So I used a text file mail.txt and fed it to the AI. Well, well! What do you say?
I'll let you read the whole file to find out who won - and why! Here is what the mail.txt file looked like: Here is the context: >> Here, in this thread, the context thing with respect to AI, >> anyone having any luck knowing what to do with that? It is >> mentioned 14 times in llamafile(1) but not how to actually >> set it up with your own data? > > One way to set context is via the http api which is > openai compatible. > > You create the queries using python and include your context > with the query. It may have the ability to remember context > so you only need it once, but running locally you can resend > the context each time. You can, but how much? So this is the context? You mean include it in the prompt? Then it is more easy to find in the llamafile(1) man page, it is probably -c N, --ctx-size N. If the unit is bytes that means 2048 bytes. Okay, that I can try it right now just by inserting all the data from a file into the query (prompt) and ask. And everyone can try that, actually. The question: In the above mail, what sentence is the most original? Here is what the AI said: The possible answers: 1. Here, in this thread, the context thing with respect to AI, anyone having any luck knowing what to do with that? 2. One way to set context is via the http api which is openai compatible. 3. You create the queries using python and include your context with the query. 4. It may have the ability to remember context so you only need it once, but running locally you can resend the context each time. 5. Then it is more easy to find in the llamafile(1) man page, it is probably -c N, --ctx-size N. 6. If the unit is bytes that means 2048 bytes. 7. Okay, that I can try it right now just by inserting all the data from a file into the query (prompt) and ask. 8. And everyone can try that, actually. The answer is 1. "Here, in this thread, the context thing with respect to AI, anyone having any luck knowing what to do with that?" This sentence is original because it starts the discussion about context in the thread. It is asking a question that is specific to the thread and is trying to find out if anyone has had any success with setting context for AI. It is not repeating or summarizing information that has already been stated and is the first mention of the topic in the thread. -- underground experts united https://dataswamp.org/~incal
