mostlylucid.mockllmapi 1.0.2

mostlylucid.mockllmapi

A lightweight ASP.NET Core middleware for generating realistic mock API responses using local LLMs (via Ollama). Add intelligent mock endpoints to any project with just 2 lines of code!

Features

• 🚀 Super Simple: Addmostlylucid.mockllmapi() + Mapmostlylucid.mockllmapi("/api/mock") = instant mock API
• ⚙️ Configurable: appsettings.json or inline configuration
• 🎨 Shape Control: Specify exact JSON structure via header, query param, or request body
• 📡 Real-time Streaming: Server-Sent Events (SSE) support with progressive JSON generation
• 🎲 Highly Variable Data: Each request generates completely different realistic data
• 🔧 All HTTP Methods: Supports GET, POST, PUT, DELETE, PATCH
• 🌐 Wildcard Routing: Any path under your chosen endpoint works
• 📦 NuGet Package: Easy to add to existing projects

Quick Start

Installation

dotnet add package mostlylucid.mockllmapi

Prerequisites

1. Install .NET 8.0 SDK or later
2. Install Ollama and pull a model:

   ollama pull llama3
   

Basic Usage

Program.cs:

using mostlylucid.mockllmapi;

var builder = WebApplication.CreateBuilder(args);

// Add LLMock API services
builder.Services.Addmostlylucid.mockllmapi(builder.Configuration);

var app = builder.Build();

// Map mock endpoints at /api/mock
app.Mapmostlylucid.mockllmapi("/api/mock");

app.Run();

appsettings.json:

{
  "mostlylucid.mockllmapi": {
    "BaseUrl": "http://localhost:11434/v1/",
    "ModelName": "llama3",
    "Temperature": 1.2
  }
}

That's it! Now all requests to /api/mock/** return intelligent mock data.

Configuration Options

Via appsettings.json (Recommended)

{
  "mostlylucid.mockllmapi": {
    "BaseUrl": "http://localhost:11434/v1/",
    "ModelName": "llama3",
    "Temperature": 1.2,
    "TimeoutSeconds": 30,
    "EnableVerboseLogging": false,
    "CustomPromptTemplate": null
  }
}

Via Code

builder.Services.Addmostlylucid.mockllmapi(options =>
{
    options.BaseUrl = "http://localhost:11434/v1/";
    options.ModelName = "mixtral";
    options.Temperature = 1.5;
    options.TimeoutSeconds = 60;
});

Custom Endpoint Patterns

// Default: /api/mock/** and /api/mock/stream/**
app.Mapmostlylucid.mockllmapi("/api/mock");

// Custom pattern
app.Mapmostlylucid.mockllmapi("/demo");
// Creates: /demo/** and /demo/stream/**

// Without streaming
app.Mapmostlylucid.mockllmapi("/api/mock", includeStreaming: false);

Usage Examples

Basic Request

curl http://localhost:5000/api/mock/users?limit=5

Returns realistic user data generated by the LLM.

With Shape Control

curl -X POST http://localhost:5000/api/mock/orders \
  -H "X-Response-Shape: {\"orderId\":\"string\",\"total\":0.0,\"items\":[{\"sku\":\"string\",\"qty\":0}]}" \
  -H "Content-Type: application/json" \
  -d '{"customerId":"cus_123"}'

LLM generates data matching your exact shape specification.

Streaming

curl -N http://localhost:5000/api/mock/stream/products?category=electronics \
  -H "Accept: text/event-stream"

Returns Server-Sent Events as JSON is generated:

data: {"chunk":"{","done":false}
data: {"chunk":"\"id\"","done":false}
...
data: {"content":"{full json here}","done":true}

Advanced Features

Custom Prompt Templates

Override the default prompts with your own:

{
  "mostlylucid.mockllmapi": {
    "CustomPromptTemplate": "Generate mock data for {method} {path}. Body: {body}. Use seed: {randomSeed}"
  }
}

Available placeholders:

• {method} - HTTP method (GET, POST, etc.)
• {path} - Full request path with query string
• {body} - Request body
• {randomSeed} - Generated random seed (GUID)
• {timestamp} - Unix timestamp
• {shape} - Shape specification (if provided)

Multiple Instances

Mount multiple mock APIs with different configurations:

// Development data with high randomness
builder.Services.Addmostlylucid.mockllmapi("Dev", options =>
{
    options.Temperature = 1.5;
    options.ModelName = "llama3";
});

