Skip to main content

​
Examples

All examples are in the examples/ directory. Each is self-contained and runnable.

​
Quick Start

ExampleWhat It Shows
basic_usage.pyMinimal @llm_function call with typed output
template_params_example.pyDynamic docstring templates with _template_params

​
Tool Usage

ExampleWhat It Shows
tool_usage_example.py@tool decorator, multi-tool agent
multimodal_tool_example.pyTools returning ImgPath/ImgUrl
agent_as_tool_example.pyNesting one agent as a tool for another

​
Chat & Streaming

ExampleWhat It Shows
streaming_example.pyConsuming LLMChunkArriveEvent for real-time output
event_stream_example.pyFull event stream consumption pattern
abort_example.pyAbortSignal for cancellation

​
PyRepl & Runtime

ExampleWhat It Shows
pyrepl_example.pyPersistent REPL: variables, streaming, reset
pyrepl_seaborn_multimodal_images.pyPyRepl image artifact capture and multimodal tool return with multiple seaborn plots
selfref_example.pyruntime.selfref.context.* primitives

​
Full Agent

ExampleWhat It Shows
tui_general_agent_example.pyComplete coding agent with TUI, PyRepl, FileToolset, SelfRef, fork, compaction
This is the reference implementation for building a production agent. See Harness Patterns for an architectural walkthrough.

​
Running Examples

# Clone the repo
git clone https://github.com/NiJingzhe/SimpleLLMFunc.git
cd SimpleLLMFunc

# Install dependencies
poetry install

# Copy and configure provider.json
cp examples/provider_template.json examples/provider.json
# Edit examples/provider.json with your API keys

# Run any example
poetry run python examples/basic_usage.py
poetry run python examples/tui_general_agent_example.py

​
Building Your Own

Start from one of these patterns:

One-shot Function

@llm_function — typed input/output, no state

Chat Agent

@llm_chat + tools — multi-turn with ReAct loop

Full Agent

PyRepl + SelfRef + FileToolset + TUI — production-grade