17
edits
Changes
From Gramps
→How does it all work? - updating colours
The {{man label|Chat With Tree}} Gramplet is built in such a way that it sends off a list of "tool names" to the LLM, and based on the message sent, will determine what tools it needs to respond. The tools in the respond execute an interaction with your Gramps database, and the results are then send back to the LLM again, so that the LLM can process the information for an answer.
This interaction between tool calling, thinking of the model, is shown in the ```<span style="color: #000; background-color: #fce8b2">yellow balloons```</span>.
You will find out that certain models are way better, or smarter, in this tool calling task then other models. As an example, try asking the model a very difficult question. Example:
<blockquote>
<span style="color: black; background-color: #CECdcf8c6;">
From the start person of this genealogy tree, can you tell me all names going back in time by following the mother, then the father, then the mother, then the father, and so on, until you do not find a person anymore? Name all these people with their birth dates, and based on the birth locations, and occupations of these people, based on your own knowledge of these places, can you tell me the most likely family heritage we are looking into?
</span>
