refactoring

Author: KSemenenko

.editorconfig

@@ -1,9 +1,12 @@
 # Repository Guidelines
 
-# Rules to follow
+## Rules to follow
 - Always run `dotnet build GraphRag.slnx` (or the relevant project) before executing any `dotnet test` command.
 - Default to the latest available versions (e.g., Apache AGE `latest`) when selecting dependencies, per user request ("тобі треба latest").
 - Do not create or rely on fake database stores (e.g., `FakePostgresGraphStore`); all tests must use real connectors/backing services.
+- Keep default prompts in static C# classes; do not rely on prompt files under `prompts/` for built-in templates.
+- Register language models through Microsoft.Extensions.AI keyed services; avoid bespoke `LanguageModelConfig` providers.
+- Always run `dotnet format GraphRag.slnx` before finishing work.
 
 # Conversations
 any resulting updates to agents.md should go under the section "## Rules to follow"

AGENTS.md

@@ -3,6 +3,7 @@
     <PackageVersion Include="coverlet.collector" Version="6.0.4" />
     <PackageVersion Include="Microsoft.Azure.Cosmos" Version="3.54.0" />
     <PackageVersion Include="Microsoft.Extensions.Configuration" Version="9.0.10" />
+    <PackageVersion Include="Microsoft.Extensions.Caching.Memory" Version="9.0.10" />
     <PackageVersion Include="Microsoft.Extensions.DependencyInjection" Version="9.0.10" />
     <PackageVersion Include="Microsoft.Extensions.Logging" Version="9.0.10" />
     <PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="9.0.10" />
@@ -20,4 +21,4 @@
     <PackageVersion Include="xunit" Version="2.9.3" />
     <PackageVersion Include="xunit.runner.visualstudio" Version="3.1.5" />
   </ItemGroup>
-</Project>
+</Project>

Directory.Packages.props

@@ -93,13 +93,55 @@ graphrag/
 
 ---
 
+## Pipeline Cache
+
+GraphRag exposes the `IPipelineCache` abstraction. To use the built-in in-memory cache, register it alongside the standard ASP.NET Core services:
+
+```csharp
+using GraphRag.Cache;
+
+builder.Services.AddMemoryCache();
+builder.Services.AddSingleton<IPipelineCache, MemoryPipelineCache>();
+```
+
+Prefer a different backend? Implement `IPipelineCache` yourself and register it through DI—the pipeline will pick up your custom cache automatically.
+
+---
+
+## Language Model Registration
+
+GraphRAG delegates language-model configuration to [Microsoft.Extensions.AI](https://learn.microsoft.com/dotnet/ai/overview). Register keyed clients for every `ModelId` you reference in configuration—pick any string key that matches your config:
+
+```csharp
+using Azure;
+using Azure.AI.OpenAI;
+using GraphRag.Config;
+using Microsoft.Extensions.AI;
+
+var openAi = new OpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+const string chatModelId = "chat_model";
+const string embeddingModelId = "embedding_model";
+
+builder.Services.AddKeyedSingleton<IChatClient>(
+    chatModelId,
+    _ => openAi.GetChatClient(chatDeployment));
+
+builder.Services.AddKeyedSingleton<IEmbeddingGenerator<string, Embedding>>(
+    embeddingModelId,
+    _ => openAi.GetEmbeddingClient(embeddingDeployment));
+```
+
+Rate limits, retries, and other policies should be configured when you create these clients (for example by wrapping them with `Polly` handlers). `GraphRagConfig.Models` simply tracks the set of model keys that have been registered so overrides can validate references.
+
+---
+
 ## Indexing, Querying, and Prompt Tuning Alignment
 
 The .NET port mirrors the [GraphRAG indexing architecture](https://microsoft.github.io/graphrag/index/overview/) and its query workflows so downstream applications retain parity with the Python reference implementation.
 
