mirror of
https://github.com/microsoft/graphrag.git
synced 2025-11-05 12:23:27 +00:00
c644338bae
* Refactor config
- Add new ModelConfig to represent LLM settings
- Combines LLMParameters, ParallelizationParameters, encoding_model, and async_mode
- Add top level models config that is a list of available LLM ModelConfigs
- Remove LLMConfig inheritance and delete LLMConfig
- Replace the inheritance with a model_id reference to the ModelConfig listed in the top level models config
- Remove all fallbacks and hydration logic from create_graphrag_config
- This removes the automatic env variable overrides
- Support env variables within config files using Templating
- This requires "$" to be escaped with extra "$" so ".*\\.txt$" becomes ".*\\.txt$$"
- Update init content to initialize new config file with the ModelConfig structure
* Use dict of ModelConfig instead of list
* Add model validations and unit tests
* Fix ruff checks
* Add semversioner change
* Fix unit tests
* validate root_dir in pydantic model
* Rename ModelConfig to LanguageModelConfig
* Rename ModelConfigMissingError to LanguageModelConfigMissingError
* Add validationg for unexpected API keys
* Allow skipping pydantic validation for testing/mocking purposes.
* Add default lm configs to verb tests
* smoke test
* remove config from flows to fix llm arg mapping
* Fix embedding llm arg mapping
* Remove timestamp from smoke test outputs
* Remove unused "subworkflows" smoke test properties
* Add models to smoke test configs
* Update smoke test output path
* Send logs to logs folder
* Fix output path
* Fix csv test file pattern
* Update placeholder
* Format
* Instantiate default model configs
* Fix unit tests for config defaults
* Fix migration notebook
* Remove create_pipeline_config
* Remove several unused config models
* Remove indexing embedding and input configs
* Move embeddings function to config
* Remove skip_workflows
* Remove skip embeddings in favor of explicit naming
* fix unit test spelling mistake
* self.models[model_id] is already a language model. Remove redundant casting.
* update validation errors to instruct users to rerun graphrag init
* instantiate LanguageModelConfigs with validation
* skip validation in unit tests
* update verb tests to use default model settings instead of skipping validation
* test using llm settings
* cleanup verb tests
* remove unsafe default model config
* remove the ability to skip pydantic validation
* remove None union types when default values are set
* move vector_store from embeddings to top level of config and delete resolve_paths
* update vector store settings
* fix vector store and smoke tests
* fix serializing vector_store settings
* fix vector_store usage
* fix vector_store type
* support cli overrides for loading graphrag config
* rename storage to output
* Add --force flag to init
* Remove run_id and resume, fix Drift config assignment
* Ruff
---------
Co-authored-by: Nathan Evans <github@talkswithnumbers.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
83 lines
3.4 KiB
Python
83 lines
3.4 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from pandas.testing import assert_series_equal
|
|
|
|
from graphrag.callbacks.noop_workflow_callbacks import NoopWorkflowCallbacks
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.config.enums import LLMType
|
|
from graphrag.index.workflows.create_final_covariates import (
|
|
run_workflow,
|
|
workflow_name,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
create_test_context,
|
|
load_test_table,
|
|
)
|
|
|
|
MOCK_LLM_RESPONSES = [
|
|
"""
|
|
(COMPANY A<|>GOVERNMENT AGENCY B<|>ANTI-COMPETITIVE PRACTICES<|>TRUE<|>2022-01-10T00:00:00<|>2022-01-10T00:00:00<|>Company A was found to engage in anti-competitive practices because it was fined for bid rigging in multiple public tenders published by Government Agency B according to an article published on 2022/01/10<|>According to an article published on 2022/01/10, Company A was fined for bid rigging while participating in multiple public tenders published by Government Agency B.)
|
|
""".strip()
|
|
]
|
|
|
|
|
|
async def test_create_final_covariates():
|
|
input = load_test_table("create_base_text_units")
|
|
expected = load_test_table(workflow_name)
|
|
|
|
context = await create_test_context(
|
|
storage=["create_base_text_units"],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
llm_settings = config.get_language_model_config(
|
|
config.claim_extraction.model_id
|
|
).model_dump()
|
|
llm_settings["type"] = LLMType.StaticResponse
|
|
llm_settings["responses"] = MOCK_LLM_RESPONSES
|
|
config.claim_extraction.strategy = {
|
|
"type": "graph_intelligence",
|
|
"llm": llm_settings,
|
|
"claim_description": "description",
|
|
}
|
|
|
|
await run_workflow(
|
|
config,
|
|
context,
|
|
NoopWorkflowCallbacks(),
|
|
)
|
|
|
|
actual = await load_table_from_storage(workflow_name, context.storage)
|
|
|
|
assert len(actual.columns) == len(expected.columns)
|
|
# our mock only returns one covariate per text unit, so that's a 1:1 mapping versus the LLM-extracted content in the test data
|
|
assert len(actual) == len(input)
|
|
|
|
# assert all of the columns that covariates copied from the input
|
|
assert_series_equal(actual["text_unit_id"], input["id"], check_names=False)
|
|
|
|
# make sure the human ids are incrementing
|
|
assert actual["human_readable_id"][0] == 1
|
|
assert actual["human_readable_id"][1] == 2
|
|
|
|
# check that the mock data is parsed and inserted into the correct columns
|
|
assert actual["covariate_type"][0] == "claim"
|
|
assert actual["subject_id"][0] == "COMPANY A"
|
|
assert actual["object_id"][0] == "GOVERNMENT AGENCY B"
|
|
assert actual["type"][0] == "ANTI-COMPETITIVE PRACTICES"
|
|
assert actual["status"][0] == "TRUE"
|
|
assert actual["start_date"][0] == "2022-01-10T00:00:00"
|
|
assert actual["end_date"][0] == "2022-01-10T00:00:00"
|
|
assert (
|
|
actual["description"][0]
|
|
== "Company A was found to engage in anti-competitive practices because it was fined for bid rigging in multiple public tenders published by Government Agency B according to an article published on 2022/01/10"
|
|
)
|
|
assert (
|
|
actual["source_text"][0]
|
|
== "According to an article published on 2022/01/10, Company A was fined for bid rigging while participating in multiple public tenders published by Government Agency B."
|
|
)
|