graphrag/tests/verbs/test_create_final_documents.py

77 lines
2.0 KiB
Python
Raw Normal View History

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
from graphrag.index.run.utils import create_run_context
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_input_tables,
load_test_table,
)
async def test_create_final_documents():
input_tables = load_input_tables([
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
"workflow:create_base_text_units",
])
expected = load_test_table(workflow_name)
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
context = create_run_context(None, None, None)
await context.runtime_storage.set(
"base_text_units", input_tables["workflow:create_base_text_units"]
)
config = get_config_for_workflow(workflow_name)
steps = build_steps(config)
actual = await get_workflow_output(
input_tables,
{
"steps": steps,
},
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
context=context,
)
compare_outputs(actual, expected)
async def test_create_final_documents_with_attribute_columns():
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
input_tables = load_input_tables(["workflow:create_base_text_units"])
expected = load_test_table(workflow_name)
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
context = create_run_context(None, None, None)
await context.runtime_storage.set(
"base_text_units", input_tables["workflow:create_base_text_units"]
)
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,
},
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
context=context,
)
# 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
Artifact cleanup (#1341) * Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
2024-11-13 15:11:19 -08:00
compare_outputs(
actual, expected, columns=["id", "human_readable_id", "text", "text_unit_ids"]
)
assert len(actual.columns) == 5
assert "title" not in actual.columns
assert "attributes" in actual.columns