[pull] main from microsoft:main

.github/workflows/gh-pages.yml

@@ -31,7 +31,7 @@ jobs:
 
       - name: Install dependencies
         shell: bash
-        run: uv sync --extra dev
+        run: uv sync
 
       - name: mkdocs build
         shell: bash

.github/workflows/python-ci.yml

@@ -67,7 +67,7 @@ jobs:
       - name: Install dependencies
         shell: bash
         run: |
-          uv sync --extra dev
+          uv sync
           uv pip install gensim
 
       - name: Check

.github/workflows/python-integration-tests.yml

@@ -67,7 +67,7 @@ jobs:
       - name: Install dependencies
         shell: bash
         run: |
-          uv sync --extra dev
+          uv sync
           uv pip install gensim
 
       - name: Build

.github/workflows/python-notebook-tests.yml

@@ -67,7 +67,7 @@ jobs:
       - name: Install dependencies
         shell: bash
         run: |
-          uv sync --extra dev
+          uv sync
           uv pip install gensim
 
       - name: Notebook Test

.github/workflows/python-smoke-tests.yml

@@ -72,7 +72,7 @@ jobs:
       - name: Install dependencies
         shell: bash
         run: |
-          uv sync --extra dev
+          uv sync
           uv pip install gensim
 
       - name: Build

.semversioner/next-release/patch-20251006231459594285.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Housekeeping toward 2.7."
+}

DEVELOPING.md

@@ -11,12 +11,8 @@
 
 ## Install Dependencies
 ```shell
-# (optional) create virtual environment
-uv venv --python 3.10
-source .venv/bin/activate
-
 # install python dependencies
-uv sync --extra dev
+uv sync
 ```
 
 ## Execute the indexing engine

docs/developing.md

@@ -12,12 +12,8 @@
 ## Install Dependencies
 
 ```sh
-# (optional) create virtual environment
-uv venv --python 3.10
-source .venv/bin/activate
-
 # install python dependencies
-uv sync --extra dev
+uv sync
 ```
 
 ## Execute the Indexing Engine

docs/examples_notebooks/api_overview.ipynb

@@ -67,6 +67,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# note that we expect this to fail on the deployed docs because the PROJECT_DIRECTORY is not set to a real location.\n",
+    "# if you run this notebook locally, make sure to point at a location containing your settings.yaml\n",
     "graphrag_config = load_config(Path(PROJECT_DIRECTORY))"
    ]
   },

docs/examples_notebooks/custom_vector_store.ipynb

@@ -61,6 +61,7 @@
     "import numpy as np\n",
     "import yaml\n",
     "\n",
+    "from graphrag.config.models.vector_store_schema_config import VectorStoreSchemaConfig\n",
     "from graphrag.data_model.types import TextEmbedder\n",
     "\n",
     "# GraphRAG vector store components\n",
@@ -147,14 +148,12 @@
     "        self.vectors: dict[str, np.ndarray] = {}\n",
     "        self.connected = False\n",
     "\n",
-    "        print(\n",
-    "            f\"🚀 SimpleInMemoryVectorStore initialized for collection: {self.collection_name}\"\n",
-    "        )\n",
+    "        print(f\"🚀 SimpleInMemoryVectorStore initialized for index: {self.index_name}\")\n",
     "\n",
     "    def connect(self, **kwargs: Any) -> None:\n",
     "        \"\"\"Connect to the vector storage (no-op for in-memory store).\"\"\"\n",
     "        self.connected = True\n",
-    "        print(f\"✅ Connected to in-memory vector store: {self.collection_name}\")\n",
+    "        print(f\"✅ Connected to in-memory vector store: {self.index_name}\")\n",
     "\n",
     "    def load_documents(\n",
     "        self, documents: list[VectorStoreDocument], overwrite: bool = True\n",
@@ -250,7 +249,7 @@
     "    def get_stats(self) -> dict[str, Any]:\n",
     "        \"\"\"Get statistics about the vector store (custom method).\"\"\"\n",
     "        return {\n",
-    "            \"collection_name\": self.collection_name,\n",
+    "            \"index_name\": self.index_name,\n",
     "            \"document_count\": len(self.documents),\n",
     "            \"vector_count\": len(self.vectors),\n",
     "            \"connected\": self.connected,\n",
@@ -353,11 +352,11 @@
    "outputs": [],
    "source": [
     "# Test creating vector store using the factory\n",
-    "vector_store_config = {\"collection_name\": \"test_collection\"}\n",
+    "schema = VectorStoreSchemaConfig(index_name=\"test_collection\")\n",
     "\n",
     "# Create vector store instance using factory\n",
     "vector_store = VectorStoreFactory.create_vector_store(\n",
-    "    CUSTOM_VECTOR_STORE_TYPE, vector_store_config\n",
+    "    CUSTOM_VECTOR_STORE_TYPE, vector_store_schema_config=schema\n",
     ")\n",
     "\n",
     "print(f\"✅ Created vector store instance: {type(vector_store).__name__}\")\n",
@@ -486,9 +485,13 @@
     "    print(\"🚀 Simulating GraphRAG pipeline with custom vector store...\\n\")\n",
     "\n",
     "    # 1. GraphRAG creates vector store using factory\n",
-    "    config = {\"collection_name\": \"graphrag_entities\", \"similarity_threshold\": 0.3}\n",
+    "    schema = VectorStoreSchemaConfig(index_name=\"graphrag_entities\")\n",
     "\n",
-    "    store = VectorStoreFactory.create_vector_store(CUSTOM_VECTOR_STORE_TYPE, config)\n",
+    "    store = VectorStoreFactory.create_vector_store(\n",
+    "        CUSTOM_VECTOR_STORE_TYPE,\n",
+    "        vector_store_schema_config=schema,\n",
+    "        similarity_threshold=0.3,\n",
+    "    )\n",
     "    store.connect()\n",
     "\n",
     "    print(\"✅ Step 1: Vector store created and connected\")\n",
@@ -549,7 +552,8 @@
     "    # Test 1: Basic functionality\n",
     "    print(\"Test 1: Basic functionality\")\n",
     "    store = VectorStoreFactory.create_vector_store(\n",
-    "        CUSTOM_VECTOR_STORE_TYPE, {\"collection_name\": \"test\"}\n",
+    "        CUSTOM_VECTOR_STORE_TYPE,\n",
+    "        vector_store_schema_config=VectorStoreSchemaConfig(index_name=\"test\"),\n",
     "    )\n",
     "    store.connect()\n",
     "\n",
@@ -597,7 +601,8 @@
     "    # Test 5: Error handling\n",
     "    print(\"\\nTest 5: Error handling\")\n",
     "    disconnected_store = VectorStoreFactory.create_vector_store(\n",
-    "        CUSTOM_VECTOR_STORE_TYPE, {\"collection_name\": \"test2\"}\n",
+    "        CUSTOM_VECTOR_STORE_TYPE,\n",
+    "        vector_store_schema_config=VectorStoreSchemaConfig(index_name=\"test2\"),\n",
     "    )\n",
     "\n",
     "    try:\n",
@@ -653,7 +658,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "graphrag-venv (3.10.18)",
+   "display_name": "graphrag",
    "language": "python",
    "name": "python3"
   },
@@ -667,7 +672,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.18"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,

