mirror of
https://github.com/microsoft/graphrag.git
synced 2025-06-26 23:19:58 +00:00
c02ab0984a
* Remove create_final_nodes * Rename final entity output to "entities" * Remove duplicate code from graph extraction * Rename create_final_relationships output to "relationships" * Rename create_final_communities output to "communities" * Combine compute_communities and create_final_communities * Rename create_final_covariates output to "covariates" * Rename create_final_community_reports output to "community_reports" * Rename create_final_text_units output to "text_units" * Rename create_final_documents output to "documents" * Remove transient snapshots config * Move create_final_entities to finalize_entities operation * Move create_final_relationships flow to finalize_relationships operation * Reuse some community report functions * Collapse most of graph and text unit-based report generation * Unify schemas files * Move community reports extractor * Move NLP report prompt to prompts folder * Fix a few pandas warnings * Rename embeddings config to embed_text * Rename claim_extraction config to extract_claims * Remove nltk from standard graph extraction * Fix verb tests * Fix extract graph config naming * Fix moved file reference * Create v1-to-v2 migration notebook * Semver * Fix smoke test artifact count * Raise tpm/rpm on smoke tests * Update drift settings for smoke tests * Reuse project directory var in api notebook * Format * Format
72 lines
2.1 KiB
Python
72 lines
2.1 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.callbacks.noop_workflow_callbacks import NoopWorkflowCallbacks
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.config.embeddings import (
|
|
all_embeddings,
|
|
)
|
|
from graphrag.config.enums import TextEmbeddingTarget
|
|
from graphrag.index.workflows.generate_text_embeddings import (
|
|
run_workflow,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
create_test_context,
|
|
)
|
|
|
|
|
|
async def test_generate_text_embeddings():
|
|
context = await create_test_context(
|
|
storage=[
|
|
"documents",
|
|
"relationships",
|
|
"text_units",
|
|
"entities",
|
|
"community_reports",
|
|
]
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
llm_settings = config.get_language_model_config(
|
|
config.embed_text.model_id
|
|
).model_dump()
|
|
|
|
config.embed_text.strategy = {
|
|
"type": "mock",
|
|
"llm": llm_settings,
|
|
}
|
|
config.embed_text.target = TextEmbeddingTarget.all
|
|
config.snapshots.embeddings = True
|
|
|
|
await run_workflow(
|
|
config,
|
|
context,
|
|
NoopWorkflowCallbacks(),
|
|
)
|
|
|
|
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 = await load_table_from_storage(
|
|
"embeddings.entity.description", context.storage
|
|
)
|
|
|
|
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 = await load_table_from_storage(
|
|
"embeddings.document.text", context.storage
|
|
)
|
|
|
|
assert len(document_text_embeddings.columns) == 2
|
|
assert "id" in document_text_embeddings.columns
|
|
assert "embedding" in document_text_embeddings.columns
|