mirror of
https://github.com/microsoft/graphrag.git
synced 2025-11-25 14:37:12 +00:00
17658c5df8
* New workflow to generate embeddings in a single workflow * New workflow to generate embeddings in a single workflow * version change * clean tests without any embeddings references * clean tests without any embeddings references * remove code * feedback implemented * changes in logic * feedback implemented * store in table bug fixed * smoke test for generate_text_embeddings workflow * smoke test fix * add generate_text_embeddings to the list of transient workflows * smoke tests * fix * ruff formatting updates * fix * smoke test fixed * smoke test fixed * fix lancedb import * smoke test fix * ignore sorting * smoke test fixed * smoke test fixed * check smoke test * smoke test fixed * change config for vector store * format fix * vector store changes * revert debug profile back to empty filepath * merge conflict solved * merge conflict solved * format fixed * format fixed * fix return dataframe * snapshot fix * format fix * embeddings param implemented * validation fixes * fix map * fix map * fix properties * config updates * smoke test fixed * settings change * Update collection config and rework back-compat * Repalce . with - for embedding store --------- Co-authored-by: Alonso Guevara <alonsog@microsoft.com> Co-authored-by: Josh Bradley <joshbradley@microsoft.com> Co-authored-by: Nathan Evans <github@talkswithnumbers.com>
61 lines
1.5 KiB
Python
61 lines
1.5 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.index.workflows.v1.create_final_documents 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_final_documents():
|
|
input_tables = load_input_tables([
|
|
"workflow:create_final_text_units",
|
|
])
|
|
expected = load_expected(workflow_name)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|
|
|
|
compare_outputs(actual, expected)
|
|
|
|
|
|
async def test_create_final_documents_with_attribute_columns():
|
|
input_tables = load_input_tables(["workflow:create_final_text_units"])
|
|
expected = load_expected(workflow_name)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
config["document_attribute_columns"] = ["title"]
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|
|
|
|
# we should have dropped "title" and added "attributes"
|
|
# our test dataframe does not have attributes, so we'll assert without it
|
|
# and separately confirm it is in the output
|
|
compare_outputs(actual, expected, columns=["id", "text_unit_ids", "raw_content"])
|
|
assert len(actual.columns) == 4
|
|
assert "attributes" in actual.columns
|