docs: add comprehensive documentation with README and detailed guides

- Add user-friendly README.md with quick start guide
- Create docs/ folder with structured technical documentation:
  - installation.md: Build and setup instructions
  - configuration.md: Complete config reference
  - usage.md: CLI usage guide with examples
  - architecture.md: System design and patterns
  - components/: Deep dive into each component (OpenQueryApp, SearchTool, Services, Models)
  - api/: CLI reference, environment variables, programmatic API
  - troubleshooting.md: Common issues and solutions
  - performance.md: Latency, throughput, and optimization
- All documentation fully cross-referenced with internal links
- Covers project overview, architecture, components, APIs, and support

See individual files for complete documentation.
This commit is contained in:
OpenQuery Documentation
2026-03-19 10:01:58 +01:00
parent b28d8998f7
commit 65ca2401ae
16 changed files with 7073 additions and 0 deletions

309
docs/api/cli.md Normal file
View File

@@ -0,0 +1,309 @@
# CLI Reference
Complete command-line interface reference for OpenQuery.
## 📋 Table of Contents
1. [Command Structure](#command-structure)
2. [Main Command: `openquery`](#main-command-openquery)
3. [Configure Command: `openquery configure`](#configure-command-openquery-configure)
4. [Exit Codes](#exit-codes)
5. [Examples by Use Case](#examples-by-use-case)
6. [Shell Integration](#shell-integration)
## Command Structure
OpenQuery uses [System.CommandLine](https://learn.microsoft.com/dotnet/standard/commandline/) for CLI parsing.
### Syntax
```bash
openquery [GLOBAL-OPTIONS] <COMMAND> [COMMAND-OPTIONS] [ARGUMENTS]
```
If no command specified, `openquery` (main command) is assumed.
### Help
```bash
openquery --help
openquery configure --help
```
Shows usage, options, examples.
### Version
```bash
openquery --version # if implemented
```
---
## Main Command: `openquery`
Ask a question and get an AI-powered answer.
### Synopsis
```bash
openquery [OPTIONS] <question>
```
### Arguments
| Name | Arity | Type | Description |
|------|-------|------|-------------|
| `question` | ZeroOrMore | `string[]` | The question to ask (positional, concatenated with spaces) |
**Notes**:
- `ZeroOrMore` means you can omit the question (shows help)
- Multiple words are combined: `openquery what is quantum``"what is quantum"`
- Use quotes for questions with special characters: `openquery "what's the weather?"`
### Options
| Option | Aliases | Type | Default | Description |
|--------|---------|------|---------|-------------|
| `--chunks` | `-c` | `int` | `DefaultChunks` (config) | Number of top context chunks to pass to LLM |
| `--results` | `-r` | `int` | `DefaultResults` (config) | Number of search results per query |
| `--queries` | `-q` | `int` | `DefaultQueries` (config) | Number of search queries to generate |
| `--short` | `-s` | `bool` | `false` | Request a concise answer |
| `--long` | `-l` | `bool` | `false` | Request a detailed answer |
| `--verbose` | `-v` | `bool` | `false` | Show detailed progress information |
**Option Notes**:
- `--short` and `--long` are flags; if both specified, `--long` takes precedence
- Integer options validate as positive numbers (parsed by System.CommandLine)
- Defaults come from config file or hardcoded (3, 5, 3 respectively)
### Behavior
1. Loads API key (env `OPENROUTER_API_KEY` or config file)
2. Loads model (env `OPENROUTER_MODEL` or config)
3. Executes workflow:
- Generate queries (if `--queries > 1`)
- Run search pipeline
- Stream final answer
4. Exits with code 0 on success, 1 on error
### Examples
```bash
# Basic
openquery "What is the capital of France?"
# With options
openquery -q 5 -r 10 -c 4 "Explain quantum computing"
# Short answer
openquery -s "Who won the 2024 election?"
# Verbose mode
openquery -v "How does photosynthesis work?"
# Combined
openquery -l -v -q 8 "History of the internet"
```
---
## Configure Command: `openquery configure`
Configure OpenQuery settings (API key, model, defaults).