 - **Indexing overview.** Workflows such as `extract_graph`, `create_communities`, and `community_summaries` map 1:1 to the [default data flow](https://microsoft.github.io/graphrag/index/default_dataflow/) and persist the same tables (`text_units`, `entities`, `relationships`, `communities`, `community_reports`, `covariates`). The new prompt template loader honours manual or auto-tuned prompts before falling back to the stock templates in `prompts/`.
 - **Query capabilities.** The query pipeline retains global search, local search, drift search, and question generation semantics described in the [GraphRAG query overview](https://microsoft.github.io/graphrag/query/overview/). Each orchestrator continues to assemble context from the indexed tables so you can reference [global](https://microsoft.github.io/graphrag/query/global_search/) or [local](https://microsoft.github.io/graphrag/query/local_search/) narratives interchangeably.
-- **Prompt tuning.** GraphRAG’s [manual](https://microsoft.github.io/graphrag/prompt_tuning/manual_prompt_tuning/) and [auto](https://microsoft.github.io/graphrag/prompt_tuning/auto_prompt_tuning/) strategies are surfaced through `GraphRagConfig.PromptTuning`. Store custom templates under `prompts/` or point `PromptTuning.Manual.Directory`/`PromptTuning.Auto.Directory` at your tuning outputs. Files follow the stage keys documented in `docs/indexing-and-query.md` (for example, `index/community_reports/system.txt` overrides the community summary system prompt). Templates can use placeholders such as `{{max_length}}`, `{{max_entities}}`, and `{{entities}}`.
+- **Prompt tuning.** GraphRAG’s [manual](https://microsoft.github.io/graphrag/prompt_tuning/manual_prompt_tuning/) and [auto](https://microsoft.github.io/graphrag/prompt_tuning/auto_prompt_tuning/) strategies are surfaced through `GraphRagConfig.PromptTuning`. Store custom templates under `prompts/` or point `PromptTuning.Manual.Directory`/`PromptTuning.Auto.Directory` at your tuning outputs. You can also skip files entirely by assigning inline text (multi-line or prefixed with `inline:`) to workflow prompt properties. Stage keys and placeholders are documented in `docs/indexing-and-query.md`.
 
 See [`docs/indexing-and-query.md`](docs/indexing-and-query.md) for a deeper mapping between the .NET workflows and the research publications underpinning GraphRAG.
 

README.md

@@ -13,6 +13,37 @@ GraphRAG for .NET keeps feature parity with the Python reference project describ
 - **Storage schema.** Tables share the column layout described under [index outputs](https://microsoft.github.io/graphrag/index/outputs/). The new strongly-typed records (`CommunityRecord`, `CovariateRecord`, etc.) mirror the JSON representation used by the Python implementation.
 - **Cluster configuration.** `GraphRagConfig.ClusterGraph` exposes the same knobs as the Python `cluster_graph` settings, enabling largest-component filtering and deterministic seeding.
 
+## Language Model Registration
+
+Workflows resolve language models from the DI container via [Microsoft.Extensions.AI](https://learn.microsoft.com/dotnet/ai/overview). Register keyed services for every `ModelId` you plan to reference:
+
+```csharp
+using Azure;
+using Azure.AI.OpenAI;
+using GraphRag.Config;
+using Microsoft.Extensions.AI;
+
+var openAi = new OpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+const string chatModelId = "chat_model";
+const string embeddingModelId = "embedding_model";
+
+services.AddKeyedSingleton<IChatClient>(chatModelId, _ => openAi.GetChatClient(chatDeployment));
+services.AddKeyedSingleton<IEmbeddingGenerator<string, Embedding>>(embeddingModelId, _ => openAi.GetEmbeddingClient(embeddingDeployment));
+```
+
+Configure retries, rate limits, and logging when you construct the concrete clients. `GraphRagConfig.Models` simply records the set of registered keys so configuration overrides can validate references.
+
+## Pipeline Cache
+
+`IPipelineCache` is intentionally infrastructure-neutral. To mirror ASP.NET Core's in-memory behaviour, register the built-in cache services alongside the provided adapter:
+
+```csharp
+services.AddMemoryCache();
+services.AddSingleton<IPipelineCache, MemoryPipelineCache>();
+```
+
+Need Redis or something else? Implement `IPipelineCache` yourself and register it through DI; the pipeline will automatically consume your custom cache.
+
 ## Query Capabilities
 
