[pull] main from microsoft:main

.semversioner/3.0.2.json

@@ -0,0 +1,50 @@
+{
+  "changes": [
+    {
+      "description": "Add CSVTableProvider",
+      "type": "patch"
+    },
+    {
+      "description": "Add DataReader class for typed dataframe loading from TableProvider across indexing workflows and query CLI",
+      "type": "patch"
+    },
+    {
+      "description": "Add TableProvider abstraction for table-based storage operations",
+      "type": "patch"
+    },
+    {
+      "description": "Add async iterator support to InputReader and use it in load_input_documents and load_update_documents workflows.",
+      "type": "patch"
+    },
+    {
+      "description": "Add table provider factory.",
+      "type": "patch"
+    },
+    {
+      "description": "Fix missed py 3.13.",
+      "type": "patch"
+    },
+    {
+      "description": "Move document ID, human_readable_id, and raw_data initialization from create_final_documents into load_input_documents and load_update_documents.",
+      "type": "patch"
+    },
+    {
+      "description": "Remove NetworkX dependency from graph utilities; move to DataFrame-based implementations in graphrag.graphs package.",
+      "type": "patch"
+    },
+    {
+      "description": "Remove unnecessary response format check. Fixes: #2203",
+      "type": "patch"
+    },
+    {
+      "description": "add profiling to get memory usage",
+      "type": "patch"
+    },
+    {
+      "description": "update notebooks",
+      "type": "patch"
+    }
+  ],
+  "created_at": "2026-02-13T18:01:44+00:00",
+  "version": "3.0.2"
+}

.semversioner/next-release/patch-20260212002508389038.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "add streamming to the two first workflows"
+}

.semversioner/next-release/patch-20260213160631396575.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "add csv table smoke tests"
+}

CHANGELOG.md

@@ -1,6 +1,20 @@
 # Changelog
 Note: version releases in the 0.x.y range may introduce breaking changes.
 
+## 3.0.2
+
+- patch: Add CSVTableProvider
+- patch: Add DataReader class for typed dataframe loading from TableProvider across indexing workflows and query CLI
+- patch: Add TableProvider abstraction for table-based storage operations
+- patch: Add async iterator support to InputReader and use it in load_input_documents and load_update_documents workflows.
+- patch: Add table provider factory.
+- patch: Fix missed py 3.13.
+- patch: Move document ID, human_readable_id, and raw_data initialization from create_final_documents into load_input_documents and load_update_documents.
+- patch: Remove NetworkX dependency from graph utilities; move to DataFrame-based implementations in graphrag.graphs package.
+- patch: Remove unnecessary response format check. Fixes: #2203
+- patch: add profiling to get memory usage
+- patch: update notebooks
+
 ## 3.0.1
 
 - patch: Fix missing dependency.

packages/graphrag-cache/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "graphrag-cache"
-version = "3.0.1"
+version = "3.0.2"
 description = "GraphRAG cache package."
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},
@@ -31,8 +31,8 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "graphrag-common==3.0.1",
-    "graphrag-storage==3.0.1",
+    "graphrag-common==3.0.2",
+    "graphrag-storage==3.0.2",
 ]
 
 [project.urls]

packages/graphrag-chunking/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "graphrag-chunking"
-version = "3.0.1"
+version = "3.0.2"
 description = "Chunking utilities for GraphRAG"
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},
@@ -30,7 +30,7 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "graphrag-common==3.0.1",
+    "graphrag-common==3.0.2",
     "pydantic~=2.10",
 ]
 

packages/graphrag-common/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "graphrag-common"
-version = "3.0.1"
+version = "3.0.2"
 description = "Common utilities and types for GraphRAG"
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},

packages/graphrag-input/graphrag_input/csv.py

@@ -5,12 +5,18 @@
 
 import csv
 import logging
+import sys
 
 from graphrag_input.structured_file_reader import StructuredFileReader
 from graphrag_input.text_document import TextDocument
 
 logger = logging.getLogger(__name__)
 
+try:
+    csv.field_size_limit(sys.maxsize)
+except OverflowError:
+    csv.field_size_limit(100 * 1024 * 1024)
+
 
 class CSVFileReader(StructuredFileReader):
     """Reader implementation for csv files."""

packages/graphrag-input/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "graphrag-input"
-version = "3.0.1"
+version = "3.0.2"
 description = "Input document loading utilities for GraphRAG"
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},
@@ -30,8 +30,8 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "graphrag-common==3.0.1",
-    "graphrag-storage==3.0.1    ",
+    "graphrag-common==3.0.2",
+    "graphrag-storage==3.0.2    ",
     "pydantic~=2.10",
     "markitdown~=0.1.0",
     "markitdown[pdf]"

packages/graphrag-llm/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "graphrag-llm"
-version = "3.0.1"
+version = "3.0.2"
 description = "GraphRAG LLM package."
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},
@@ -33,8 +33,8 @@ classifiers = [
 ]
 dependencies = [
     "azure-identity~=1.25",
-    "graphrag-cache==3.0.1",
-    "graphrag-common==3.0.1",
+    "graphrag-cache==3.0.2",
+    "graphrag-common==3.0.2",
     "jinja2~=3.1",
     "litellm~=1.80",
     "nest-asyncio2~=1.7",

packages/graphrag-storage/graphrag_storage/file_storage.py

@@ -144,6 +144,10 @@ async def get_creation_date(self, key: str) -> str:
 
         return get_timestamp_formatted_with_local_tz(creation_time_utc)
 
+    def get_path(self, key: str) -> Path:
+        """Get the full file path for a key (for streaming access)."""
+        return _join_path(self._base_dir, key)
+
 
 def _join_path(file_path: Path, file_name: str) -> Path:
     """Join a path and a file. Independent of the OS."""

packages/graphrag-storage/graphrag_storage/tables/__init__.py

@@ -3,6 +3,7 @@
 
 """Table provider module for GraphRAG storage."""
 
+from .table import Table
 from .table_provider import TableProvider
 
-__all__ = ["TableProvider"]
+__all__ = ["Table", "TableProvider"]