### Synopsis
```bash
openquery configure [OPTIONS]
```
### Options
| Option | Type | Description |
|--------|------|-------------|
| `--interactive` / `-i` | `bool` | Launch interactive configuration wizard |
| `--key` | `string` | Set OpenRouter API key |
| `--model` | `string` | Set default LLM model |
| `--queries` | `int?` | Set default number of queries |
| `--chunks` | `int?` | Set default number of chunks |
| `--results` | `int?` | Set default number of results |
**Note**: Nullable options (`int?`) only update if provided.
### Behavior
- **Interactive mode** (`-i`): Prompts for each setting with current defaults shown in brackets
- **Non-interactive**: Only updates provided options, leaves others untouched
- Writes to `~/.config/openquery/config` (creates directory if missing)
- Overwrites entire file (not incremental)
### Interactive Mode Details
Models presented with numbered menu:
```
Available models:
1. qwen/qwen3.5-flash-02-23
2. qwen/qwen3.5-122b-a10b
3. minimax/minimax-m2.5
4. google/gemini-3-flash-preview
5. deepseek/deepseek-v3.2
6. moonshotai/kuki-k2.5
Model [qwen/qwen3.5-flash-02-23]:
```
- Enter number (1-6) to select preset
- Or enter custom model string (any OpenRouter model)
### Examples
```bash
# Interactive wizard
openquery configure -i
# Set just API key
openquery configure --key "sk-or-xxxxxxxxxxxx"
# Set multiple defaults
openquery configure --model "google/gemini-3-flash-preview" --queries 5 --chunks 4
# Update model only
openquery configure --model "deepseek/deepseek-v3.2"
```
---
## Exit Codes
| Code | Meaning |
|------|---------|
| `0` | Success - answer generated and streamed |
| `1` | Error - API key missing, network failure, or exception |
**Usage in scripts**:
```bash
openquery "question"
if [ $? -eq 0 ]; then
echo "Success"
else
echo "Failed" >&2
fi
```
---
## Examples by Use Case
### Quick Facts
```bash
openquery -s "capital of France"
```
Fast, concise, minimal tokens.
### Research Paper
```bash
openquery -l -q 5 -r 10 -c 4 "quantum entanglement experiments"
```
Multiple angles, deep sources, detailed synthesis.
### News & Current Events
```bash
openquery -v "latest news about OpenAI"
```
See everything: queries, results, which sources fetched.
### Troubleshooting
```bash
# Reduce scope if errors
openquery -q 1 -r 2 "test question"
```
### Save Answer to File
```bash
openquery "question" 2>/dev/null | sed 's/.\x08//g' > answer.md
```
(Removes spinner characters)
### Batch Processing
```bash
for q in $(cat questions.txt); do
echo "## $q" >> all-answers.md
openquery -s "$q" 2>/dev/null | sed 's/.\x08//g' >> all-answers.md
echo "" >> all-answers.md
done
```
---
## Shell Integration
### Aliases (add to ~/.bashrc or ~/.zshrc)
```bash
# Short alias
alias oq='openquery'
# Presets
alias oqs='openquery -s' # short
alias oql='openquery -l' # long
alias oqv='openquery -v' # verbose
alias oqr='openquery -q 5 -r 10 -c 4' # research mode
# Config shortcuts
alias oqcfg='openquery configure -i'
```
### Functions
```bash
# Save answer cleanly (removes spinner chars)
oqsave() {
local query="$*"
local filename="answer-$(date +%Y%m%d-%H%M%S).md"
openquery "$query" 2>/dev/null | sed 's/.\x08//g' > "$filename"
echo "Saved to $filename"
}
# Search and grep results
oqgrep() {
openquery "$1" 2>/dev/null | sed 's/.\x08//g' | grep -i "$2"
}
```
### Environment Setup Script
```bash
# ~/.local/bin/openquery-env.sh
export OPENROUTER_API_KEY="sk-or-..."
export OPENROUTER_MODEL="qwen/qwen3.5-flash-02-23"
export SEARXNG_URL="http://localhost:8002"
```
Source it: `source ~/.local/bin/openquery-env.sh`
---
## Next Steps
- **[Configuration](configuration.md)** - Set up your environment
- **[Usage](usage.md)** - Learn usage patterns and tips
- **[Troubleshooting](troubleshooting.md)** - Fix common problems
---
**Quick Reference Card**
```
# Ask
openquery "question"
openquery -s "quick fact"
openquery -l -q 5 "deep research"
# Configure
openquery configure -i
openquery configure --key "..."
openquery configure --model "..."
