diff --git a/.semversioner/2.0.0.json b/.semversioner/2.0.0.json new file mode 100644 index 00000000..89c9a658 --- /dev/null +++ b/.semversioner/2.0.0.json @@ -0,0 +1,146 @@ +{ + "changes": [ + { + "description": "Add children to communities to avoid re-compute.", + "type": "major" + }, + { + "description": "Reorganize and rename workflows and their outputs.", + "type": "major" + }, + { + "description": "Rework API to accept callbacks.", + "type": "major" + }, + { + "description": "Add LMM Manager and Factory, to support provider registration", + "type": "minor" + }, + { + "description": "Add NLP graph extraction.", + "type": "minor" + }, + { + "description": "Add pipeline_start and pipeline_end callbacks.", + "type": "minor" + }, + { + "description": "Move embeddings snapshots to the workflow runner.", + "type": "minor" + }, + { + "description": "Remove config inheritance, hydration, and automatic env var overlays.", + "type": "minor" + }, + { + "description": "Rework the update output storage structure.", + "type": "minor" + }, + { + "description": "Add caching to NLP extractor.", + "type": "patch" + }, + { + "description": "Add vector store id reference to embeddings config.", + "type": "patch" + }, + { + "description": "Export NLP community reports prompt.", + "type": "patch" + }, + { + "description": "Fix DRIFT search on Azure AI Search.", + "type": "patch" + }, + { + "description": "Fix StopAsyncIteration catch.", + "type": "patch" + }, + { + "description": "Fix missing embeddings workflow in FastGraphRAG.", + "type": "patch" + }, + { + "description": "Fix proper use of n_depth for drift search", + "type": "patch" + }, + { + "description": "Fix report generation recursion.", + "type": "patch" + }, + { + "description": "Fix summarization over large datasets for inc indexing. Fix relationship summarization", + "type": "patch" + }, + { + "description": "Optimize data iteration by removing some iterrows from code", + "type": "patch" + }, + { + "description": "Patch json mode for community reports", + "type": "patch" + }, + { + "description": "Properly increment text unit IDs during updates.", + "type": "patch" + }, + { + "description": "Refactor config defaults from constants to type-safe, hierarchical dataclass.", + "type": "patch" + }, + { + "description": "Require explicit azure auth settings when using AOI.", + "type": "patch" + }, + { + "description": "Separates graph pruning for differential usage.", + "type": "patch" + }, + { + "description": "Tuck flow functions under their workflow modules.", + "type": "patch" + }, + { + "description": "Update fnllm. Remove unused libs.", + "type": "patch" + }, + { + "description": "Use ModelProvider for query module", + "type": "patch" + }, + { + "description": "Use shared schema for final outputs.", + "type": "patch" + }, + { + "description": "add dynamic retry logic.", + "type": "patch" + }, + { + "description": "add option to prepend metadata into chunks", + "type": "patch" + }, + { + "description": "cleanup query code duplication.", + "type": "patch" + }, + { + "description": "implemented multi-index querying for api layer", + "type": "patch" + }, + { + "description": "multi index query cli support", + "type": "patch" + }, + { + "description": "remove unused columns and change property document_attribute_columns to metadata", + "type": "patch" + }, + { + "description": "update multi-index query to support new workflows", + "type": "patch" + } + ], + "created_at": "2025-02-25T23:30:50+00:00", + "version": "2.0.0" +} \ No newline at end of file diff --git a/.semversioner/next-release/major-20250204190309656024.json b/.semversioner/next-release/major-20250204190309656024.json deleted file mode 100644 index 49106ad7..00000000 --- a/.semversioner/next-release/major-20250204190309656024.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "major", - "description": "Reorganize and rename workflows and their outputs." -} diff --git a/.semversioner/next-release/major-20250213175726371530.json b/.semversioner/next-release/major-20250213175726371530.json deleted file mode 100644 index 33db379e..00000000 --- a/.semversioner/next-release/major-20250213175726371530.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "major", - "description": "Add children to communities to avoid re-compute." -} diff --git a/.semversioner/next-release/major-20250219010328495371.json b/.semversioner/next-release/major-20250219010328495371.json deleted file mode 100644 index 5689f091..00000000 --- a/.semversioner/next-release/major-20250219010328495371.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "major", - "description": "Rework API to accept callbacks." -} diff --git a/.semversioner/next-release/minor-20250109223356701278.json b/.semversioner/next-release/minor-20250109223356701278.json deleted file mode 100644 index eadc2b49..00000000 --- a/.semversioner/next-release/minor-20250109223356701278.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Remove config inheritance, hydration, and automatic env var overlays." -} diff --git a/.semversioner/next-release/minor-20250122234420705255.json b/.semversioner/next-release/minor-20250122234420705255.json deleted file mode 100644 index 55e6ac83..00000000 --- a/.semversioner/next-release/minor-20250122234420705255.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Add NLP graph extraction." -} diff --git a/.semversioner/next-release/minor-20250212001549728393.json b/.semversioner/next-release/minor-20250212001549728393.json deleted file mode 100644 index fa6c4856..00000000 --- a/.semversioner/next-release/minor-20250212001549728393.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Rework the update output storage structure." -} diff --git a/.semversioner/next-release/minor-20250219193155428669.json b/.semversioner/next-release/minor-20250219193155428669.json deleted file mode 100644 index c0215592..00000000 --- a/.semversioner/next-release/minor-20250219193155428669.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Add LMM Manager and Factory, to support provider registration" -} diff --git a/.semversioner/next-release/minor-20250221001507100298.json b/.semversioner/next-release/minor-20250221001507100298.json deleted file mode 100644 index 5cfecc05..00000000 --- a/.semversioner/next-release/minor-20250221001507100298.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Add pipeline_start and pipeline_end callbacks." -} diff --git a/.semversioner/next-release/minor-20250225003631981779.json b/.semversioner/next-release/minor-20250225003631981779.json deleted file mode 100644 index 4a689a74..00000000 --- a/.semversioner/next-release/minor-20250225003631981779.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "minor", - "description": "Move embeddings snspshots to the workflow runner." -} diff --git a/.semversioner/next-release/patch-20250121150223319652.json b/.semversioner/next-release/patch-20250121150223319652.json deleted file mode 100644 index 704e78c5..00000000 --- a/.semversioner/next-release/patch-20250121150223319652.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "implemented multi-index querying for api layer" -} diff --git a/.semversioner/next-release/patch-20250121205226363912.json b/.semversioner/next-release/patch-20250121205226363912.json deleted file mode 100644 index 7597e075..00000000 --- a/.semversioner/next-release/patch-20250121205226363912.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix DRIFT search on Azure AI Search." -} diff --git a/.semversioner/next-release/patch-20250127224919088925.json b/.semversioner/next-release/patch-20250127224919088925.json deleted file mode 100644 index 5e0d8904..00000000 --- a/.semversioner/next-release/patch-20250127224919088925.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Add vector store id reference to embeddings config." -} diff --git a/.semversioner/next-release/patch-20250128230417263466.json b/.semversioner/next-release/patch-20250128230417263466.json deleted file mode 100644 index acd0756c..00000000 --- a/.semversioner/next-release/patch-20250128230417263466.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Require explicit azure auth settings when using AOI." -} diff --git a/.semversioner/next-release/patch-20250129215755119892.json b/.semversioner/next-release/patch-20250129215755119892.json deleted file mode 100644 index cfd8e6ac..00000000 --- a/.semversioner/next-release/patch-20250129215755119892.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix missing embeddings workflow in FastGraphRAG." -} diff --git a/.semversioner/next-release/patch-20250130182248267480.json b/.semversioner/next-release/patch-20250130182248267480.json deleted file mode 100644 index 0415bfce..00000000 --- a/.semversioner/next-release/patch-20250130182248267480.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix report generation recursion." -} diff --git a/.semversioner/next-release/patch-20250131200818198240.json b/.semversioner/next-release/patch-20250131200818198240.json deleted file mode 100644 index 3e5bb81d..00000000 --- a/.semversioner/next-release/patch-20250131200818198240.