I’m trying to follow along to this tutorial https://www.youtube.com/watch?v=E2shqsYwxck (Building Corrective RAG from scratch with open-source, local LLMs) with source code here: https://github.com/langchain-ai/langgraph/blob/main/examples/rag/langgraph_crag_local.ipynb. I am getting the following error at the index section (Code followed by error output in image).
# Load
url = "https://lilianweng.github.io/posts/2023-06-23-agent/"
loader = WebBaseLoader(url)
docs = loader.load()
# Split
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
chunk_size=500, chunk_overlap=100
)
all_splits = text_splitter.split_documents(docs)
# Embed and index
if run_local == "Yes":
embedding = GPT4AllEmbeddings()
else:
embedding = MistralAIEmbeddings(mistral_api_key=mistral_api_key)
# Index
vectorstore = Chroma.from_documents(
documents=all_splits,
collection_name="rag-chroma",
embedding=embedding,
)
retriever = vectorstore.as_retriever()
I believe this is a Windows and Chroma package compatibility issue. I’ve tried using the python Locale package to check what culture my computer is using. It seems the python environment is fine but Chroma is not recognizing it….any advice?