# Debug
openquery -v "question"
# Help
openquery --help
```

View File

@@ -0,0 +1,235 @@
# Environment Variables
Reference for all environment variables used by OpenQuery.
## 📋 Summary
| Variable | Purpose | Required | Default | Example |
|----------|---------|----------|---------|---------|
| `OPENROUTER_API_KEY` | OpenRouter authentication | **Yes** | (none) | `sk-or-...` |
| `OPENROUTER_MODEL` | Override default LLM model | No | `qwen/qwen3.5-flash-02-23` | `google/gemini-3-flash-preview` |
| `SEARXNG_URL` | SearxNG instance URL | No | `http://localhost:8002` | `https://searx.example.com` |
## Detailed Reference
### `OPENROUTER_API_KEY`
**Purpose**: Your OpenRouter API authentication token.
**Required**: Yes, unless you have `ApiKey` set in config file.
**How to Obtain**:
1. Sign up at https://openrouter.ai
2. Go to Dashboard → API Keys
3. Copy your key (starts with `sk-or-`)
**Priority**: Overrides config file `ApiKey`.
**Setting**:
```bash
# Bash/Zsh
export OPENROUTER_API_KEY="sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
# Fish
set -x OPENROUTER_API_KEY "sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
# PowerShell
$env:OPENROUTER_API_KEY="sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
# Windows CMD
set OPENROUTER_API_KEY=sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
```
**Security**:
- Never commit API key to version control
- Don't share key publicly
- Use environment variables or config file with restrictive permissions (600)
- Rotate key if accidentally exposed
**Validation**: OpenQuery checks if key is empty string and exits with error if missing:
```
[Error] API Key is missing. Set OPENROUTER_API_KEY environment variable or run 'configure -i' to set it up.
```
### `OPENROUTER_MODEL`
**Purpose**: Override the default LLM model used for both query generation and final answer.
**Required**: No.
**Default**: `qwen/qwen3.5-flash-02-23`
**Available Models** (from OpenRouter):
| Model | Provider | Context | Cost (Input/Output per 1M tokens) |
|-------|----------|---------|-----------------------------------|
| `qwen/qwen3.5-flash-02-23` | Alibaba | 200K | \$0.10 / \$0.20 |
| `qwen/qwen3.5-122b-a10b` | Alibaba | 200K | ~\$0.20 / ~\$0.40 |
| `minimax/minimax-m2.5` | MiniMax | 200K | ~\$0.20 / ~\$0.40 |
| `google/gemini-3-flash-preview` | Google | 1M | ~\$0.10 / ~\$0.40 |
| `deepseek/deepseek-v3.2` | DeepSeek | 200K | ~\$0.10 / ~\$0.30 |
| `moonshotai/kimi-k2.5` | Moonshot AI | 200K | ~\$0.10 / ~\$0.30 |
(See OpenRouter for current pricing.)
**Setting**:
```bash
export OPENROUTER_MODEL="google/gemini-3-flash-preview"
```
**Interactive Config Models**: The `configure -i` wizard shows only these 6 models for convenience, but you can set any OpenRouter model via environment variable or non-interactive configure.
**Note**: Different models have different:
- Speed (Flash models faster)
- Cost (check pricing)
- Quality (may vary by task)
- Context window size (Gemini 3 Flash has 1M tokens, others ~200K)
### `SEARXNG_URL`
**Purpose**: URL of the SearxNG metasearch instance.
**Required**: No.
**Default**: `http://localhost:8002`
**Format**: Must include protocol (`http://` or `https://`) and host:port.
**Setting**:
```bash
# Local Docker instance
export SEARXNG_URL="http://localhost:8002"
# Remote instance with HTTPS
export SEARXNG_URL="https://searx.example.com"
# Custom port
export SEARXNG_URL="http://localhost:8080"
```
**Finding a Public Instance**:
- Visit https://searx.space for list of public instances
- Choose one with HTTPS and low latency
- Note: Public instances may have rate limits or require attribution
**Priority**: Overrides any default, but not config file (no config setting for SearxNG URL - only env var). Could be added to config in future.
