mirror of
https://github.com/langchain-ai/learning-langchain.git
synced 2026-07-01 16:06:32 -04:00
mayo
20 lines
592 B
Python
20 lines
592 B
Python
from langchain_community.document_loaders import TextLoader
|
|
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
|
from langchain_openai import OpenAIEmbeddings
|
|
|
|
# Load the document
|
|
loader = TextLoader("./test.txt")
|
|
doc = loader.load()
|
|
|
|
# Split the document
|
|
splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
|
chunks = splitter.split_documents(doc)
|
|
|
|
# Generate embeddings
|
|
embeddings_model = OpenAIEmbeddings(model="text-embedding-3-small")
|
|
embeddings = embeddings_model.embed_documents(
|
|
[chunk.page_content for chunk in chunks]
|
|
)
|
|
|
|
print(embeddings)
|