Simple Chat¶

A lightweight conversational AI with no tools and no agent overhead. This is the simplest possible Diapason setup: just Ollama and a local model. Ideal for general-purpose chat, Q&A, brainstorming, and getting started quickly.

Quickstart (3 minutes)¶

1. Install Ollama and pull a model¶

# Install Ollama: https://ollama.com
ollama pull qwen3.5:4b

2. Install and initialize Diapason¶

git clone https://github.com/carlitoetienne01-spec/Diapason.git
cd Diapason
uv sync
diapason init --preset chat-simple

3. Ask a question¶

diapason ask "What is quantum computing?"

That's it. No API keys, no tools, no cloud -- just a local model answering your questions.

CLI Commands¶

# Single question
diapason ask "Explain the difference between TCP and UDP"

# Interactive chat session (multi-turn conversation)
diapason chat

# Start the API server for the browser or desktop app
diapason serve

# Override the model for a single query
diapason ask -m qwen3.5:9b "Explain general relativity"

# Adjust temperature (0.0 = deterministic, 1.0 = creative)
diapason ask -t 0.2 "List the planets in our solar system"

# Output raw JSON
diapason ask --json "What is 2+2?"

Configuration Reference¶

The preset writes this to ~/.diapason/config.toml:

[engine]
default = "ollama"

[intelligence]
default_model = "qwen3.5:4b"       # Fast and lightweight
# default_model = "qwen3.5:9b"     # Better quality
# default_model = "llama3.1:8b"    # Alternative model

[agent]
default_agent = "simple"            # Single-turn, no tools

[server]
host = "0.0.0.0"
port = 8000

Model options¶

Model	Parameters	Speed	Quality	Best for
`qwen3.5:4b`	4B	Fast	Good	Quick answers, lightweight hardware
`qwen3.5:9b`	9B	Balanced	Better	General-purpose chat, explanations
`qwen3.5:35b`	35B	Slower	Best	Complex reasoning, detailed analysis
`llama3.1:8b`	8B	Balanced	Good	Alternative if you prefer Meta models

To switch models, either edit ~/.diapason/config.toml or override per-query:

diapason ask -m qwen3.5:35b "Write a detailed comparison of REST and GraphQL"

To pull a new model:

ollama pull qwen3.5:35b

Using the Browser App¶

Start the backend server and the React frontend with one command:

./scripts/quickstart.sh

This opens http://localhost:5173 in your browser with a full chat interface, streaming responses, and an energy monitoring dashboard.

To run just the API server (for use with the desktop app or external clients):

diapason serve

The server is OpenAI-compatible, so any client that works with the OpenAI API can point to http://localhost:8000/v1.

Using the Desktop App¶

Start the backend: diapason serve (or ./scripts/quickstart.sh).
Build the desktop app from the authenticated checkout. No release is currently published; on Carlito's Mac, use ./scripts/install-desktop.sh.
The app connects to http://localhost:8000 automatically.

Switching Models¶

You can change the default model at any time:

Edit the config:

# Open the config file
${EDITOR:-nano} ~/.diapason/config.toml
# Change default_model to your preferred model

Pull and switch in one step:

ollama pull deepseek-r1:14b
diapason ask -m deepseek-r1:14b "Hello"

Use an environment variable:

DIAPASON_MODEL=qwen3.5:9b diapason ask "Hello"

Troubleshooting¶

"No running engine found" -- Make sure Ollama is running. Start it with ollama serve or open the Ollama desktop app.

"Model not found" -- Pull the model first with ollama pull <model-name>. List available models with ollama list.

Slow responses -- Use a smaller model (qwen3.5:4b). Check available memory; models need RAM roughly equal to their parameter count in GB (e.g., 9B model needs ~9 GB).

Want to add tools later? -- Switch to the Code Assistant or Deep Research config. Simple chat is intentionally minimal.

Browser app not loading -- Make sure both the backend (diapason serve) and frontend are running. The ./scripts/quickstart.sh script starts both automatically.