**Test Your Instance**:
```bash
curl "$SEARXNG_URL/search?q=test&format=json" | head
```
Expected: JSON with `"results": [...]`.
---
## Configuration Priority Recap
When OpenQuery needs a value:
1. **Command-line option** (`--model`, `--key` from configure) - highest
2. **Environment variable** (`OPENROUTER_MODEL`, `OPENROUTER_API_KEY`, `SEARXNG_URL`)
3. **Configuration file** (`~/.config/openquery/config`: `Model`, `ApiKey`)
4. **Hard-coded default** (only for model)
**Example**:
```bash
# Config file: Model=qwen/qwen3.5-flash-02-23
export OPENROUTER_MODEL="deepseek/deepseek-v3.2"
openquery --model "google/gemini-3-flash-preview" "question"
# Uses: model=google (CLI override), overrides env and config
```
---
## Troubleshooting Environment Variables
### Variable Not Taking Effect
**Symptom**: `openquery` still uses old value after export.
**Causes**:
- Exported in different shell session
- Exported after running `openquery`
- Shell profile not reloaded
**Check**:
```bash
echo $OPENROUTER_API_KEY
# Should print the key (or blank if unset)
```
**Fix**:
```bash
# Export in current session
export OPENROUTER_API_KEY="sk-or-..."
# Or add to ~/.bashrc / ~/.zshrc and restart terminal
```
### Special Characters in Values
If your API key contains special characters (`$`, `!`, etc.), quote properly:
```bash
export OPENROUTER_API_KEY='sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
# Single quotes prevent shell expansion
```
### Variable Name Typos
`OPENROUTER_API_KEY` is all caps with underscores. `openrouter_api_key` (lowercase) won't work.
**Check spelling**:
```bash
env | grep -i openrouter
```
### Windows Environment Variables
On Windows, environment variables are set per-session or user-level:
**PowerShell** (current session):
```powershell
$env:OPENROUTER_API_KEY="sk-or-..."
```
**Persistent** (PowerShell):
```powershell
[Environment]::SetEnvironmentVariable("OPENROUTER_API_KEY", "sk-or-...", "User")
```
**CMD**:
```cmd
set OPENROUTER_API_KEY=sk-or-...
```
**System Properties** → Advanced → Environment Variables (GUI)
---
## Next Steps
- **[Configuration File](../configuration.md)** - Persistent configuration
- **[Usage Guide](../usage.md)** - How to use these variables
- **[Troubleshooting](../troubleshooting.md)** - Diagnose environment issues
---
**Quick Reference**
```bash
# Required
export OPENROUTER_API_KEY="sk-or-..."
# Optional (override defaults)
export OPENROUTER_MODEL="google/gemini-3-flash-preview"
export SEARXNG_URL="https://searx.example.com"
# Run
openquery "your question"
```

508
docs/api/programmatic.md Normal file
View File

@@ -0,0 +1,508 @@
# Programmatic API Reference
How to use OpenQuery components programmatically in your own C# code.
## 📋 Table of Contents
1. [Overview](#overview)
2. [Using OpenQueryApp Programmatically](#using-openqueryapp-programmatically)
3. [Using Individual Services](#using-individual-services)
4. [Custom Implementations](#custom-implementations)
5. [Thread Safety](#thread-safety)
6. [Error Handling](#error-handling)
## Overview
OpenQuery is designed as a library of composable services, not just a CLI tool. You can reference the project (or extract the core classes) and use them in your own applications.
