From f35d015539d470aa9c402058e797be382e5eb2d2 Mon Sep 17 00:00:00 2001 From: Timothy <50641082+txmxthy@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:23:10 +1200 Subject: [PATCH] TEST for format and PR --- ingestion.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ingestion.py b/ingestion.py index 8c58a02..7431cae 100644 --- a/ingestion.py +++ b/ingestion.py @@ -7,7 +7,7 @@ from langchain.docstore.document import Document from langchain.embeddings import HuggingFaceInstructEmbeddings - from langchain.text_splitter import RecursiveCharacterTextSplitter +from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.vectorstores import Chroma from utilities.constants import (CHROMA_CFG, @@ -15,7 +15,7 @@ # Config @TODO, Load config from env chunk_size = 1000 -chunk_overlap = 200 +chunk_overlap = 200d embedding_model="hkunlp/instructor-xl"