10 Commits

Author	SHA1	Message	Date
Copilot	2030f94eb4	Refactor CacheFactory, StorageFactory, and VectorStoreFactory to use consistent registration patterns and add custom vector store documentation (#2006) ... * Initial plan * Refactor VectorStoreFactory to use registration functionality like StorageFactory Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix linting issues in VectorStoreFactory refactoring Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove backward compatibility support from VectorStoreFactory and StorageFactory Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Run ruff check --fix and ruff format, add semversioner file Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff formatting fixes * Fix pytest errors in storage factory tests by updating PipelineStorage interface implementation Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff formatting fixes * update storage factory design * Refactor CacheFactory to use registration functionality like StorageFactory Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * revert copilot changes * fix copilot changes * update comments * Fix failing pytest compatibility for factory tests Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * update class instantiation issue * ruff fixes * fix pytest * add default value * ruff formatting changes * ruff fixes * revert minor changes * cleanup cache factory * Update CacheFactory tests to match consistent factory pattern Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * update pytest thresholds * adjust threshold levels * Add custom vector store implementation notebook Create comprehensive notebook demonstrating how to implement and register custom vector stores with GraphRAG as a plug-and-play framework. Includes: - Complete implementation of SimpleInMemoryVectorStore - Registration with VectorStoreFactory - Testing and validation examples - Configuration examples for GraphRAG settings - Advanced features and best practices - Production considerations checklist The notebook provides a complete walkthrough for developers to understand and implement their own vector store backends. Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * remove sample notebook for now * update tests * fix cache pytests * add pandas-stub to dev dependencies * disable warning check for well known key * skip tests when running on ubuntu * add documentation for custom vector store implementations * ignore ruff findings in notebooks * fix merge breakages * speedup CLI import statements * remove unnecessary import statements in init file * Add str type option on storage/cache type * Fix store name * Add LoggerFactory * Fix up logging setup across CLI/API * Add LoggerFactory test * Fix err message * Semver * Remove enums from factory methods --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> Co-authored-by: Josh Bradley <joshbradley@microsoft.com> Co-authored-by: Nathan Evans <github@talkswithnumbers.com>	2025-08-28 13:53:07 -07:00
Copilot	13bf315a35	Refactor StorageFactory class to use registration functionality (#1944) ... * Initial plan for issue * Refactored StorageFactory to use a registration-based approach Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Added semversioner change record Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix Python CI test failures and improve code quality Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff formatting fixes --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> Co-authored-by: Josh Bradley <joshbradley@microsoft.com>	2025-07-10 12:08:44 -06:00
Copilot	e84df28e64	Improve internal logging functionality by using Python's standard logging module (#1956) ... * Initial plan for issue * Implement standard logging module and integrate with existing loggers Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Add test cases and improve documentation for standard logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Apply ruff formatting and add semversioner file for logging improvements Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove custom logger classes and refactor to use standard logging only Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Apply ruff formatting to resolve CI/CD test failures Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Add semversioner file and fix linting issues Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff fixes * fix spelling error * Remove StandardProgressLogger and refactor to use standard logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove LoggerFactory and custom loggers, refactor to use standard logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix pyright error: use logger.info() instead of calling logger as function in cosmosdb_pipeline_storage.py Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff fixes * Remove deprecated logger files that were marked as deprecated placeholders Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Replace custom get_logger with standard Python logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix linting issues found by ruff check --fix Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff check fixes * add word to dictionary * Fix type checker error in ModelManager.