diff --git a/ingest.py b/ingest.py index 148a8a5f4..9175afba4 100644 --- a/ingest.py +++ b/ingest.py @@ -9,7 +9,7 @@ def ingest_docs(): """Get documents from web pages.""" - loader = ReadTheDocsLoader("langchain.readthedocs.io/en/latest/") + loader = ReadTheDocsLoader("api.python.langchain.com/en/latest/") raw_documents = loader.load() text_splitter = RecursiveCharacterTextSplitter( chunk_size=1000, diff --git a/ingest.sh b/ingest.sh index 73b75a899..3b63a31dd 100755 --- a/ingest.sh +++ b/ingest.sh @@ -2,5 +2,5 @@ # This involves scraping the data from the web and then cleaning up and putting in Weaviate. # Error if any command fails set -e -wget -r -A.html https://langchain.readthedocs.io/en/latest/ +wget -r -A.html https://api.python.langchain.com/en/latest/ python3 ingest.py