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "remove unused columns and change property document_attribute_columns to metadata" -} diff --git a/.semversioner/next-release/patch-20250204201317556265.json b/.semversioner/next-release/patch-20250204201317556265.json deleted file mode 100644 index c0171221..00000000 --- a/.semversioner/next-release/patch-20250204201317556265.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "multi index query cli support" -} diff --git a/.semversioner/next-release/patch-20250204235603673724.json b/.semversioner/next-release/patch-20250204235603673724.json deleted file mode 100644 index f4253841..00000000 --- a/.semversioner/next-release/patch-20250204235603673724.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix proper use of n_depth for drift search" -} diff --git a/.semversioner/next-release/patch-20250206203219915745.json b/.semversioner/next-release/patch-20250206203219915745.json deleted file mode 100644 index 218e0a87..00000000 --- a/.semversioner/next-release/patch-20250206203219915745.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "add option to prepend metadata into chunks" -} diff --git a/.semversioner/next-release/patch-20250210180318886210.json b/.semversioner/next-release/patch-20250210180318886210.json deleted file mode 100644 index 3b19d5c8..00000000 --- a/.semversioner/next-release/patch-20250210180318886210.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Add caching to NLP extractor." -} diff --git a/.semversioner/next-release/patch-20250210204532206223.json b/.semversioner/next-release/patch-20250210204532206223.json deleted file mode 100644 index fcb6ad6e..00000000 --- a/.semversioner/next-release/patch-20250210204532206223.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "cleanup query code duplication." -} diff --git a/.semversioner/next-release/patch-20250211001113319704.json b/.semversioner/next-release/patch-20250211001113319704.json deleted file mode 100644 index acf406ef..00000000 --- a/.semversioner/next-release/patch-20250211001113319704.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Separates graph pruning for differential usage." -} diff --git a/.semversioner/next-release/patch-20250211204342373101.json b/.semversioner/next-release/patch-20250211204342373101.json deleted file mode 100644 index 6552d55e..00000000 --- a/.semversioner/next-release/patch-20250211204342373101.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "update multi-index query to support new workflows" -} diff --git a/.semversioner/next-release/patch-20250212004406773499.json b/.semversioner/next-release/patch-20250212004406773499.json deleted file mode 100644 index 9566da19..00000000 --- a/.semversioner/next-release/patch-20250212004406773499.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Export NLP community reports prompt." -} diff --git a/.semversioner/next-release/patch-20250213164253709667.json b/.semversioner/next-release/patch-20250213164253709667.json deleted file mode 100644 index 213f2a9c..00000000 --- a/.semversioner/next-release/patch-20250213164253709667.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "add dynamic retry logic." -} diff --git a/.semversioner/next-release/patch-20250213222251109897.json b/.semversioner/next-release/patch-20250213222251109897.json deleted file mode 100644 index 9870ded8..00000000 --- a/.semversioner/next-release/patch-20250213222251109897.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Optimize data iteration by removing some iterrows from code" -} diff --git a/.semversioner/next-release/patch-20250214221550439648.json b/.semversioner/next-release/patch-20250214221550439648.json deleted file mode 100644 index f017d23e..00000000 --- a/.semversioner/next-release/patch-20250214221550439648.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Patch json mode for community reports" -} diff --git a/.semversioner/next-release/patch-20250218193057481504.json b/.semversioner/next-release/patch-20250218193057481504.json deleted file mode 100644 index 06fd5e4f..00000000 --- a/.semversioner/next-release/patch-20250218193057481504.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Tuck flow functions under their workflow modules." -} diff --git a/.semversioner/next-release/patch-20250219182755748457.json b/.semversioner/next-release/patch-20250219182755748457.json deleted file mode 100644 index af950732..00000000 --- a/.semversioner/next-release/patch-20250219182755748457.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Refactor config defaults from constants to type-safe, hierarchical dataclass." -} diff --git a/.semversioner/next-release/patch-20250221172728280340.json b/.semversioner/next-release/patch-20250221172728280340.json deleted file mode 100644 index c4fb80da..00000000 --- a/.semversioner/next-release/patch-20250221172728280340.