__new__ method Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Refactor multiple logging.getLogger() calls to use single logger per file Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove progress_logger parameter from build_index() and logger parameter from generate_indexing_prompts() Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove logger parameter from run_pipeline and standardize logger naming Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Replace logger parameter with log_level parameter in CLI commands Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix import ordering in notebook files to pass poetry poe check Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove --logger parameter from smoke test command Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix Windows CI/CD issue with log file cleanup in tests Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Add StreamHandler to root logger in __main__.py for CLI logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Only add StreamHandler if root logger doesn't have existing StreamHandler Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix import ordering in notebook files to pass ruff checks Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Replace logging.StreamHandler with colorlog.StreamHandler for colorized log output Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Regenerate poetry.lock file after adding colorlog dependency Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix import ordering in notebook files to pass ruff checks Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * move printing of dataframes to debug level * remove colorlog for now * Refactor workflow callbacks to inherit from logging.Handler Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix linting issues in workflow callback handlers Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix pyright type errors in blob and file workflow callbacks Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Refactor pipeline logging to use pure logging.Handler subclasses Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Rename workflow callback classes to workflow logger classes and move to logger directory Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * update dictionary * apply ruff fixes * fix function name * simplify logger code * update * Remove error, warning, and log methods from WorkflowCallbacks and replace with standard logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * ruff fixes * Fix pyright errors by removing WorkflowCallbacks from strategy type signatures Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove ConsoleWorkflowLogger and apply consistent formatter to all handlers Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff fixes * Refactor pipeline_logger.py to use standard FileHandler and remove FileWorkflowLogger Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove conditional azure import checks from blob_workflow_logger.py Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Fix pyright type checking errors in mock_provider.py and utils.py Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Run ruff check --fix to fix import ordering in notebooks Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Merge configure_logging and create_pipeline_logger into init_loggers function Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * Remove configure_logging and create_pipeline_logger functions, replace all usage with init_loggers Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff fixes * cleanup unused code * Update init_loggers to accept GraphRagConfig instead of ReportingConfig Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff check fixes * Fix test failures by providing valid GraphRagConfig with required model configurations Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff fixes * remove logging_workflow_callback * cleanup logging messages * Add logging to track progress of pandas DataFrame apply operation in create_base_text_units Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * cleanup logger logic throughout codebase * update * more cleanup of old loggers * small logger cleanup * final code cleanup and added loggers to query * add verbose logging to query * minor code cleanup * Fix broken unit tests for chunk_text and standard_logging Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * apply ruff fixes * Fix test_chunk_text by mocking progress_ticker function instead of ProgressTicker class Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> * remove unnecessary logger * remove rich and fix type annotation * revert test formatting changes my by copilot * promote graphrag logs to root logger * add correct semversioner file * revert change to file * revert formatting changes that have no effect * fix changes after merge with main * revert unnecessary copilot changes * remove whitespace * cleanup docstring * simplify some logic with less code * update poetry lock file * ruff fixes --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: jgbradley1 <654554+jgbradley1@users.noreply.github.com> Co-authored-by: Josh Bradley <joshbradley@microsoft.com>	2025-07-09 18:29:03 -06:00
Nathan Evans	1df89727c3	Pipeline registration (#1940) ... * Move covariate run conditional * All pipeline registration * Fix method name construction * Rename context storage -> output_storage * Rename OutputConfig as generic StorageConfig * Reuse Storage model under InputConfig * Move input storage creation out of document loading * Move document loading into workflows * Semver * Fix smoke test config for new workflows * Fix unit tests --------- Co-authored-by: Alonso Guevara <alonsog@microsoft.com>	2025-06-12 16:14:39 -07:00
