This presents a unified, standalone AI chatbot combining concepts from multiple eSim AI proposals:
- Netlist Analyzer: Automatically extracts syntax validations, checks for floating nodes, misses of subcircuits or SPICE models (From PR-434).
- Semantics & RAG Engine Base: Integrating Langchain and Ollama logic structure (From PR-394).
- Consolidated UI: A PyQt5 Desktop application unifying both the capabilities into one separate product.
-
Install requirements: Make sure you have an active virtual environment that supports Python 3.9 / 3.10.
pip install -r requirements.txt
-
Ollama Setup: For the LLM features, you should have Ollama running locally.
ollama serve ollama pull qwen2.5-coder:3b
-
Run the Interface:
python main.py
- Load Netlist: Browse and select a
.ciror.cir.outfile from your system. - Analyze Netlist: Runs background SPICE validations and logic checks to identify bad designs, floating nodes, and missing models. It saves the structured output.
- Ask AI: You can query the bot about your analyzed netlist and general EDA / eSim problems.