wehub-resource-sync
c889a57b6b
Test Suites / Build CI Environment (push) Has been cancelled
Test Suites / Basic Tests (push) Has been cancelled
Test Suites / End-to-End Tests (push) Has been cancelled
Test Suites / CLI Tests (push) Has been cancelled
Test Suites / Slow End-to-End Tests (push) Has been cancelled
Test Suites / Graph Database Tests (push) Has been cancelled
Test Suites / Vector DB Tests (push) Has been cancelled
Test Suites / Temporal Graph Test (push) Has been cancelled
Test Suites / Search Test on Different DBs (push) Has been cancelled
Test Suites / Example Tests (push) Has been cancelled
Test Suites / Notebook Tests (push) Has been cancelled
Test Suites / OS and Python Tests Ubuntu (push) Has been cancelled
Test Suites / OS and Python Tests Extended (push) Has been cancelled
Test Suites / LLM Test Suite (push) Has been cancelled
Test Suites / S3 File Storage Test (push) Has been cancelled
Test Suites / Run Integration Tests (push) Has been cancelled
Test Suites / MCP Tests (push) Has been cancelled
Test Suites / Docker Compose Test (push) Has been cancelled
Test Suites / Docker CI test (push) Has been cancelled
Test Suites / Relational DB Migration Tests (push) Has been cancelled
Test Suites / Distributed Cognee Test (push) Has been cancelled
Test Suites / DB Examples Tests (push) Has been cancelled
Test Suites / Test Completion Status (push) Has been cancelled
Test Suites / Claude Code Review (push) Has been cancelled
Test Suites / basic checks (push) Has been cancelled
build | Build and Push Cognee MCP Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Scorecard supply-chain security / Scorecard analysis (push) Has been cancelled
build | Build and Push Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.11) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.12) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (kuzu, kuzu) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (neo4j, neo4j) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Examples (push) Has been cancelled
Weighted Edges Tests / Code Quality for Weighted Edges (push) Has been cancelled
91 lines
4.0 KiB
Python
91 lines
4.0 KiB
Python
from cognee.shared.logging_utils import get_logger
|
|
from os.path import basename
|
|
from uuid import NAMESPACE_OID, uuid5
|
|
|
|
from cognee.tasks.chunks import chunk_by_paragraph
|
|
from cognee.modules.chunking.Chunker import Chunker
|
|
from .models.DocumentChunk import DocumentChunk
|
|
|
|
logger = get_logger()
|
|
|
|
|
|
class TextChunker(Chunker):
|
|
async def read(self):
|
|
document_id = str(self.document.id)
|
|
document_name = self.document.name or basename(self.document.raw_data_location)
|
|
paragraph_chunks = []
|
|
async for content_text in self.get_text():
|
|
for chunk_data in chunk_by_paragraph(
|
|
content_text,
|
|
self.max_chunk_size,
|
|
batch_paragraphs=True,
|
|
):
|
|
if self.chunk_size + chunk_data["chunk_size"] <= self.max_chunk_size:
|
|
paragraph_chunks.append(chunk_data)
|
|
self.chunk_size += chunk_data["chunk_size"]
|
|
else:
|
|
if len(paragraph_chunks) == 0:
|
|
yield DocumentChunk(
|
|
id=chunk_data["chunk_id"],
|
|
text=chunk_data["text"],
|
|
chunk_size=chunk_data["chunk_size"],
|
|
is_part_of=self.document,
|
|
chunk_index=self.chunk_index,
|
|
cut_type=chunk_data["cut_type"],
|
|
contains=[],
|
|
importance_weight=self.document.importance_weight,
|
|
document_id=document_id,
|
|
document_name=document_name,
|
|
metadata={
|
|
"index_fields": ["text"],
|
|
},
|
|
)
|
|
paragraph_chunks = []
|
|
self.chunk_size = 0
|
|
else:
|
|
chunk_text = " ".join(chunk["text"] for chunk in paragraph_chunks)
|
|
try:
|
|
yield DocumentChunk(
|
|
id=uuid5(
|
|
NAMESPACE_OID, f"{str(self.document.id)}-{self.chunk_index}"
|
|
),
|
|
text=chunk_text,
|
|
chunk_size=self.chunk_size,
|
|
is_part_of=self.document,
|
|
chunk_index=self.chunk_index,
|
|
cut_type=paragraph_chunks[len(paragraph_chunks) - 1]["cut_type"],
|
|
contains=[],
|
|
importance_weight=self.document.importance_weight,
|
|
document_id=document_id,
|
|
document_name=document_name,
|
|
metadata={
|
|
"index_fields": ["text"],
|
|
},
|
|
)
|
|
except Exception as e:
|
|
logger.error(e)
|
|
raise e
|
|
paragraph_chunks = [chunk_data]
|
|
self.chunk_size = chunk_data["chunk_size"]
|
|
|
|
self.chunk_index += 1
|
|
|
|
if len(paragraph_chunks) > 0:
|
|
try:
|
|
yield DocumentChunk(
|
|
id=uuid5(NAMESPACE_OID, f"{str(self.document.id)}-{self.chunk_index}"),
|
|
text=" ".join(chunk["text"] for chunk in paragraph_chunks),
|
|
chunk_size=self.chunk_size,
|
|
is_part_of=self.document,
|
|
chunk_index=self.chunk_index,
|
|
cut_type=paragraph_chunks[len(paragraph_chunks) - 1]["cut_type"],
|
|
contains=[],
|
|
importance_weight=self.document.importance_weight,
|
|
document_id=document_id,
|
|
document_name=document_name,
|
|
metadata={"index_fields": ["text"]},
|
|
)
|
|
except Exception as e:
|
|
logger.error(e)
|
|
raise e
|