### Initialize and Start Project

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/AGENTS.md

Commands to clone submodules, install dependencies, and launch the backend and frontend servers.

```bash
# Initialize (clone submodules + install deps)
make init

# Set up environment
test -f .env || cp sample.env .env  # then set DEEPGRAM_API_KEY

# Start both servers
make start
# Backend: http://localhost:8081
# Frontend: http://localhost:8080
```

--------------------------------

### Initialize and Start Local Development

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/README.md

Use this Makefile command to initialize the project, copy environment variables, and start the local development server. Ensure your DEEPGRAM_API_KEY is set in the .env file.

```bash
make init
cp sample.env .env  # Add your DEEPGRAM_API_KEY
make start
```

--------------------------------

### Install Dependencies

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/AGENTS.md

Commands to install required packages for the .NET backend and the Vite frontend.

```bash
dotnet restore
```

```bash
cd frontend && corepack pnpm install
```

--------------------------------

### Project Setup and Configuration

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Initialize and configure the project using the Makefile commands and environment variables. The project requires .NET SDK, Git, and a Deepgram API key.

```bash
# Check prerequisites
make check-prereqs

# Initialize project (clone submodules + install dependencies)
make init

# Configure environment
cp sample.env .env
# Edit .env and set your Deepgram API key:
```

--------------------------------

### Project Build and Run Commands

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Commands to start backend and frontend servers, run tests, clean build artifacts, and update submodules.

```bash
make start
# Backend: http://localhost:8081
# Frontend: http://localhost:8080
```

```bash
make start-backend   # Port 8081
```

```bash
make start-frontend  # Port 8080
```

```bash
make test
```

```bash
make clean
```

```bash
make update
```

--------------------------------

### Curl Request Examples for Text Intelligence API

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Examples demonstrating various error scenarios when interacting with the Text Intelligence API using curl. Includes missing authorization, invalid tokens, and malformed request bodies.

```bash
# Missing authorization token
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=true" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello world"}' | jq
```

```json
{
  "error": {
    "type": "AuthenticationError",
    "code": "MISSING_TOKEN",
    "message": "Authorization header with Bearer token is required"
  }
}
```

```bash
# Invalid/expired token
curl -X POST "http://localhost:8081/api/text-intelligence" \
  -H "Authorization: Bearer invalid_token" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello"}' | jq
```

```json
{
  "error": {
    "type": "AuthenticationError",
    "code": "INVALID_TOKEN",
    "message": "Invalid or expired session token"
  }
}
```

```bash
# Missing text/url in body
curl -X POST "http://localhost:8081/api/text-intelligence" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}' | jq
```

```json
{
  "error": {
    "type": "validation_error",
    "code": "INVALID_TEXT",
    "message": "Request must contain either 'text' or 'url' field"
  }
}
```

```bash
# Both text and url provided (invalid)
curl -X POST "http://localhost:8081/api/text-intelligence" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello", "url": "https://example.com"}' | jq
```

```json
{
  "error": {
    "type": "validation_error",
    "code": "INVALID_TEXT",
    "message": "Request must contain either 'text' or 'url', not both"
  }
}
```

--------------------------------

### Start and Stop Commands

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/AGENTS.md

Utility commands for managing the application lifecycle, including separate server execution and cleanup.

```bash
make start
```

```bash
# Terminal 1 — Backend
dotnet run

# Terminal 2 — Frontend
cd frontend && corepack pnpm run dev -- --port 8080 --no-open
```

```bash
lsof -ti:8080,8081 | xargs kill -9 2>/dev/null
```

```bash
rm -rf bin obj frontend/node_modules frontend/.vite
make init
```

--------------------------------

### Conventional Commit Examples

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/AGENTS.md

Standardized commit message formats for the project. Do not include Co-Authored-By lines for Claude.

```text
feat(csharp-text-intelligence): add diarization support
fix(csharp-text-intelligence): resolve WebSocket close handling
refactor(csharp-text-intelligence): simplify session endpoint
chore(deps): update frontend submodule
```

--------------------------------

### Get Application Metadata

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Returns application metadata from the `deepgram.toml` configuration file, including title, description, use case, language, framework, and SDK version information.

```bash
# Get application metadata
curl -s http://localhost:8081/api/metadata | jq
```

