mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-03 15:10:17 +00:00
c8c354e357
* 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
79 lines
2.3 KiB
Python
79 lines
2.3 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from io import BytesIO
|
|
|
|
import pandas as pd
|
|
|
|
from graphrag.index.config.embeddings import (
|
|
all_embeddings,
|
|
)
|
|
from graphrag.index.run.utils import create_run_context
|
|
from graphrag.index.workflows.v1.generate_text_embeddings import (
|
|
build_steps,
|
|
workflow_name,
|
|
)
|
|
|
|
from .util import (
|
|
get_config_for_workflow,
|
|
get_workflow_output,
|
|
load_input_tables,
|
|
)
|
|
|
|
|
|
async def test_generate_text_embeddings():
|
|
input_tables = load_input_tables(
|
|
inputs=[
|
|
"workflow:create_final_documents",
|
|
"workflow:create_final_relationships",
|
|
"workflow:create_final_text_units",
|
|
"workflow:create_final_entities",
|
|
"workflow:create_final_community_reports",
|
|
]
|
|
)
|
|
context = create_run_context(None, None, None)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
config["text_embed"]["strategy"]["type"] = "mock"
|
|
config["snapshot_embeddings"] = True
|
|
|
|
config["embedded_fields"] = all_embeddings
|
|
|
|
steps = build_steps(config)
|
|
|
|
await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
context,
|
|
)
|
|
|
|
parquet_files = context.storage.keys()
|
|
|
|
for field in all_embeddings:
|
|
assert f"embeddings.{field}.parquet" in parquet_files
|
|
|
|
# entity description should always be here, let's assert its format
|
|
entity_description_embeddings_buffer = BytesIO(
|
|
await context.storage.get(
|
|
"embeddings.entity.description.parquet", as_bytes=True
|
|
)
|
|
)
|
|
entity_description_embeddings = pd.read_parquet(
|
|
entity_description_embeddings_buffer
|
|
)
|
|
assert len(entity_description_embeddings.columns) == 2
|
|
assert "id" in entity_description_embeddings.columns
|
|
assert "embedding" in entity_description_embeddings.columns
|
|
|
|
# every other embedding is optional but we've turned them all on, so check a random one
|
|
document_text_embeddings_buffer = BytesIO(
|
|
await context.storage.get("embeddings.document.text.parquet", as_bytes=True)
|
|
)
|
|
document_text_embeddings = pd.read_parquet(document_text_embeddings_buffer)
|
|
assert len(document_text_embeddings.columns) == 2
|
|
assert "id" in document_text_embeddings.columns
|
|
assert "embedding" in document_text_embeddings.columns
|