mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
24 lines
671 B
Python
24 lines
671 B
Python
from pathlib import Path
|
|
|
|
from langchain_community.document_loaders import TextLoader
|
|
from langchain_community.vectorstores import Neo4jVector
|
|
from langchain_openai import OpenAIEmbeddings
|
|
from langchain_text_splitters import TokenTextSplitter
|
|
|
|
txt_path = Path(__file__).parent / "dune.txt"
|
|
|
|
# Load the text file
|
|
loader = TextLoader(str(txt_path))
|
|
raw_documents = loader.load()
|
|
|
|
# Define chunking strategy
|
|
splitter = TokenTextSplitter(chunk_size=512, chunk_overlap=24)
|
|
documents = splitter.split_documents(raw_documents)
|
|
|
|
# Calculate embedding values and store them in the graph
|
|
Neo4jVector.from_documents(
|
|
documents,
|
|
OpenAIEmbeddings(),
|
|
index_name="dune",
|
|
)
|