Last active
September 7, 2026 04:03
-
-
Save kyzmitch/7596ffa18a355939aaef40f16fa924f8 to your computer and use it in GitHub Desktop.
How to run graphify with LLM
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # 0. Install | |
| brew install uv | |
| # 0.1 Install more | |
| export OPENAI_BASE_URL="https://api.siliconflow.com/v1" | |
| export OPENAI_API_KEY="your-siliconflow-api-key" | |
| # 3 LLM must be Visual Language Model for graphify!!! which is crazy | |
| export OPENAI_MODEL="deepseek-ai/DeepSeek-V4-Flash-0731" | |
| # 3.1 | |
| uv tool install "graphifyy[openai]" --force | |
| # 4. Run Graphify forcing the openai backend wrapper | |
| graphify . --backend openai | |
| # Or pass the model on the CLI: | |
| graphify extract /Users/user/ \ | |
| --backend openai \ | |
| --model deepseek-ai/DeepSeek-V4 | |
| # Full working sequence | |
| # 1. Install with OpenAI backend support (one-time) | |
| uv tool install "graphifyy[openai]" --force | |
| # 2. Configure SiliconFlow | |
| export OPENAI_BASE_URL="https://api.siliconflow.com/v1" | |
| export OPENAI_API_KEY="sk-..." # your SiliconFlow key | |
| export OPENAI_MODEL="deepseek-ai/DeepSeek-V4" | |
| # 3. Run on catowseriOS | |
| graphify /Users/sourcecode/folder --backend openai |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment