bwanab/rag_ollama ? reverse-engineered prompt
Reverse engineered prompt
Build me a simple local question answering app that uses Ollama and LlamaIndex to chat with a text file using retrieval augmented generation.
I want to be able to run one Python script, have it load the sample text in the data folder, store embeddings in a local vector database, and then let me ask questions in the terminal after it finishes indexing. Please make it easy to set up with the requirements file, and keep it working with a local Ollama model so it does not need a cloud API.
Use the provided example text as the default source, and make the prompt feel like a small demo I can run right away. If anything needs a current setup detail, look up the latest docs online and keep the code simple and readable.
Are you gonna build this?
make sure you review the code using coderabbit