Hi @nstylianides what are your other options when creating llama app? I had a try on NextJS template but could not reproduce you issue:

❯ npx create-llama@latest
✔ What is your project named? … my-app
✔ Which template would you like to use? › Agentic RAG (e.g. chat with docs)
✔ Which framework would you like to use? › NextJS
✔ Would you like to set up observability? › No
✔ Please provide your OpenAI API key (leave blank to skip): …
✔ Which data source would you like to use? › Use an example PDF
✔ Would you like to add another data source? › No
✔ Would you like to use LlamaParse (improved parser for RAG - requires API key)? … no / yes
✔ Would you like to use a vector database? › No, just store the data in the file system
✔ Would you like to build an agent using tools? If so, select the tools here, otherwise just press enter ›
✔ How would you like to proceed? › Generate code, install dependencies, and run the app (~2 min)

If you don't have index_store.json in the cache folder then i guess you had chosen the No data source option. Please make sure you had a file in the data folder.

Hi there. I have resolved the issue by using WSL env in my windows.

When using llamaindex index in windows i have concluded to the following:

1. Python example in Windows it works.
2. LlamaIndex.ts in windows it always fails to create the index_store.json
3. LlamaIndex.ts in windows WSL it works like a charm.

I am not sure what is the issue since error reporting is either missing or confusing. e.g. "contextWindow" could be easily confused with browser context windows.

THANK YOU FOR THIS LIBRARY for it can be a swiss knife in every dev toolset.
But, IMHO, it needs much better documentation, reference and howto based on cases.

Is there an official Course on how to better utilize the Llmaindex library?