github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-09 22:45:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/from documents (#3919)

Browse Source 
Co-authored-by: Gabriel Altay <gabriel.altay@gmail.com>
This commit is contained in:
Harrison Chase 2023-05-01 20:28:14 -07:00 committed by GitHub
parent e7e29f9937
commit 05170b6764
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
langchain/indexes/vectorstore.py
View File

@ -9,6 +9,7 @@ from langchain.embeddings.base import Embeddings
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.llms.base import BaseLLM
from langchain.llms.openai import OpenAI
from langchain.schemas import Document
from langchain.text_splitter import RecursiveCharacterTextSplitter, TextSplitter
from langchain.vectorstores.base import VectorStore
from langchain.vectorstores.chroma import Chroma
@ -67,7 +68,11 @@ class VectorstoreIndexCreator(BaseModel):
docs = []
for loader in loaders:
docs.extend(loader.load())
sub_docs = self.text_splitter.split_documents(docs)
return self.from_documents(docs)
def from_documents(self, documents: List[Document]) -> VectorStoreIndexWrapper:
"""Create a vectorstore index from documents."""
sub_docs = self.text_splitter.split_documents(documents)
vectorstore = self.vectorstore_cls.from_documents(
sub_docs, self.embedding, **self.vectorstore_kwargs
)