--------------------------------

### Get Application Metadata API

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Returns application metadata from the `deepgram.toml` configuration file, including title, description, use case, language, framework, and SDK version information.

```APIDOC
## GET /api/metadata

### Description
Returns application metadata from the `deepgram.toml` configuration file, including title, description, use case, language, framework, and SDK version information.

### Method
GET

### Endpoint
/api/metadata

### Request Example
```bash
curl -s http://localhost:8081/api/metadata | jq
```

### Response
#### Success Response (200)
- **title** (string) - The title of the application.
- **description** (string) - A brief description of the application.
- **author** (string) - Information about the author or team.
- **repository** (string) - URL to the project repository.
- **useCase** (string) - The primary use case of the application.
- **language** (string) - The programming language used.
- **framework** (string) - The framework used.
- **sdk** (string) - The version of the SDK used.
- **tags** (array) - An array of relevant tags.

#### Response Example
```json
{
  "title": "C# Text Intelligence",
  "description": "Get started using Deepgram's Text Intelligence with this C# demo app",
  "author": "Deepgram DX Team <devrel@deepgram.com> (https://developers.deepgram.com)",
  "repository": "https://github.com/deepgram-starters/csharp-text-intelligence",
  "useCase": "text-intelligence",
  "language": "csharp",
  "framework": "dotnet",
  "sdk": "6.6.1",
  "tags": ["text-intelligence", "text-analysis", "summarization", "sentiment", "csharp", "dotnet"]
}
```
```

--------------------------------

### Get Session Token

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Retrieves a JWT session token required for authenticating subsequent API requests. The token is valid for 3600 seconds (1 hour) and must be included as a Bearer token in the Authorization header for protected endpoints.

```bash
# Get a session token
curl -s http://localhost:8081/api/session | jq

# Response:
{
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}

# Store token for subsequent requests
TOKEN=$(curl -s http://localhost:8081/api/session | jq -r '.token')
echo "Session token: $TOKEN"
```

--------------------------------

### Get Session Token API

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Retrieves a JWT session token required for authenticating subsequent API requests. The token is valid for 3600 seconds (1 hour) and must be included as a Bearer token in the Authorization header for protected endpoints.

```APIDOC
## GET /api/session

### Description
Retrieves a JWT session token required for authenticating subsequent API requests. The token is valid for 3600 seconds (1 hour) and must be included as a Bearer token in the Authorization header for protected endpoints.

### Method
GET

### Endpoint
/api/session

### Request Example
```bash
curl -s http://localhost:8081/api/session | jq
```

### Response
#### Success Response (200)
- **token** (string) - The JWT session token.

#### Response Example
```json
{
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}
```
```

--------------------------------

### Project Testing Commands

Source: https://github.com/deepgram-starters/csharp-text-intelligence/blob/main/AGENTS.md

Commands to execute conformance tests and verify API endpoints manually.

```bash
# Run conformance tests (requires app to be running)
make test

# Manual endpoint check
curl -sf http://localhost:8081/api/metadata | python3 -m json.tool
curl -sf http://localhost:8081/api/session | python3 -m json.tool
```

--------------------------------

### Environment Variables Configuration

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Configure application behavior using environment variables in the .env file. Ensure DEEPGRAM_API_KEY is set.

```bash
# Required - Deepgram API key from https://console.deepgram.com
DEEPGRAM_API_KEY=your_api_key_here
```

```bash
# Optional - Backend server port (default: 8081)
PORT=8081
```

```bash
# Optional - Server bind address (default: 0.0.0.0)
HOST=0.0.0.0
```

```bash
# Optional - JWT signing secret for production (auto-generated if not set)
SESSION_SECRET=your_secure_secret_for_production
```

--------------------------------

### C# Deepgram SDK for Text Analysis

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Initialize the Deepgram library and client, configure analysis options, and analyze text content using the .NET SDK. Access results like summary, topics, sentiment, and intents.

```csharp
using Deepgram;
using Deepgram.Models.Analyze.v1;

// Initialize the Deepgram library
Library.Initialize();

// Create an analyze client with your API key
var apiKey = Environment.GetEnvironmentVariable("DEEPGRAM_API_KEY");
var deepgramClient = ClientFactory.CreateAnalyzeClient(apiKey);

// Configure analysis options
var schema = new AnalyzeSchema
{
    Language = "en",
    Summarize = true,    // Enable summarization
    Topics = true,       // Enable topic detection
    Sentiment = true,    // Enable sentiment analysis
    Intents = true       // Enable intent detection
};

// Analyze text content
var textContent = "Your text content to analyze here...";
var result = await deepgramClient.AnalyzeText(
    new TextSource(textContent),
    schema
);

// Access results
var summary = result.Results?.Summary?.Text;
var topics = result.Results?.Topics?.Segments;
var sentiment = result.Results?.Sentiments?.Average;
var intents = result.Results?.Intents?.Segments;
```

--------------------------------

### Health Check Endpoint

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Returns the health status of the backend service. Useful for monitoring, load balancers, and container orchestration systems.

```bash
# Check service health
curl -s http://localhost:8081/health | jq
```

