adding phrase matching to ebook rag engen #36

Merged
Richie merged 36 commits from feature/adding-phrase-matching-to-ebook-rag-engen into main 2026-07-25 10:17:10 -04:00
3 changed files with 103 additions and 2 deletions
Showing only changes of commit 8e2ca365c2 - Show all commits
@@ -27,4 +27,5 @@ tokens = [
"will", "will",
"with", "with",
"would", "would",
"did",
] ]
@@ -1,5 +1,27 @@
tokens = [ tokens = [
"a", "a",
"an", "an",
"did",
"didn't",
"he",
"here",
"how",
"i",
"it",
"she",
"that",
"the", "the",
"there",
"they",
"this",
"we",
"what",
"when",
"where",
"which",
"who",
"whom",
"whose",
"why",
"you",
] ]
@@ -1,18 +1,71 @@
phrases = [ phrases = [
"ended up", "a little",
"had a",
"across the", "across the",
"and she",
"anyone in", "anyone in",
"are you", "are you",
"around him", "around him",
"around the", "around the",
"as much", "as much",
"as soon", "as soon",
"at all",
"at least",
"before the", "before the",
"behind him", "behind him",
"between the", "between the",
"but she",
"could not",
"did he",
"did i",
"did it",
"did not believe",
"did not care",
"did not even",
"did not know what",
"did not know",
"did not like",
"did not look",
"did not mean",
"did not move",
"did not need",
"did not see",
"did not seem",
"did not think",
"did not understand",
"did not want",
"did not",
"did she",
"did so",
"did that",
"did the",
"did they",
"did what",
"did you", "did you",
"didn't answer",
"didn't care",
"didn't even",
"didn't expect",
"didn't feel",
"didn't get",
"didn't i",
"didn't know",
"didn't like",
"didn't look",
"didn't make",
"didn't mean",
"didn't need",
"didn't really",
"didn't say",
"didn't see",
"didn't seem",
"didn't think",
"didn't want",
"didn't you",
"end up", "end up",
"ended up",
"had a",
"had been",
"have been",
"he asked", "he asked",
"he concluded", "he concluded",
"he continued", "he continued",
@@ -49,26 +102,34 @@ phrases = [
"how many", "how many",
"i am", "i am",
"i don't", "i don't",
"i said",
"i was", "i was",
"i wouldn't", "i wouldn't",
"i'm not", "i'm not",
"if he",
"if they",
"is in", "is in",
"is not", "is not",
"is that", "is that",
"is the", "is the",
"it had", "it had",
"it had", "it had",
"it is",
"it was", "it was",
"it wasn't", "it wasn't",
"it wasn't", "it wasn't",
"no one",
"of course", "of course",
"of force", "of force",
"of it",
"of magic", "of magic",
"of marines", "of marines",
"of power", "of power",
"of those", "of those",
"old man", "old man",
"older man", "older man",
"one of",
"out of",
"set up", "set up",
"she admitted", "she admitted",
"she asked", "she asked",
@@ -84,7 +145,22 @@ phrases = [
"tell you", "tell you",
"that had", "that had",
"that is", "that is",
"that she",
"that was", "that was",
"the dark",
"the door",
"the first",
"the last",
"the man",
"the one",
"the only",
"the other",
"the rest",
"the room",
"the same",
"the two",
"the way",
"the world",
"there are", "there are",
"there was", "there was",
"there were", "there were",
@@ -98,6 +174,7 @@ phrases = [
"through his", "through his",
"through the", "through the",
"to find", "to find",
"to get",
"to keep", "to keep",
"to stay", "to stay",
"to stop", "to stop",
@@ -129,6 +206,7 @@ phrases = [
"you are", "you are",
"you can't", "you can't",
"you don't", "you don't",
"you know",
"you need", "you need",
"you were", "you were",
] ]