Chunkers: Refactor each chunker & add base class
Adds a base chunker from which any chunker can inherit. Existing chunkers are refactored to inherit from this base chunker.
This commit is contained in:
27
embedchain/chunkers/base_chunker.py
Normal file
27
embedchain/chunkers/base_chunker.py
Normal file
@@ -0,0 +1,27 @@
|
||||
import hashlib
|
||||
|
||||
|
||||
class BaseChunker:
|
||||
def __init__(self, text_splitter):
|
||||
self.text_splitter = text_splitter
|
||||
|
||||
def create_chunks(self, loader, url):
|
||||
documents = []
|
||||
ids = []
|
||||
datas = loader.load_data(url)
|
||||
metadatas = []
|
||||
for data in datas:
|
||||
content = data["content"]
|
||||
meta_data = data["meta_data"]
|
||||
chunks = self.text_splitter.split_text(content)
|
||||
url = meta_data["url"]
|
||||
for chunk in chunks:
|
||||
chunk_id = hashlib.sha256((chunk + url).encode()).hexdigest()
|
||||
ids.append(chunk_id)
|
||||
documents.append(chunk)
|
||||
metadatas.append(meta_data)
|
||||
return {
|
||||
"documents": documents,
|
||||
"ids": ids,
|
||||
"metadatas": metadatas,
|
||||
}
|
||||
Reference in New Issue
Block a user