petya
1fd7486a85
Each of the 122 code slides now has a standalone .py script in examples/slide-NNN/script.py with the LLM provider pattern from bro-js/agents/teacher/assistant/src/angry_teacher/llm.py: - load_dotenv() + ChatOpenAI with base_url=https://llm.brojs.ru/v1 - OPENAI_API_KEY from .env (with safe (or '' or None) pattern) - Same comment block with alternative model/base_url choices Layout: - sec1/sec5: code extracted from slide-NN.js (addCodeBlock) - sec2/sec3/sec4: code extracted from sectionN.pptx via python-pptx (JetBrains Mono font shapes) 100 scripts contain runnable code, 22 are visual-only (dividers, intro, recap) and just print the slide title. Setup: cp .env.example .env # fill OPENAI_API_KEY (or symlink to your # teacher/assistant/.env) pip install -r requirements.txt python examples/slide-005/script.py
24 lines
592 B
Plaintext
24 lines
592 B
Plaintext
# Python deps для examples/*.py
|
|
# Запуск: pip install -r requirements.txt
|
|
# (или uv pip install -r requirements.txt)
|
|
|
|
# LLM provider (паттерн скопирован из bro-js/agents/teacher/assistant)
|
|
python-dotenv>=1.0.0
|
|
langchain-openai>=0.2.0
|
|
langchain>=1.0.0
|
|
langchain-core>=1.0.0
|
|
|
|
# LangGraph 1.0 (секция 2)
|
|
langgraph>=1.0.0
|
|
|
|
# Deep Agents (секция 3)
|
|
deepagents>=0.6.0
|
|
|
|
# Open SWE (секция 4) — приложение, не pip-пакет; см. github.com/langchain-ai/open-swe
|
|
|
|
# LangSmith (секция 5)
|
|
langsmith>=0.8.0
|
|
|
|
# Tooling
|
|
pydantic>=2.0
|