mirror of
https://github.com/microsoft/graphrag.git
synced 2025-11-11 15:24:21 +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>
76 lines
2.8 KiB
Python
76 lines
2.8 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
"""StorageFactory Tests.
|
|
|
|
These tests will test the StorageFactory class and the creation of each storage type that is natively supported.
|
|
"""
|
|
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
from graphrag.config.enums import OutputType
|
|
from graphrag.storage.blob_pipeline_storage import BlobPipelineStorage
|
|
from graphrag.storage.cosmosdb_pipeline_storage import CosmosDBPipelineStorage
|
|
from graphrag.storage.factory import StorageFactory
|
|
from graphrag.storage.file_pipeline_storage import FilePipelineStorage
|
|
from graphrag.storage.memory_pipeline_storage import MemoryPipelineStorage
|
|
|
|
# cspell:disable-next-line well-known-key
|
|
WELL_KNOWN_BLOB_STORAGE_KEY = "DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;BlobEndpoint=http://127.0.0.1:10000/devstoreaccount1;"
|
|
# cspell:disable-next-line well-known-key
|
|
WELL_KNOWN_COSMOS_CONNECTION_STRING = "AccountEndpoint=https://127.0.0.1:8081/;AccountKey=C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
|
|
|
|
|
|
def test_create_blob_storage():
|
|
kwargs = {
|
|
"type": "blob",
|
|
"connection_string": WELL_KNOWN_BLOB_STORAGE_KEY,
|
|
"base_dir": "testbasedir",
|
|
"container_name": "testcontainer",
|
|
}
|
|
storage = StorageFactory.create_storage(OutputType.blob, kwargs)
|
|
assert isinstance(storage, BlobPipelineStorage)
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not sys.platform.startswith("win"),
|
|
reason="cosmosdb emulator is only available on windows runners at this time",
|
|
)
|
|
def test_create_cosmosdb_storage():
|
|
kwargs = {
|
|
"type": "cosmosdb",
|
|
"connection_string": WELL_KNOWN_COSMOS_CONNECTION_STRING,
|
|
"base_dir": "testdatabase",
|
|
"container_name": "testcontainer",
|
|
}
|
|
storage = StorageFactory.create_storage(OutputType.cosmosdb, kwargs)
|
|
assert isinstance(storage, CosmosDBPipelineStorage)
|
|
|
|
|
|
def test_create_file_storage():
|
|
kwargs = {"type": "file", "base_dir": "/tmp/teststorage"}
|
|
storage = StorageFactory.create_storage(OutputType.file, kwargs)
|
|
assert isinstance(storage, FilePipelineStorage)
|
|
|
|
|
|
def test_create_memory_storage():
|
|
kwargs = {"type": "memory"}
|
|
storage = StorageFactory.create_storage(OutputType.memory, kwargs)
|
|
assert isinstance(storage, MemoryPipelineStorage)
|
|
|
|
|
|
def test_register_and_create_custom_storage():
|
|
class CustomStorage:
|
|
def __init__(self, **kwargs):
|
|
pass
|
|
|
|
StorageFactory.register("custom", CustomStorage)
|
|
storage = StorageFactory.create_storage("custom", {})
|
|
assert isinstance(storage, CustomStorage)
|
|
|
|
|
|
def test_create_unknown_storage():
|
|
with pytest.raises(ValueError, match="Unknown storage type: unknown"):
|
|
StorageFactory.create_storage("unknown", {})
|