// Stable test data
builder.Services.Addmostlylucid.mockllmapi("Test", options =>
{
    options.Temperature = 0.3;
    options.ModelName = "llama3";
});

app.Mapmostlylucid.mockllmapi("/api/dev");
app.Mapmostlylucid.mockllmapi("/api/test");

Shape Specification

Three ways to control response structure:

1. Header (recommended): X-Response-Shape: {"field":"type"}
2. Query param: ?shape=%7B%22field%22%3A%22type%22%7D (URL-encoded JSON)
3. Body field: {"shape": {...}, "actualData": ...}

Testing

Use the included LLMApi.http file with:

• Visual Studio / Rider HTTP client
• VS Code REST Client extension
• Any HTTP client

Testing

The project includes comprehensive unit tests:

# Run all tests
dotnet test

# Run with detailed output
dotnet test --verbosity detailed

Test Coverage:

• ✅ Body reading (empty, JSON content)
• ✅ Shape extraction (query param, header, body field, precedence)
• ✅ Prompt generation (randomness, shape inclusion, streaming modes)
• ✅ Request building (temperature, model, messages)
• ✅ Edge cases (invalid JSON, missing data)

Architecture

graph LR
    Client[Client] -->|HTTP Request| API[LLMApi<br/>Minimal API]
    API -->|Chat Completion| Ollama[Ollama API<br/>localhost:11434]
    Ollama -->|Inference| Model[llama3 Model]
    Model -->|Response| Ollama
    Ollama -->|JSON/Stream| API
    API -->|JSON/SSE| Client

    API -.->|uses| Helper[AutoApiHelper]

    style API fill:#4CAF50
    style Helper fill:#2196F3
    style Model fill:#FF9800

Request Flow

sequenceDiagram
    participant C as Client
    participant A as LLMApi
    participant H as AutoApiHelper
    participant O as Ollama
    participant M as llama3

    C->>A: GET/POST/PUT/DELETE /api/auto/**
    A->>H: Extract context (method, path, body, shape)
    H->>H: Generate random seed + timestamp
    H->>H: Build prompt with randomness
    H-->>A: Prompt + temperature=1.2
    A->>O: POST /v1/chat/completions
    O->>M: Run inference
    M-->>O: Generated JSON
    O-->>A: Response
    A-->>C: JSON Response

Shape Control Flow

flowchart TD
    Start[Request Arrives] --> CheckQuery{Shape in<br/>Query Param?}
    CheckQuery -->|Yes| UseQuery[Use Query Shape]
    CheckQuery -->|No| CheckHeader{Shape in<br/>Header?}
    CheckHeader -->|Yes| UseHeader[Use Header Shape]
    CheckHeader -->|No| CheckBody{Shape in<br/>Body Field?}
    CheckBody -->|Yes| UseBody[Use Body Shape]
    CheckBody -->|No| NoShape[No Shape Constraint]

    UseQuery --> BuildPrompt[Build Prompt]
    UseHeader --> BuildPrompt
    UseBody --> BuildPrompt
    NoShape --> BuildPrompt

    BuildPrompt --> AddRandom[Add Random Seed<br/>+ Timestamp]
    AddRandom --> SendLLM[Send to LLM]

    style UseQuery fill:#4CAF50
    style UseHeader fill:#4CAF50
    style UseBody fill:#4CAF50
    style NoShape fill:#FFC107

Projects:

• mostlylucid.mockllmapi: NuGet package library
• LLMApi: Demo application
• LLMApi.Tests: xUnit test suite (13 tests)

Why Use mostlylucid.mockllmapi?

• 🚀 Rapid Prototyping: Frontend development without waiting for backend
• 🎭 Demos: Show realistic data flows without hardcoded fixtures
• 🧪 Testing: Generate varied test data for edge cases
• 📐 API Design: Experiment with response shapes before implementing
• 🎓 Learning: Example of LLM integration in .NET minimal APIs
• 🔌 Zero Maintenance: No database, no state, no mock data files to maintain

Building the NuGet Package

cd mostlylucid.mockllmapi
dotnet pack -c Release

Package will be in bin/Release/mostlylucid.mockllmapi.{version}.nupkg

Contributing

This is a sample project demonstrating LLM-powered mock APIs. Feel free to fork and customize!

License

This is free and unencumbered software released into the public domain. See LICENSE for details or visit unlicense.org.