### Core Interfaces
Currently, OpenQuery uses concrete classes rather than interfaces. To use programmatically:
1. Reference the `OpenQuery` project/dll
2. Add `using OpenQuery.Services;` and `using OpenQuery.Tools;`
3. Instantiate dependencies
4. Call methods
### Dependency Chain
```
Your Code
├── OpenRouterClient (LLM API)
├── SearxngClient (Search API)
├── EmbeddingService (requires OpenRouterClient)
└── SearchTool (requires SearxngClient + EmbeddingService)
└── (internally uses ArticleService, ChunkingService, RateLimiter)
```
---
## Using OpenQueryApp Programmatically
### Minimal Example
```csharp
using OpenQuery;
using OpenQuery.Services;
using OpenQuery.Tools;
using OpenQuery.Models;
// 1. Configure
string apiKey = Environment.GetEnvironmentVariable("OPENROUTER_API_KEY")
?? throw new InvalidOperationException("API key required");
string searxngUrl = Environment.GetEnvironmentVariable("SEARXNG_URL")
?? "http://localhost:8002";
string model = Environment.GetEnvironmentVariable("OPENROUTER_MODEL")
?? "qwen/qwen3.5-flash-02-23";
// 2. Instantiate services
var openRouterClient = new OpenRouterClient(apiKey);
var searxngClient = new SearxngClient(searxngUrl);
var embeddingService = new EmbeddingService(openRouterClient);
var searchTool = new SearchTool(searxngClient, embeddingService);
var openQuery = new OpenQueryApp(openRouterClient, searchTool, model);
// 3. Execute
var options = new OpenQueryOptions(
Chunks: 3,
Results: 5,
Queries: 3,
Short: false,
Long: false,
Verbose: false,
Question: "What is quantum entanglement?"
);
await openQuery.RunAsync(options);
```
**Output**: Streams answer to `Console.Out` (hardcoded in `OpenQueryApp`). To capture output, modify `OpenQueryApp` or redirect console.
### Capturing Output
`OpenQueryApp.RunAsync` writes directly to `Console`. To capture:
**Option 1**: Redirect Console (hacky)
```csharp
var sw = new StringWriter();
Console.SetOut(sw);
await openQuery.RunAsync(options);
string answer = sw.ToString();
```
**Option 2**: Modify OpenQueryApp to accept TextWriter (not currently supported)
**Option 3**: Reimplement using OpenQuery components without `OpenQueryApp`
```csharp
public async Task<string> GetAnswerAsync(string question, OpenQueryOptions options)
{
var sb = new StringBuilder();
var reporter = new StatusReporter(options.Verbose);
// Replicate OpenQueryApp.RunAsync but collect output
// ... (copy logic from OpenQuery.cs)
return sb.ToString();
}
```
---
## Using Individual Services
### OpenRouterClient
```csharp
var client = new OpenRouterClient("your-api-key");
// Non-streaming chat completion
var request = new ChatCompletionRequest(
model: "qwen/qwen3.5-flash-02-23",
messages: new List<Message>
{
new Message("system", "You are a helpful assistant."),
new Message("user", "What is 2+2?")
}
);
var response = await client.CompleteAsync(request);
Console.WriteLine(response.Choices[0].Message.Content);
// Streaming chat completion
var streamRequest = request with { Stream = true };
await foreach (var chunk in client.StreamAsync(streamRequest))
{
if (chunk.TextDelta != null)
Console.Write(chunk.TextDelta);
}
// Embeddings
var embeddingRequest = new EmbeddingRequest(
model: "openai/text-embedding-3-small",
input: new List<string> { "text 1", "text 2" }
);
float[][] embeddings = await client.EmbedAsync(embeddingRequest.Model, embeddingRequest.Input);
// embeddings[0] is vector for "text 1"
```
### SearxngClient
```csharp
var searxng = new SearxngClient("http://localhost:8002");
List<SearxngResult> results = await searxng.SearchAsync("quantum physics", limit: 5);
foreach (var result in results)
{
Console.WriteLine($"{result.Title}");
Console.WriteLine($"{result.Url}");
Console.WriteLine($"{result.Content}");
Console.WriteLine();
}
```
### EmbeddingService
```csharp
var client = new OpenRouterClient("your-api-key");
var embeddingService = new EmbeddingService(client); // default model: openai/text-embedding-3-small
// Single embedding
float[] embedding = await embeddingService.GetEmbeddingAsync("Hello world");
// Batch embeddings (with progress)
List<string> texts = new() { "text 1", "text 2", "text 3" };
float[][] embeddings = await embeddingService.GetEmbeddingsAsync(
texts,
onProgress: msg => Console.WriteLine(msg)
);
// Cosine similarity
float similarity = EmbeddingService.CosineSimilarity(embedding1, embedding2);
```
### ArticleService
```csharp
var article = await ArticleService.FetchArticleAsync("https://example.com/article");
Console.WriteLine(article.Title);
Console.WriteLine(article.TextContent);
Console.WriteLine($"Readable: {article.IsReadable}");
```
Note: `Article` type comes from SmartReader library (not OpenQuery-specific).