docs/examples_notebooks/drift_search.ipynb

@@ -20,11 +20,11 @@
     "from pathlib import Path\n",
     "\n",
     "import pandas as pd\n",
-    "import tiktoken\n",
     "\n",
     "from graphrag.config.enums import ModelType\n",
     "from graphrag.config.models.drift_search_config import DRIFTSearchConfig\n",
     "from graphrag.config.models.language_model_config import LanguageModelConfig\n",
+    "from graphrag.config.models.vector_store_schema_config import VectorStoreSchemaConfig\n",
     "from graphrag.language_model.manager import ModelManager\n",
     "from graphrag.query.indexer_adapters import (\n",
     "    read_indexer_entities,\n",
@@ -37,6 +37,7 @@
     "    DRIFTSearchContextBuilder,\n",
     ")\n",
     "from graphrag.query.structured_search.drift_search.search import DRIFTSearch\n",
+    "from graphrag.tokenizer.get_tokenizer import get_tokenizer\n",
     "from graphrag.vector_stores.lancedb import LanceDBVectorStore\n",
     "\n",
     "INPUT_DIR = \"./inputs/operation dulce\"\n",
@@ -62,12 +63,16 @@
     "# load description embeddings to an in-memory lancedb vectorstore\n",
     "# to connect to a remote db, specify url and port values.\n",
     "description_embedding_store = LanceDBVectorStore(\n",
-    "    collection_name=\"default-entity-description\",\n",
+    "    vector_store_schema_config=VectorStoreSchemaConfig(\n",
+    "        index_name=\"default-entity-description\"\n",
+    "    ),\n",
     ")\n",
     "description_embedding_store.connect(db_uri=LANCEDB_URI)\n",
     "\n",
     "full_content_embedding_store = LanceDBVectorStore(\n",
-    "    collection_name=\"default-community-full_content\",\n",
+    "    vector_store_schema_config=VectorStoreSchemaConfig(\n",
+    "        index_name=\"default-community-full_content\"\n",
+    "    )\n",
     ")\n",
     "full_content_embedding_store.connect(db_uri=LANCEDB_URI)\n",
     "\n",
@@ -94,33 +99,33 @@
    "outputs": [],
    "source": [
     "api_key = os.environ[\"GRAPHRAG_API_KEY\"]\n",
-    "llm_model = os.environ[\"GRAPHRAG_LLM_MODEL\"]\n",
-    "embedding_model = os.environ[\"GRAPHRAG_EMBEDDING_MODEL\"]\n",
     "\n",
     "chat_config = LanguageModelConfig(\n",
     "    api_key=api_key,\n",
-    "    type=ModelType.OpenAIChat,\n",
-    "    model=llm_model,\n",
+    "    type=ModelType.Chat,\n",
+    "    model_provider=\"openai\",\n",
+    "    model=\"gpt-4.1\",\n",
     "    max_retries=20,\n",
     ")\n",
     "chat_model = ModelManager().get_or_create_chat_model(\n",
     "    name=\"local_search\",\n",
-    "    model_type=ModelType.OpenAIChat,\n",
+    "    model_type=ModelType.Chat,\n",
     "    config=chat_config,\n",
     ")\n",
     "\n",
-    "token_encoder = tiktoken.encoding_for_model(llm_model)\n",
+    "tokenizer = get_tokenizer(chat_config)\n",
     "\n",
     "embedding_config = LanguageModelConfig(\n",
     "    api_key=api_key,\n",
-    "    type=ModelType.OpenAIEmbedding,\n",
-    "    model=embedding_model,\n",
+    "    type=ModelType.Embedding,\n",
+    "    model_provider=\"openai\",\n",
+    "    model=\"text-embedding-3-small\",\n",
     "    max_retries=20,\n",
     ")\n",
     "\n",
     "text_embedder = ModelManager().get_or_create_embedding_model(\n",
     "    name=\"local_search_embedding\",\n",
-    "    model_type=ModelType.OpenAIEmbedding,\n",
+    "    model_type=ModelType.Embedding,\n",
     "    config=embedding_config,\n",
     ")"
    ]
@@ -173,12 +178,12 @@
     "    reports=reports,\n",
     "    entity_text_embeddings=description_embedding_store,\n",
     "    text_units=text_units,\n",
-    "    token_encoder=token_encoder,\n",
+    "    tokenizer=tokenizer,\n",
     "    config=drift_params,\n",
     ")\n",
     "\n",
     "search = DRIFTSearch(\n",
-    "    model=chat_model, context_builder=context_builder, token_encoder=token_encoder\n",
+    "    model=chat_model, context_builder=context_builder, tokenizer=tokenizer\n",
     ")"
    ]
   },
@@ -212,7 +217,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "graphrag",
    "language": "python",
    "name": "python3"
   },
@@ -226,7 +231,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,

