LlamaIndex
LlamaIndex can consume documents retrieved from an indexed ApertureDB
descriptor class. Use the same embedding model to encode stored documents and
the search query. This example reads a class whose descriptors have a text
property and converts the matches to LlamaIndex documents.
from aperturedb.CommonLibrary import create_connector
from aperturedb.Descriptors import Descriptors
from llama_index.core import Document, VectorStoreIndex
descriptors = Descriptors(create_connector())
descriptors.find_similar("Documents", query_embedding, 5, results={"list": ["text"]})
documents = [Document(text=row["text"]) for row in descriptors.response]
index = VectorStoreIndex.from_documents(documents)
answer = index.as_query_engine().query(question)
Configure LlamaIndex's embedding model and LLM before building the local index.
Graph database
Aperturedb can also be used as a PropertyGraph in LlamaIndex. There is an implementation in the github respository
An example to auto build a Knowledge Graph from a unstructured (text form) data using an LLM can be implemented as follows:
mkdir -p 'data/paul_graham/'
wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'
Ingesting the nodes
from llama_index.graph_stores.ApertureDB import ApertureDBGraphStore
from llama_index.core import SimpleDirectoryReader, PropertyGraphIndex
from llama_index.core.indices.property_graph import SchemaLLMPathExtractor
from llama_index.llms.openai import OpenAI
graph_store = ApertureDBGraphStore()
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
kg_extractor = SchemaLLMPathExtractor(
llm=OpenAI(model="gpt-3.5-turbo", temperature=0.0),
strict=True
)
index = PropertyGraphIndex.from_documents(
documents,
embed_kg_nodes=False,
kg_extractors=[kg_extractor],
property_graph_store=graph_store,
show_progress=True,
)
Querying the nodes.
from llama_index.graph_stores.ApertureDB import ApertureDBGraphStore
from llama_index.core import SimpleDirectoryReader, PropertyGraphIndex
from llama_index.core.indices.property_graph import SchemaLLMPathExtractor
from llama_index.llms.openai import OpenAI
graph_store = ApertureDBGraphStore()
kg_extractor = SchemaLLMPathExtractor(
llm=OpenAI(model="gpt-3.5-turbo", temperature=0.0),
strict=True,
)
index = PropertyGraphIndex.from_existing(
embed_kg_nodes=False,
kg_extractors=[kg_extractor],
property_graph_store=graph_store,
show_progress=True
)
def run_queries(query_engine):
query_str = [
"What has Paul graham worked on?",
"Who has Paul Graham worked with?"
]
for qs in query_str:
response = query_engine.query(qs)
print(f"{qs=}")
print(f"{response.response=}")
print("=" * 50)
run_queries(query_engine)