Jake/dungeon_masters_vault
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test message

Browse Source
This commit is contained in:
Jake Pullen
2026-05-18 15:20:09 +01:00
parent d0cd215210
commit 2781c2e89e
1 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
idea.txt
+9 -7
View File
@@ -1,13 +1,15 @@
the idea here is to drop the vectors and semantic search, in favour of optimised knowledge base and llm tool calling. the idea here is to drop the vectors and semantic search, in favour of optimised knowledge base and llm tool calling.
the current implementation loads the closest semantic chunks based on semantics. the current implementation loads the closest semantic chunks based on semantics.
what if. what if.
we ingest and enrich with a focus on tagging entities (knowing our qa will be around entities) we ingest and enrich with a focus on tagging entities (knowing our qa will be around entities)
we transform, grouping all entity related infornation together we transform, grouping all entity related infornation together
we load that grouped information out into toon files. we load that grouped information out into toon files.
we give the agent a tool to load 1 or more toon file based on entites in the question. we give the agent a tool to load 1 or more toon file based on entites in the question.
the context window for modern llm is big enough to fit the entire campain notes, but we still risk poison or confusion if we fill the context window with irrelevant notes. the context window for modern llm is big enough to fit the entire campain notes, but we still risk poison or confusion if we fill the context window with irrelevant notes.
also wonder if we should give the full file at enrichment rather than chunks? worth experimenting... also wonder if we should give the full file at enrichment rather than chunks? worth experimenting...
test message pls ignore