mirror of
https://github.com/microsoft/graphrag.git
synced 2026-01-14 00:57:23 +08:00
8fd7730067
Some checks failed
Python Build and Type Check / python-ci (ubuntu-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
* Delete NoopTextSplitter * Delete unused check_token_limit * Add base chunking factory and migrate workflow to use it * Split apart chunker module * Co-locate chunking/splitting * Collapse token splitting functionality into one class/function * Restore create_base_text_units parameterization * Move Tokenizer base class to common package * Move pre-pending into chunkers * Streamline config * Fix defaults construction * Add prepending tests * Remove chunk_size_includes_metadata config * Revert ChunkingDocument interface * Move metadata prepending to a util * Move Tokenizer back to GR core * Fix tokenizer removal from chunker * Set defaults for chunking config * Move chunking to monorepo package * Format * Typo * Add ChunkResult model * Streamline chunking config * Add missing version updates for graphrag_chunking
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.config.models.graph_rag_config import GraphRagConfig
|
|
from graphrag.index.workflows.create_base_text_units import run_workflow
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
compare_outputs,
|
|
create_test_context,
|
|
load_test_table,
|
|
update_document_metadata,
|
|
)
|
|
|
|
|
|
async def test_create_base_text_units():
|
|
expected = load_test_table("text_units")
|
|
|
|
context = await create_test_context()
|
|
|
|
config = GraphRagConfig(models=DEFAULT_MODEL_CONFIG) # type: ignore
|
|
|
|
await run_workflow(config, context)
|
|
|
|
actual = await load_table_from_storage("text_units", context.output_storage)
|
|
|
|
compare_outputs(actual, expected, columns=["text", "document_id", "n_tokens"])
|
|
|
|
|
|
async def test_create_base_text_units_metadata():
|
|
expected = load_test_table("text_units_metadata")
|
|
|
|
context = await create_test_context()
|
|
|
|
config = GraphRagConfig(models=DEFAULT_MODEL_CONFIG) # type: ignore
|
|
config.input.metadata = ["title"]
|
|
config.chunking.prepend_metadata = True
|
|
|
|
await update_document_metadata(config.input.metadata, context)
|
|
|
|
await run_workflow(config, context)
|
|
|
|
actual = await load_table_from_storage("text_units", context.output_storage)
|
|
compare_outputs(actual, expected, ["text", "document_id", "n_tokens"])
|