File size: 9,430 Bytes
b34efa5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 |
"""
Text chunking module for Norwegian RAG chatbot.
Splits documents into manageable chunks for embedding and retrieval.
"""
import re
from typing import List, Optional, Tuple
from ..api.config import CHUNK_SIZE, CHUNK_OVERLAP
class TextChunker:
"""
Splits documents into manageable chunks for embedding and retrieval.
Supports different chunking strategies optimized for Norwegian text.
"""
@staticmethod
def chunk_text(
text: str,
chunk_size: int = CHUNK_SIZE,
chunk_overlap: int = CHUNK_OVERLAP,
strategy: str = "paragraph"
) -> List[str]:
"""
Split text into chunks using the specified strategy.
Args:
text: Text to split into chunks
chunk_size: Maximum size of each chunk
chunk_overlap: Overlap between consecutive chunks
strategy: Chunking strategy ('fixed', 'paragraph', or 'sentence')
Returns:
List of text chunks
"""
if not text:
return []
if strategy == "fixed":
return TextChunker.fixed_size_chunks(text, chunk_size, chunk_overlap)
elif strategy == "paragraph":
return TextChunker.paragraph_chunks(text, chunk_size, chunk_overlap)
elif strategy == "sentence":
return TextChunker.sentence_chunks(text, chunk_size, chunk_overlap)
else:
raise ValueError(f"Unknown chunking strategy: {strategy}")
@staticmethod
def fixed_size_chunks(
text: str,
chunk_size: int = CHUNK_SIZE,
chunk_overlap: int = CHUNK_OVERLAP
) -> List[str]:
"""
Split text into fixed-size chunks with overlap.
Args:
text: Text to split into chunks
chunk_size: Maximum size of each chunk
chunk_overlap: Overlap between consecutive chunks
Returns:
List of text chunks
"""
if not text:
return []
chunks = []
start = 0
text_length = len(text)
while start < text_length:
end = min(start + chunk_size, text_length)
# If this is not the first chunk and we're not at the end,
# try to find a good breaking point (whitespace)
if start > 0 and end < text_length:
# Look for the last whitespace within the chunk
last_whitespace = text.rfind(' ', start, end)
if last_whitespace != -1:
end = last_whitespace + 1 # Include the space
# Add the chunk
chunks.append(text[start:end].strip())
# Move the start position for the next chunk, considering overlap
start = end - chunk_overlap if end < text_length else text_length
return chunks
@staticmethod
def paragraph_chunks(
text: str,
max_chunk_size: int = CHUNK_SIZE,
chunk_overlap: int = CHUNK_OVERLAP
) -> List[str]:
"""
Split text into chunks based on paragraphs.
Args:
text: Text to split into chunks
max_chunk_size: Maximum size of each chunk
chunk_overlap: Overlap between consecutive chunks
Returns:
List of text chunks
"""
if not text:
return []
# Split text into paragraphs
paragraphs = re.split(r'\n\s*\n', text)
paragraphs = [p.strip() for p in paragraphs if p.strip()]
chunks = []
current_chunk = []
current_size = 0
for paragraph in paragraphs:
paragraph_size = len(paragraph)
# If adding this paragraph would exceed the max chunk size and we already have content,
# save the current chunk and start a new one
if current_size + paragraph_size > max_chunk_size and current_chunk:
chunks.append('\n\n'.join(current_chunk))
# For overlap, keep some paragraphs from the previous chunk
overlap_size = 0
overlap_paragraphs = []
# Add paragraphs from the end until we reach the desired overlap
for p in reversed(current_chunk):
if overlap_size + len(p) <= chunk_overlap:
overlap_paragraphs.insert(0, p)
overlap_size += len(p)
else:
break
current_chunk = overlap_paragraphs
current_size = overlap_size
# If the paragraph itself is larger than the max chunk size, split it further
if paragraph_size > max_chunk_size:
# First, add the current chunk if it's not empty
if current_chunk:
chunks.append('\n\n'.join(current_chunk))
current_chunk = []
current_size = 0
# Then split the large paragraph into fixed-size chunks
paragraph_chunks = TextChunker.fixed_size_chunks(paragraph, max_chunk_size, chunk_overlap)
chunks.extend(paragraph_chunks)
else:
# Add the paragraph to the current chunk
current_chunk.append(paragraph)
current_size += paragraph_size
# Add the last chunk if it's not empty
if current_chunk:
chunks.append('\n\n'.join(current_chunk))
return chunks
@staticmethod
def sentence_chunks(
text: str,
max_chunk_size: int = CHUNK_SIZE,
chunk_overlap: int = CHUNK_OVERLAP
) -> List[str]:
"""
Split text into chunks based on sentences.
Args:
text: Text to split into chunks
max_chunk_size: Maximum size of each chunk
chunk_overlap: Overlap between consecutive chunks
Returns:
List of text chunks
"""
if not text:
return []
# Norwegian-aware sentence splitting
# This pattern handles common Norwegian sentence endings
sentence_pattern = r'(?<=[.!?])\s+(?=[A-ZÆØÅ])'
sentences = re.split(sentence_pattern, text)
sentences = [s.strip() for s in sentences if s.strip()]
chunks = []
current_chunk = []
current_size = 0
for sentence in sentences:
sentence_size = len(sentence)
# If adding this sentence would exceed the max chunk size and we already have content,
# save the current chunk and start a new one
if current_size + sentence_size > max_chunk_size and current_chunk:
chunks.append(' '.join(current_chunk))
# For overlap, keep some sentences from the previous chunk
overlap_size = 0
overlap_sentences = []
# Add sentences from the end until we reach the desired overlap
for s in reversed(current_chunk):
if overlap_size + len(s) <= chunk_overlap:
overlap_sentences.insert(0, s)
overlap_size += len(s)
else:
break
current_chunk = overlap_sentences
current_size = overlap_size
# If the sentence itself is larger than the max chunk size, split it further
if sentence_size > max_chunk_size:
# First, add the current chunk if it's not empty
if current_chunk:
chunks.append(' '.join(current_chunk))
current_chunk = []
current_size = 0
# Then split the large sentence into fixed-size chunks
sentence_chunks = TextChunker.fixed_size_chunks(sentence, max_chunk_size, chunk_overlap)
chunks.extend(sentence_chunks)
else:
# Add the sentence to the current chunk
current_chunk.append(sentence)
current_size += sentence_size
# Add the last chunk if it's not empty
if current_chunk:
chunks.append(' '.join(current_chunk))
return chunks
@staticmethod
def clean_chunk(chunk: str) -> str:
"""
Clean a text chunk by removing excessive whitespace and normalizing.
Args:
chunk: Text chunk to clean
Returns:
Cleaned text chunk
"""
if not chunk:
return ""
# Replace multiple whitespace with a single space
cleaned = re.sub(r'\s+', ' ', chunk)
# Normalize Norwegian characters (if needed)
# This ensures consistent handling of æ, ø, å
cleaned = cleaned.replace('æ', 'æ').replace('Æ', 'Æ')
cleaned = cleaned.replace('ø', 'ø').replace('Ø', 'Ø')
cleaned = cleaned.replace('å', 'å').replace('Å', 'Å')
return cleaned.strip()
|