Having completed the Preparedness steps, I asked ChatGPT the following question:<\/p>\n
\u201cI have a collection of 2993 mementos which has an Index containing a Reference No and Description for each item. I want to create a RAG interrogation capability on the Reference No and Description information. The Index file is named \u2018Memento Collection Index for AI\u2019 and it is located in my laptop at C:\\Users\\pwils\\Documents\\AI. The first two rows of the Index file contain descriptive information about the file and can be ignored. The 3rd row contains the headers for each of the Index fields. There are fourteen fields in all with the first two titled \u2018Reference No\u2019 and \u2018Description\u2019. What\u2019s the first thing I should do to create the RAG interrogation capability?\u201d<\/p>\n
ChatGPT responded with advice to remove the first two rows in the spreadsheet, and to convert it to a csv file. In subsequent exchanges, ChatGPT suggested the following changes and additions to the csv file which would enable the AI to provide more insightful answers:<\/p>\n
At this point I decided that, for this first stage in this journey, I would simply stick with the very first suggestion \u2013 to create a new column called \u2018Item Label\u2019 combining the Reference No and the Description separated by a hyphen. Once I have something working, I can return to these other sophistications.<\/p>\n
In the course of this extended exchange, ChatGPT also offered to provide \u201cthe exact 40-line Python script that will turn your spreadsheet into a working RAG search system for the 2993 mementos\u201d. I accepted and in the course of the subsequent interchange was offered an easier approach which involves acquiring a desktop RAG tool called AnythingLLM which would run locally and require no programming. The latter sounded exactly what I needed and I set about downloading and installing it.<\/p>\n","protected":false},"excerpt":{"rendered":"
Having completed the Preparedness steps, I asked ChatGPT the following question: \u201cI have a collection of 2993 mementos which has an Index containing a Reference No and Description for each item. I want to create a RAG interrogation capability on … Continue reading