Merge branch 'main' into docs/reasoning-models

Author: natoverse

.semversioner/2.2.0.json

@@ -0,0 +1,46 @@
+{
+  "changes": [
+    {
+      "description": "Support OpenAI reasoning models.",
+      "type": "minor"
+    },
+    {
+      "description": "Add option to snapshot raw extracted graph tables.",
+      "type": "patch"
+    },
+    {
+      "description": "Added batching logic to the prompt tuning autoselection embeddings workflow",
+      "type": "patch"
+    },
+    {
+      "description": "Align config classes and docs better.",
+      "type": "patch"
+    },
+    {
+      "description": "Align embeddings table loading with configured fields.",
+      "type": "patch"
+    },
+    {
+      "description": "Brings parity with our latest NLP extraction approaches.",
+      "type": "patch"
+    },
+    {
+      "description": "Fix fnllm to 0.2.3",
+      "type": "patch"
+    },
+    {
+      "description": "Fixes to basic search.",
+      "type": "patch"
+    },
+    {
+      "description": "Update llm args for consistency.",
+      "type": "patch"
+    },
+    {
+      "description": "add vector store integration tests",
+      "type": "patch"
+    }
+  ],
+  "created_at": "2025-04-25T23:30:57+00:00",
+  "version": "2.2.0"
+}

.semversioner/next-release/minor-20250325000101658359.json

@@ -1,6 +1,19 @@
 # Changelog
 Note: version releases in the 0.x.y range may introduce breaking changes.
 
+## 2.2.0
+
+- minor: Support OpenAI reasoning models.
+- patch: Add option to snapshot raw extracted graph tables.
+- patch: Added batching logic to the prompt tuning autoselection embeddings workflow
+- patch: Align config classes and docs better.
+- patch: Align embeddings table loading with configured fields.
+- patch: Brings parity with our latest NLP extraction approaches.
+- patch: Fix fnllm to 0.2.3
+- patch: Fixes to basic search.
+- patch: Update llm args for consistency.
+- patch: add vector store integration tests
+
 ## 2.1.0
 
 - minor: Add support for JSON input files.

.semversioner/next-release/patch-20250304195925818723.json

@@ -253,7 +253,7 @@ Parameters for manual graph pruning. This can be used to optimize the modularity
 - max_node_freq_std **float | None** - The maximum standard deviation of node frequency to allow.
 - min_node_degree **int** - The minimum node degree to allow.
 - max_node_degree_std **float | None** - The maximum standard deviation of node degree to allow.
-- min_edge_weight_pct **int** - The minimum edge weight percentile to allow.
+- min_edge_weight_pct **float** - The minimum edge weight percentile to allow.
 - remove_ego_nodes **bool** - Remove ego nodes.
 - lcc_only **bool** - Only use largest connected component.
 

.semversioner/next-release/patch-20250318015236952876.json

@@ -19,6 +19,9 @@
     ReportingType,
     TextEmbeddingTarget,
 )
+from graphrag.index.operations.build_noun_graph.np_extractors.stop_words import (
+    EN_STOP_WORDS,
+)
 from graphrag.vector_stores.factory import VectorStoreType
 
 DEFAULT_OUTPUT_BASE_DIR = "output"
@@ -42,6 +45,7 @@ class BasicSearchDefaults:
 
     prompt: None = None
     k: int = 10
+    max_context_tokens: int = 12_000
     chat_model_id: str = DEFAULT_CHAT_MODEL_ID
     embedding_model_id: str = DEFAULT_EMBEDDING_MODEL_ID
 
@@ -185,7 +189,7 @@ class TextAnalyzerDefaults:
     max_word_length: int = 15
     word_delimiter: str = " "
     include_named_entities: bool = True
-    exclude_nouns: None = None
+    exclude_nouns: list[str] = field(default_factory=lambda: EN_STOP_WORDS)
     exclude_entity_tags: list[str] = field(default_factory=lambda: ["DATE"])
     exclude_pos_tags: list[str] = field(
         default_factory=lambda: ["DET", "PRON", "INTJ", "X"]
@@ -316,8 +320,8 @@ class PruneGraphDefaults:
     max_node_freq_std: None = None
     min_node_degree: int = 1
     max_node_degree_std: None = None
-    min_edge_weight_pct: int = 40
-    remove_ego_nodes: bool = False
+    min_edge_weight_pct: float = 40.0
+    remove_ego_nodes: bool = True
     lcc_only: bool = False
 
 
@@ -338,6 +342,7 @@ class SnapshotsDefaults:
 
     embeddings: bool = False
     graphml: bool = False
+    raw_graph: bool = False
 
 
 @dataclass