### ChunkingService
```csharp
List<string> chunks = ChunkingService.ChunkText("Long article text...");
foreach (var chunk in chunks)
{
Console.WriteLine($"Chunk ({chunk.Length} chars): {chunk.Substring(0, 50)}...");
}
```
### SearchTool (Orchestration)
```csharp
var searxngClient = new SearxngClient("http://localhost:8002");
var embeddingService = new EmbeddingService(openRouterClient);
var searchTool = new SearchTool(searxngClient, embeddingService);
string context = await searchTool.ExecuteAsync(
originalQuery: "What is quantum entanglement?",
generatedQueries: new List<string>
{
"quantum entanglement definition",
"how quantum entanglement works"
},
maxResults: 5,
topChunksLimit: 3,
onProgress: msg => Console.WriteLine(msg),
verbose: true
);
Console.WriteLine("Context:");
Console.WriteLine(context);
```
Output is a formatted string:
```
[Source 1: Title](https://example.com/1)
Content chunk...
[Source 2: Title](https://example.com/2)
Content chunk...
```
---
## Custom Implementations
### Custom Progress Reporter
`SearchTool.ExecuteAsync` accepts `Action<string>? onProgress`. Provide your own:
```csharp
public class MyProgressReporter
{
public void Report(string message)
{
// Log to file
File.AppendAllText("log.txt", $"{DateTime.UtcNow}: {message}\n");
// Update UI
myLabel.Text = message;
// Send to telemetry
Telemetry.TrackEvent("OpenQueryProgress", new { message });
}
}
// Usage
var reporter = new MyProgressReporter();
await searchTool.ExecuteAsync(..., reporter.Report, verbose: false);
```
### Custom Chunking Strategy
Extend `ChunkingService` or implement your own:
```csharp
public static class MyChunkingService
{
public static List<string> ChunkText(string text, int maxSize = 500, int overlap = 50)
{
// Overlapping chunks for better context retrieval
var chunks = new List<string>();
int start = 0;
while (start < text.Length)
{
int end = Math.Min(start + maxSize, text.Length);
var chunk = text.Substring(start, end - start);
chunks.Add(chunk);
start += maxSize - overlap; // Slide window
}
return chunks;
}
}
```
### Custom Rate Limiter
Implement `IAsyncDisposable` with your own strategy (token bucket, leaky bucket):
```csharp
public class TokenBucketRateLimiter : IAsyncDisposable
{
private readonly SemaphoreSlim _semaphore;
private readonly TimeSpan _refillPeriod;
private int _tokens;
private readonly int _maxTokens;
// Implementation details...
public async Task<T> ExecuteAsync<T>(Func<Task<T>> action, CancellationToken ct)
{
await WaitForTokenAsync(ct);
try
{
return await action();
}
finally
{
// Return tokens or replenish bucket
}
}
}
```
---
## Thread Safety
**Thread-Safe Components**:
- `RateLimiter` - `SemaphoreSlim` is thread-safe
- `StatusReporter` - Channel is thread-safe
- Static utility classes (`ChunkingService`) - no state
**Not Thread-Safe** (instances should not be shared across threads):
- `OpenRouterClient` - wraps `HttpClient` (which is thread-safe but instance may have state)
- `SearxngClient` - `HttpClient` (thread-safe but reuse recommendations apply)
- `EmbeddingService` - has mutable fields (`_rateLimiter`, `_retryPipeline`)
- `SearchTool` - has mutable `_options`
**Recommendation**: Create new instances per operation or use locks if sharing.
### Example: Parallel Queries
```csharp
var tasks = questions.Select(async question =>
{
var options = new OpenQueryOptions(..., question: question);
var query = new OpenQueryApp(client, searchTool, model);
await query.RunAsync(options);
// Separate instances per task
});
await Task.WhenAll(tasks);
