mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-25 18:01:14 +00:00
1755afbdec
* Collapse non-attribute verbs * Include document_column_attributes in collapse * Remove merge_override verb * Semver * Setup initial test and config * Collapse create_base_text_units * Semver * Spelling * Fix smoke tests * Addres PR comments --------- Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
36 lines
865 B
Python
36 lines
865 B
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.index.workflows.v1.create_base_text_units import (
|
|
build_steps,
|
|
workflow_name,
|
|
)
|
|
|
|
from .util import (
|
|
compare_outputs,
|
|
get_config_for_workflow,
|
|
get_workflow_output,
|
|
load_expected,
|
|
load_input_tables,
|
|
)
|
|
|
|
|
|
async def test_create_base_text_units():
|
|
input_tables = load_input_tables(inputs=[])
|
|
expected = load_expected(workflow_name)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
# test data was created with 4o, so we need to match the encoding for chunks to be identical
|
|
config["text_chunk"]["strategy"]["encoding_name"] = "o200k_base"
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|
|
|
|
compare_outputs(actual, expected)
|