--------------------------------

### Health Check Endpoint

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Returns the health status of the backend service. Useful for monitoring, load balancers, and container orchestration systems.

```APIDOC
## GET /health

### Description
Returns the health status of the backend service. Useful for monitoring, load balancers, and container orchestration systems.

### Method
GET

### Endpoint
/health

### Request Example
```bash
curl -s http://localhost:8081/health | jq
```

### Response
#### Success Response (200)
- **status** (string) - The health status of the service (e.g., "ok").
- **service** (string) - The name of the service.

#### Response Example
```json
{
  "status": "ok",
  "service": "text-intelligence"
}
```
```

--------------------------------

### Analyze Text with Text Intelligence

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Analyzes text content for summaries, topics, sentiment, and intents using Deepgram's Text Intelligence API. The endpoint accepts either raw text or a URL in the JSON body, and supports multiple analysis features via query parameters. Requires JWT authentication.

```bash
# Analyze text with all features enabled
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=true&topics=true&sentiment=true&intents=true" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "I love this product! The quality is amazing and the customer service was incredibly helpful. I would definitely recommend it to my friends and family. The shipping was fast and the packaging was secure."}' | jq
```

```bash
# Analyze text from URL
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=v2&language=en" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/article.txt"}' | jq
```

```bash
# Analyze with specific features only (summarize and sentiment)
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=true&sentiment=true" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "The meeting was productive but ran longer than expected. We resolved several key issues."}' | jq
```

--------------------------------

### Analyze Text with Text Intelligence API

Source: https://context7.com/deepgram-starters/csharp-text-intelligence/llms.txt

Analyzes text content for summaries, topics, sentiment, and intents using Deepgram's Text Intelligence API. The endpoint accepts either raw text or a URL in the JSON body, and supports multiple analysis features via query parameters. Requires JWT authentication.

```APIDOC
## POST /api/text-intelligence

### Description
Analyzes text content for summaries, topics, sentiment, and intents using Deepgram's Text Intelligence API. The endpoint accepts either raw text or a URL in the JSON body, and supports multiple analysis features via query parameters. Requires JWT authentication.

### Method
POST

### Endpoint
/api/text-intelligence

### Query Parameters
- **summarize** (boolean or string) - Optional - Enable text summarization. Can be `true` or `v2` for different summarization versions.
- **topics** (boolean) - Optional - Enable topic detection.
- **sentiment** (boolean) - Optional - Enable sentiment analysis.
- **intents** (boolean) - Optional - Enable intent detection.
- **language** (string) - Optional - Specify the language for analysis (e.g., `en`).

### Request Body
- **text** (string) - Required if `url` is not provided - The text content to analyze.
- **url** (string) - Required if `text` is not provided - The URL of the content to analyze.

### Request Example
```bash
# Analyze text with all features enabled
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=true&topics=true&sentiment=true&intents=true" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "I love this product! The quality is amazing and the customer service was incredibly helpful. I would definitely recommend it to my friends and family. The shipping was fast and the packaging was secure."}' | jq

# Analyze text from URL
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=v2&language=en" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/article.txt"}' | jq

# Analyze with specific features only (summarize and sentiment)
curl -X POST "http://localhost:8081/api/text-intelligence?summarize=true&sentiment=true" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "The meeting was productive but ran longer than expected. We resolved several key issues."}' | jq
```

### Response
#### Success Response (200)
- **results** (object) - Contains the analysis results.
  - **summary** (object) - The summary of the text.
    - **text** (string) - The summarized text.
  - **topics** (object) - Detected topics in the text.
    - **segments** (array) - Array of topic segments.
      - **topics** (array) - Array of detected topics within a segment.
        - **topic** (string) - The identified topic.
        - **confidence** (number) - The confidence score for the topic.
  - **sentiments** (object) - Sentiment analysis results.
    - **average** (object) - The overall average sentiment.
      - **sentiment** (string) - The sentiment (e.g., 'positive', 'negative', 'neutral').
      - **confidence** (number) - The confidence score for the sentiment.
    - **segments** (array) - Sentiment analysis for text segments.
  - **intents** (object) - Detected user intents.
    - **segments** (array) - Array of intent segments.
      - **intents** (array) - Array of detected intents within a segment.
        - **intent** (string) - The identified intent.
        - **confidence** (number) - The confidence score for the intent.

#### Response Example
```json
{
  "results": {
    "summary": {
      "text": "The customer expresses strong satisfaction with the product quality, customer service, shipping speed, and packaging."
    },
    "topics": {
      "segments": [
        {
          "topics": [
            {"topic": "product quality", "confidence": 0.95},
            {"topic": "customer service", "confidence": 0.92}
          ]
        }
      ]
    },
    "sentiments": {
      "average": {"sentiment": "positive", "confidence": 0.98},
      "segments": [...] 
    },
    "intents": {
      "segments": [
        {
          "intents": [
            {"intent": "recommendation", "confidence": 0.89}
          ]
        }
      ]
    }
  }
}
```
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.