26222485f001d |
|
MD5 | 034f08270071e1b2cfff0af785775532 |
|
BLAKE2b-256 | 5fd83dddfef71b50a2a4c81114df7c86815580b17ba04f3b167d67ed12cdefd8 |
Hashes for llama_index_packs_neo4j_query_engine-0.1.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1491a107cb0d48b301306a6a47fa387a04c9c08fb1db889f7fc0c1f425ef925e |
|
MD5 | b8b6ff842719db66369fcebf191d4660 |
|
BLAKE2b-256 | 35e23c6e7e31f053121e575cbaa193977fa3fd1e956eeebb9960c9c0ed487c4b |