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix StopAsyncIteration catch." -} diff --git a/.semversioner/next-release/patch-20250224201440103182.json b/.semversioner/next-release/patch-20250224201440103182.json deleted file mode 100644 index 94254328..00000000 --- a/.semversioner/next-release/patch-20250224201440103182.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Properly increment text unit IDs during updates." -} diff --git a/.semversioner/next-release/patch-20250224223906608414.json b/.semversioner/next-release/patch-20250224223906608414.json deleted file mode 100644 index 5668bca6..00000000 --- a/.semversioner/next-release/patch-20250224223906608414.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Use ModelProvider for query module" -} diff --git a/.semversioner/next-release/patch-20250225004511391743.json b/.semversioner/next-release/patch-20250225004511391743.json deleted file mode 100644 index 264f321b..00000000 --- a/.semversioner/next-release/patch-20250225004511391743.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Update fnllm. Remove unused libs." -} diff --git a/.semversioner/next-release/patch-20250225184914720441.json b/.semversioner/next-release/patch-20250225184914720441.json deleted file mode 100644 index 9e20f967..00000000 --- a/.semversioner/next-release/patch-20250225184914720441.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Use shared schema for final outputs." -} diff --git a/.semversioner/next-release/patch-20250225224555418932.json b/.semversioner/next-release/patch-20250225224555418932.json deleted file mode 100644 index ae8e98f8..00000000 --- a/.semversioner/next-release/patch-20250225224555418932.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "type": "patch", - "description": "Fix summarization over large datasets for inc indexing. Fix relationship summarization" -} diff --git a/CHANGELOG.md b/CHANGELOG.md index dafe5aac..af217660 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,44 @@ # Changelog Note: version releases in the 0.x.y range may introduce breaking changes. +## 2.0.0 + +- major: Add children to communities to avoid re-compute. +- major: Reorganize and rename workflows and their outputs. +- major: Rework API to accept callbacks. +- minor: Add LMM Manager and Factory, to support provider registration +- minor: Add NLP graph extraction. +- minor: Add pipeline_start and pipeline_end callbacks. +- minor: Move embeddings snapshots to the workflow runner. +- minor: Remove config inheritance, hydration, and automatic env var overlays. +- minor: Rework the update output storage structure. +- patch: Add caching to NLP extractor. +- patch: Add vector store id reference to embeddings config. +- patch: Export NLP community reports prompt. +- patch: Fix DRIFT search on Azure AI Search. +- patch: Fix StopAsyncIteration catch. +- patch: Fix missing embeddings workflow in FastGraphRAG. +- patch: Fix proper use of n_depth for drift search +- patch: Fix report generation recursion. +- patch: Fix summarization over large datasets for inc indexing. Fix relationship summarization +- patch: Optimize data iteration by removing some iterrows from code +- patch: Patch json mode for community reports +- patch: Properly increment text unit IDs during updates. +- patch: Refactor config defaults from constants to type-safe, hierarchical dataclass. +- patch: Require explicit azure auth settings when using AOI. +- patch: Separates graph pruning for differential usage. +- patch: Tuck flow functions under their workflow modules. +- patch: Update fnllm. Remove unused libs. +- patch: Use ModelProvider for query module +- patch: Use shared schema for final outputs. +- patch: add dynamic retry logic. +- patch: add option to prepend metadata into chunks +- patch: cleanup query code duplication. +- patch: implemented multi-index querying for api layer +- patch: multi index query cli support +- patch: remove unused columns and change property document_attribute_columns to metadata +- patch: update multi-index query to support new workflows + ## 1.2.0 - minor: Add Drift Reduce response and streaming endpoint diff --git a/pyproject.toml b/pyproject.toml index b85f935f..87b00712 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,7 +1,7 @@ [tool.poetry] name = "graphrag" # Maintainers: do not change the version here manually, use ./scripts/release.sh -version = "1.2.0" +version = "2.0.0" description = "GraphRAG: A graph-based retrieval-augmented generation (RAG) system." authors = [ "Alonso Guevara Fernández ",