Dayenne Souza	b94290ec2b	add option to add metadata into text chunks (#1681) ... * add new options * add metadata json into input document * remove doc change * add metadata column into text loader * prepend_metadata * run fix * fix tests and patch * fix test * add watrning for metadata tokens > config size * fix typo and run fix * fix test_integration * fix test * run check * rename and fix chunking * fix * fix * fiz test verbs * fix * fix tests * fix chunking * fix index * fix cosmos test * fix vars * fix after PR * fix	2025-02-12 09:38:03 -08:00
Derek Worthen	c644338bae	Refactor config (#1593) ... * 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>	2025-01-21 17:52:06 -06:00
Josh Bradley	cbb8f8788e	Fix storage class instantiation (#1582)	2025-01-03 17:39:44 -05:00
KennyZhang1	8368b12532	Add Cosmos DB storage/cache option (#1431) ... * added cosmosdb constructor and database methods * added rest of abstract method headers * added cosmos db container methods * implemented has and delete methods * finished implementing abstract class methods * integrated class into storage factory * integrated cosmosdb class into cache factory * added support for new config file fields * replaced primary key cosmosdb initialization with connection strings * modified cosmosdb setter to require json * Fix non-default emitters * Format * Ruff * ruff * first successful run of cosmosdb indexing * removed extraneous container_name setting * require base_dir to be typed as str * reverted merged changed from closed branch * removed nested try statement * readded initial non-parquet emitter fix * added basic support for parquet emitter using internal conversions * merged with main and resolved conflicts * fixed more merge conflicts * added cosmosdb functionality to query pipeline * tested query for cosmosdb * collapsed cosmosdb schema to use minimal containers and databases * simplified create_database and create_container functions * ruff fixes and semversioner * spellcheck and ci fixes * updated pyproject toml and lock file * apply fixes after merge from main * add temporary comments * refactor cache factory * refactored storage factory * minor formatting * update dictionary * fix spellcheck typo * fix default value * fix pydantic model defaults * update pydantic models * fix init_content * cleanup how factory passes parameters to file storage * remove unnecessary output file type * update pydantic model * cleanup code * implemented clear method * fix merge from main * add test stub for cosmosdb * regenerate lock file * modified set method to collapse parquet rows * modified get method to collapse parquet rows * updated has and delete methods and docstrings to adhere to new schema * added prefix helper function * replaced delimiter for prefixed id * verified empty tests are passing * fix merges from main * add find test * update cicd step name * tested querying for new schema * resolved errors from merge conflicts * refactored set method to handle cache in new schema * refactored get method to handle cache in new schema * force unique ids to be written to cosmos for nodes * found bug with has and delete methods * modified has and delete to work with cache in new schema * fix the merge from main * minor typo fixes * update lock file * spellcheck fix * fix init function signature * minor formatting updates * remove https protocol * change localhost to 127.0.0.1 address * update pytest to use bacj engine * verified cache tests * improved speed of has function * resolved pytest error with find function * added test for child method * make container_name variable private as _container_name * minor variable name fix * cleanup cosmos pytest and make the cosmosdb storage class operations more efficient * update cicd to use different cosmosdb emulator * test with http protocol * added pytest for clear() * add longer timeout for cosmosdb emulator startup * revert http connection back to https * add comments to cicd code for future dev usage * set to container and database clients to none upon deletion * ruff changes * add comments to cicd code * removed unneeded None statements and ruff fixes * more ruff fixes * Update test_run.py * remove unnecessary call to delete container * ruff format updates * Reverted test_run.py * fix ruff formatter errors * cleanup variable names to be more consistent * remove extra semversioner file * revert pydantic model changes * revert pydantic model change * revert pydantic model change * re-enable inline formatting rule * update documentation in dev guide --------- Co-authored-by: Alonso Guevara <alonsog@microsoft.com> Co-authored-by: Josh Bradley <joshbradley@microsoft.com>	2024-12-19 13:43:21 -06:00
Josh Bradley	dad2176b3c	Miscellaneous code cleanup procedures (#1452)	2024-11-27 13:27:43 -05:00
Nathan Evans	f5b4d2fea5	Ci streamline (#988) ... * Remove excess vars from gh-pages build * Delete redundant javascript ci * Pull apart testing CI * Clean up integration tests build * Move storage tests to integration CI * Take py 3.10 out of smoke tests matrix * Use minimum supported python version for most tests * Re-run main CI on any test change * Add Josh and Kenny to author list * Update auto-resolve perms	2024-08-21 15:16:15 -06:00