* Add pipeline state property bag to run context
* Move state creation out of context util
* Move callbacks into PipelineRunContext
* Semver
* Rename state.json to context.json to avoid confusion with stats.json
* Expand smoke test row count
* Add util to create storage and cache
* Move verb tests to regular CI
* Clean up env vars
* Update smoke runtime expectations
* Rework artifact assertions
* Fix plural in name
* remove redundant artifact len check
* Remove redundant artifact len check
* Adjust graph output expectations
* Update community expectations
* Include all workflow output
* Adjust text unit expectations
* Adjust assertions per dataset
* Fix test config param name
* Update nan allowed for optional model fields
---------
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
* Add callbacks to global search
* Add callbacks to local search
* Add streaming callbacks in local search CLI
* Add callbacks to basic search
* Add callbacks to DRIFT search
* Semver
* Return generators directly in API
* Guard callbacks
* Add workflow registration
* Add ability to mutate config by workflows
* Separate graph finalization
* Separate graph pruning
* Semver
* Update tests
* Update smoke tests
* Fix iterrows on create_graph
* Remove prune_graph from llm construction
* Update test data
* Remove prune_graph from smoke tests
* Add children to the community tables
* Replace NaN children with empty list
* Replace subcommunity logic with built-in parent/child fields
* Remove restore_community_hierarchy
* Add children and frequency to migration notebook
* Format
* Semver
* Add children to reports
* Update tests
---------
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
* Rework update output structure
* Semver
* Fix unit test
* Update frequency in incremental
---------
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
* consolidate query api functions and remove code duplication
* refactor and remove more code duplication
* Add semversioner file
* fix basic search
* fix drift search and update base class function names
* update example notebooks
* Add vector store id reference to embeddings config.
* changed structure of output config section
* added cli integration for multi index global
* added cli integration for multi index local
* added cli integration for multi index drift and basic
* finished local testing of multi-index cli
* ruff fixes
* partially refactored test code to align with new output section
* more test changes for new output structure
* semversioner
* refactored to align with new multi index config proposal
* locally tested new multi-index output proposal
* cleaned up tests to align with new structure
---------
Co-authored-by: Derek Worthen <worthend.derek@gmail.com>
Corrected "this values" to "these values" for improved clarity. This ensures the documentation is more accurate and professional.
Co-authored-by: Nathan Evans <github@talkswithnumbers.com>
Corrected a missing backtick in a note within the `GRAPHRAG_API_KEY` description. This ensures proper code formatting and improves readability in the documentation. No content was altered aside from formatting adjustments.
Co-authored-by: Nathan Evans <github@talkswithnumbers.com>
* remove unused columns and change property document_attribute_columns to metadata
* format file
* fix 'metadata' column on output
* run check
* fix test on nltk
* remove docs changes
* Require explicit azure auth settings when using AOI.
- Must set LanguageModel.azure_auth_type to either
"api_key" or "managed_identity" when using AOI.
* Fix smoke tests
* Use general auth_type property instead of azure_auth_type
* Remove unused error type
* Update validation
* Update validation comment
* added multi-global-query function header
* ported over code for merging dataframes
* added connection to global streaming api function
* added function header for update context helper
* implemented and incorperated update_context function
* Updated to make sure 'parent' column in final_communities gets incremented for multi index.
* first cut at multi_local_seach function
* several minor changes and fixes
* Updated multi index local search.
* Cleaned up code.
* fixed lambda function ruff errors
* fixed more ruff errors
* moved query api helpers to util file
* moved index api helpers to util file
* merged in code left out of conflict
* changed GraphRagConfig object to support lists of vector stores
* Updated with fixes for multi_local_search.
* Minor updates.
* Minor updates.
* Updates for ruff check.
* Minor updates.
* removed redundant vector_store_configs arg
* ruff formatting changes
* semversioner
* Minor fix.
* spellcheck fixes
* ruff
* test fix for cicd errors
* another test fix
* added explicit typing for ci tests
* added dict type check for vector_store during indexing
* more ruff fixes
* moved type check
* Removed streaming. Added multi drift and basic searches.
* Formatting changes.
* Updates for pyright.
* Update for ruff.
* Ruff formatted.
* first cut at fixing vector store typing errors
* got multi local search working with new config
* ruff and test fixes
* added fix for embeddings type error
* renamed multi index api functions
* ruff
* convert config model to dict[VectorStoreConfig]
* modified tests to support new vector_store model
* ruff fixes
* changed some test setups to match new model
* changed ci/cd settings files to match new structure
* Fix stderror check
* fixed bug in vector_store_config validation
* ruff
* add database_name field to vectorstoreconfig
* removed print statements
* small refactoring for PR comments
* modified default config in test
* modified vector store config unit test
---------
Co-authored-by: dorbaker <dorbaker@microsoft.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
Updated the auto prompt tuning doc with `--selection-method` instead of only `--method` as per the latest API.
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
* 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>
* Add vector field to retrievable fields for Azure AI Search
* Add DRIFT and Basic search to smoke tests
* Semver
* Format
* Remove DRIFT smoke test for now (brittle)
* Adding basic wrappes for reduce in drift
* Add response_type parameter to run_drift_search and enhance reduce response functionality
* Add streaming endpoint
* Semver
* Spellcheck
* Ruff checks
* Count tokens on reduce
* Use list comprehension and remove llm_params map in favor of just using kwargs
* Add new inputs and missing vector store for retrieving vectors
* Format
* Semver
* Remove .Identifier files
* Fix spellcheck
* Remove unnecessary input file for notebooks