 The query layer ports the orchestrators documented in the [GraphRAG query overview](https://microsoft.github.io/graphrag/query/overview/):
@@ -34,6 +65,7 @@ Manual and auto prompt tuning are both available without code changes:
 2. **Auto tuning** integrates the outputs documented in [auto prompt tuning](https://microsoft.github.io/graphrag/prompt_tuning/auto_prompt_tuning/).
    - Point `GraphRagConfig.PromptTuning.Auto.Directory` at the folder containing the generated prompts and set `Enabled = true`.
    - The runtime prefers explicit paths from workflow configs, then manual overrides, then auto-tuned files, and finally the built-in defaults in `prompts/`.
+3. **Inline overrides** can be injected directly from code: set `ExtractGraphConfig.SystemPrompt`, `ExtractGraphConfig.Prompt`, or the equivalent properties to either a multi-line string or a value prefixed with `inline:`. Inline values bypass template file lookups and are used as-is.
 
 ### Stage Keys and Placeholders
 
@@ -51,7 +83,7 @@ Placeholders are replaced at runtime with values drawn from workflow configurati
 - `{{max_length}}` → `CommunityReportsConfig.MaxLength`
 - `{{entities}}` → bullet list of entity titles and descriptions
 
-If a template is omitted, the runtime falls back to the built-in prompts stored under `prompts/` and bundled with the repository.
+If a template is omitted, the runtime falls back to the built-in prompts defined in `GraphRagPromptLibrary`.
 
 ## Integration Tests
 

docs/indexing-and-query.md

@@ -1,32 +1,18 @@
-using System;
-using System.Collections.Generic;
-using System.Linq;
 using System.Runtime.CompilerServices;
-using System.Threading;
-using System.Threading.Tasks;
 using GraphRag.Graphs;
 using Microsoft.Azure.Cosmos;
 using Microsoft.Azure.Cosmos.Linq;
 using Microsoft.Extensions.Logging;
 
 namespace GraphRag.Storage.Cosmos;
 
-public sealed class CosmosGraphStore : IGraphStore
+public sealed class CosmosGraphStore(CosmosClient client, string databaseId, string nodesContainerId, string edgesContainerId, ILogger<CosmosGraphStore> logger) : IGraphStore
 {
-    private readonly CosmosClient _client;
-    private readonly string _databaseId;
-    private readonly string _nodesContainerId;
-    private readonly string _edgesContainerId;
-    private readonly ILogger<CosmosGraphStore> _logger;
-
-    public CosmosGraphStore(CosmosClient client, string databaseId, string nodesContainerId, string edgesContainerId, ILogger<CosmosGraphStore> logger)
-    {
-        _client = client ?? throw new ArgumentNullException(nameof(client));
-        _databaseId = databaseId ?? throw new ArgumentNullException(nameof(databaseId));
-        _nodesContainerId = nodesContainerId ?? throw new ArgumentNullException(nameof(nodesContainerId));
-        _edgesContainerId = edgesContainerId ?? throw new ArgumentNullException(nameof(edgesContainerId));
-        _logger = logger ?? throw new ArgumentNullException(nameof(logger));
-    }
+    private readonly CosmosClient _client = client ?? throw new ArgumentNullException(nameof(client));
+    private readonly string _databaseId = databaseId ?? throw new ArgumentNullException(nameof(databaseId));
+    private readonly string _nodesContainerId = nodesContainerId ?? throw new ArgumentNullException(nameof(nodesContainerId));
+    private readonly string _edgesContainerId = edgesContainerId ?? throw new ArgumentNullException(nameof(edgesContainerId));
+    private readonly ILogger<CosmosGraphStore> _logger = logger ?? throw new ArgumentNullException(nameof(logger));
 
     public async Task InitializeAsync(CancellationToken cancellationToken = default)
     {
@@ -60,7 +46,7 @@ public async Task UpsertRelationshipAsync(string sourceId, string targetId, stri
     public IAsyncEnumerable<GraphRelationship> GetOutgoingRelationshipsAsync(string sourceId, CancellationToken cancellationToken = default)
     {
         ArgumentException.ThrowIfNullOrWhiteSpace(sourceId);
-        return Fetch();
+        return Fetch(cancellationToken);
 
