How devanshikansara/localaiengineering works
This small prototype turns a natural-language CAM request into deterministic calculations: the LLM interprets the request and orchestrates tool calls, Python validates inputs and calculates results, and the LLM presents the response. The README documents the local Ollama/Qwen3:4B integration and dependent calculation chain; the sampled source confirms the registry dispatches to three calculation functions. The LLM interaction implementation was not sampled, so its links are based on README statements.
Main entry points: test_llm.py LLM interaction · tool_registry.py Tool registry · engineering_tools.py Spindle speed
Components 7
LLM interaction
- LLM interaction
test_llm.py
Tool dispatch
- Tool registry
tool_registry.py
Engineering calculations
- Spindle speed
engineering_tools.py - Feed rate
engineering_tools.py - Cutting time
engineering_tools.py
Other components
- User
- Ollama / Qwen3:4B
Connections 11
- User → LLM interaction: sends request
README.md - LLM interaction → Ollama / Qwen3:4B: interprets request
README.md - Ollama / Qwen3:4B → LLM interaction: selects tools
README.md - LLM interaction → Tool registry: requests execution
README.md - Tool registry → Spindle speed: dispatches
tool_registry.py - Tool registry → Feed rate: dispatches
tool_registry.py - Tool registry → Cutting time: dispatches
tool_registry.py - LLM interaction → Ollama / Qwen3:4B: returns tool results
README.md - Ollama / Qwen3:4B → LLM interaction: interprets results
README.md - LLM interaction → User: presents result
README.md - Ollama / Qwen3:4B → LLM interaction: chains dependent tools
README.md