```
**Better**: Create factory that spawns fresh instances.
---
## Error Handling
All public async methods may throw:
- `HttpRequestException` - network errors, non-2xx responses
- `TaskCanceledException` - timeout or cancellation
- `JsonException` - malformed JSON
- `Argument*Exception` - invalid arguments
- `Exception` - any other error
### Pattern: Try-Catch
```csharp
try
{
var response = await client.CompleteAsync(request);
Console.WriteLine(response.Choices[0].Message.Content);
}
catch (HttpRequestException ex)
{
Console.Error.WriteLine($"Network error: {ex.Message}");
}
catch (Exception ex)
{
Console.Error.WriteLine($"Unexpected error: {ex.Message}");
}
```
### Pattern: Resilience with Polly
`EmbeddingService` already wraps `client.EmbedAsync` with Polly retry. For other calls, you can add your own:
```csharp
var retryPolicy = Policy
.Handle<HttpRequestException>()
.WaitAndRetryAsync(3, attempt => TimeSpan.FromSeconds(Math.Pow(2, attempt)));
await retryPolicy.ExecuteAsync(async () =>
{
var response = await client.CompleteAsync(request);
// ...
});
```
---
## Advanced Usage
### Streaming Responses to Network
```csharp
var request = new ChatCompletionRequest(model, messages) { Stream = true };
var response = await client.StreamAsync(request);
await foreach (var chunk in response)
{
if (chunk.TextDelta != null)
{
await networkStream.WriteAsync(Encoding.UTF8.GetBytes(chunk.TextDelta));
}
}
```
### Parallel Embedding Batches with Progress
```csharp
var texts = Enumerable.Range(0, 1000).Select(i => $"Text {i}").ToList();
await embeddingService.GetEmbeddingsAsync(texts,
onProgress: progress =>
{
Console.WriteLine(progress); // "[Generating embeddings: batch 5/4]"
});
```
### Custom Embedding Service with Different Model
```csharp
var client = new OpenRouterClient(apiKey);
var customService = new EmbeddingService(client, "your-embedding-model");
float[] embedding = await customService.GetEmbeddingAsync("text");
```
---
## Limitations
### No Interface-based Design
OpenQuery uses concrete classes. For mocking in tests, you'd need to create wrappers or use tools like JustMock/Moq that can mock non-virtual methods (not recommended). Better: define interfaces like `IOpenRouterClient` and have implementations.
### Hardcoded Concurrency Settings
`ParallelProcessingOptions` is instantiated in `SearchTool` with hardcoded defaults. To customize, you'd need to:
1. Subclass `SearchTool` and override access to `_options`
2. Or modify source to accept `ParallelProcessingOptions` in constructor
3. Or use reflection (hacky)
Suggested improvement: Add constructor parameter.
### Single Responsibility Blur
`OpenQueryApp` does query generation + pipeline + streaming. Could split:
- `IQueryGenerator` (for expanding queries)
- `IPipelineExecutor` (for search tool)
- `IAnswerStreamer` (for final LLM streaming)
Currently, `OpenQueryApp` is the facade.
---
## Next Steps
- **[Components](../components/overview.md)** - Understand architecture
- **[CLI Reference](../api/cli.md)** - CLI that uses these APIs
- **[Source Code](../)** - Read implementation details
---
**Code Snippet: Full Programmatic Flow**
```csharp
using OpenQuery.Services;
using OpenQuery.Tools;
using OpenQuery.Models;
async Task<string> Research(string question)
{
var apiKey = GetApiKey(); // your method
var client = new OpenRouterClient(apiKey);
var searxng = new SearxngClient("http://localhost:8002");
var embeddings = new EmbeddingService(client);
var search = new SearchTool(searxng, embeddings);
var app = new OpenQueryApp(client, search, "qwen/qwen3.5-flash-02-23");
var options = new OpenQueryOptions(
Chunks: 3,
Results: 5,
Queries: 3,
Short: false,
Long: false,
Verbose: false,
Question: question
);
// Capture output by redirecting Console or modifying OpenQueryApp
await app.RunAsync(options);
return "streamed to console"; // would need custom capture
}
```