docs/examples_notebooks/global_search.ipynb

@@ -19,7 +19,6 @@
     "import os\n",
     "\n",
     "import pandas as pd\n",
-    "import tiktoken\n",
     "\n",
     "from graphrag.config.enums import ModelType\n",
     "from graphrag.config.models.language_model_config import LanguageModelConfig\n",
@@ -32,7 +31,8 @@
     "from graphrag.query.structured_search.global_search.community_context import (\n",
     "    GlobalCommunityContext,\n",
     ")\n",
-    "from graphrag.query.structured_search.global_search.search import GlobalSearch"
+    "from graphrag.query.structured_search.global_search.search import GlobalSearch\n",
+    "from graphrag.tokenizer.get_tokenizer import get_tokenizer"
    ]
   },
   {
@@ -58,21 +58,21 @@
    "outputs": [],
    "source": [
     "api_key = os.environ[\"GRAPHRAG_API_KEY\"]\n",
-    "llm_model = os.environ[\"GRAPHRAG_LLM_MODEL\"]\n",
     "\n",
     "config = LanguageModelConfig(\n",
     "    api_key=api_key,\n",
-    "    type=ModelType.OpenAIChat,\n",
-    "    model=llm_model,\n",
+    "    type=ModelType.Chat,\n",
+    "    model_provider=\"openai\",\n",
+    "    model=\"gpt-4.1\",\n",
     "    max_retries=20,\n",
     ")\n",
     "model = ModelManager().get_or_create_chat_model(\n",
     "    name=\"global_search\",\n",
-    "    model_type=ModelType.OpenAIChat,\n",
+    "    model_type=ModelType.Chat,\n",
     "    config=config,\n",
     ")\n",
     "\n",
-    "token_encoder = tiktoken.encoding_for_model(llm_model)"
+    "tokenizer = get_tokenizer(config)"
    ]
   },
   {
@@ -142,7 +142,7 @@
     "    community_reports=reports,\n",
     "    communities=communities,\n",
     "    entities=entities,  # default to None if you don't want to use community weights for ranking\n",
-    "    token_encoder=token_encoder,\n",
+    "    tokenizer=tokenizer,\n",
     ")"
    ]
   },
@@ -193,7 +193,7 @@
     "search_engine = GlobalSearch(\n",
     "    model=model,\n",
     "    context_builder=context_builder,\n",
-    "    token_encoder=token_encoder,\n",
+    "    tokenizer=tokenizer,\n",
     "    max_data_tokens=12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)\n",
     "    map_llm_params=map_llm_params,\n",
     "    reduce_llm_params=reduce_llm_params,\n",
@@ -241,7 +241,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "graphrag",
    "language": "python",
    "name": "python3"
   },
@@ -255,7 +255,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,