         async IAsyncEnumerable<GraphRelationship> Fetch([EnumeratorCancellation] CancellationToken token = default)
         {

src/ManagedCode.GraphRag.CosmosDb/CosmosGraphStore.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Text.Json;
 using GraphRag.Graphs;
 using Microsoft.Azure.Cosmos;

src/ManagedCode.GraphRag.CosmosDb/ServiceCollectionExtensions.cs

@@ -1,31 +1,21 @@
-using System.IO;
-using System.Text;
 using System.Text.Json;
 using Microsoft.Azure.Cosmos;
 
 namespace GraphRag.Storage.Cosmos;
 
-internal sealed class SystemTextJsonCosmosSerializer : CosmosSerializer
+internal sealed class SystemTextJsonCosmosSerializer(JsonSerializerOptions? options = null) : CosmosSerializer
 {
     private static readonly JsonSerializerOptions DefaultOptions = new(JsonSerializerDefaults.Web)
     {
         PropertyNamingPolicy = JsonNamingPolicy.CamelCase,
         WriteIndented = false
     };
 
-    private readonly JsonSerializerOptions _options;
-
-    public SystemTextJsonCosmosSerializer(JsonSerializerOptions? options = null)
-    {
-        _options = options ?? DefaultOptions;
-    }
+    private readonly JsonSerializerOptions _options = options ?? DefaultOptions;
 
     public override T FromStream<T>(Stream stream)
     {
-        if (stream is null)
-        {
-            throw new ArgumentNullException(nameof(stream));
-        }
+        ArgumentNullException.ThrowIfNull(stream);
 
         if (typeof(T) == typeof(Stream))
         {

src/ManagedCode.GraphRag.CosmosDb/SystemTextJsonCosmosSerializer.cs

@@ -1,31 +1,20 @@
-using System;
-using System.Collections.Generic;
-using System.Linq;
 using System.Runtime.CompilerServices;
-using System.Threading;
-using System.Threading.Tasks;
 using GraphRag.Graphs;
 using Microsoft.Extensions.Logging;
 using Neo4j.Driver;
 
 namespace GraphRag.Storage.Neo4j;
 
-public sealed class Neo4jGraphStore : IGraphStore, IAsyncDisposable
+public sealed class Neo4jGraphStore(IDriver driver, ILogger<Neo4jGraphStore> logger) : IGraphStore, IAsyncDisposable
 {
-    private readonly IDriver _driver;
-    private readonly ILogger<Neo4jGraphStore> _logger;
+    private readonly IDriver _driver = driver ?? throw new ArgumentNullException(nameof(driver));
+    private readonly ILogger<Neo4jGraphStore> _logger = logger ?? throw new ArgumentNullException(nameof(logger));
 
     public Neo4jGraphStore(string uri, string username, string password, ILogger<Neo4jGraphStore> logger)
         : this(GraphDatabase.Driver(uri, AuthTokens.Basic(username, password)), logger)
     {
     }
 
-    public Neo4jGraphStore(IDriver driver, ILogger<Neo4jGraphStore> logger)
-    {
-        _driver = driver ?? throw new ArgumentNullException(nameof(driver));
-        _logger = logger ?? throw new ArgumentNullException(nameof(logger));
-    }
-
     public async Task InitializeAsync(CancellationToken cancellationToken = default)
     {
         cancellationToken.ThrowIfCancellationRequested();
@@ -64,7 +53,7 @@ public IAsyncEnumerable<GraphRelationship> GetOutgoingRelationshipsAsync(string
     {
         ArgumentException.ThrowIfNullOrWhiteSpace(sourceId);
         cancellationToken.ThrowIfCancellationRequested();
-        return Fetch();
+        return Fetch(cancellationToken);
 
         async IAsyncEnumerable<GraphRelationship> Fetch([EnumeratorCancellation] CancellationToken token = default)
         {

src/ManagedCode.GraphRag.Neo4j/Neo4jGraphStore.cs

@@ -1,4 +1,3 @@
-using System;
 using GraphRag.Graphs;
 using Microsoft.Extensions.DependencyInjection;
 using Microsoft.Extensions.Logging;