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
57 lines
1.7 KiB
Python
57 lines
1.7 KiB
Python
"""
|
|
Slide 67: Slide 7
|
|
Section 3: Deep Agents
|
|
Source: slides/section3-deepagents/section3.pptx
|
|
|
|
Сгенерировано автоматически из slide-NN.js / sectionN.pptx.
|
|
Паттерн провайдера скопирован из
|
|
bro-js/agents/teacher/assistant/src/angry_teacher/llm.py.
|
|
|
|
Запуск:
|
|
cd langchain-evolution-deck
|
|
cp .env.example .env # заполни OPENAI_API_KEY
|
|
python examples/slide-067/script.py
|
|
"""
|
|
import os
|
|
from dotenv import load_dotenv
|
|
from langchain_openai import ChatOpenAI
|
|
|
|
load_dotenv()
|
|
|
|
llm = ChatOpenAI(
|
|
# model="openrouter/free",
|
|
# model="qwen/qwen3.5-35b-a3b",
|
|
model="openai/gpt-oss-20b",
|
|
# model="nvidia/nemotron-3-nano",
|
|
# model="qwen/qwen3.5-9b",
|
|
base_url="https://llm.brojs.ru/v1",
|
|
# base_url="https://api.minimax.io/v1",
|
|
# base_url="http://0.0.0.0:8090/v1",
|
|
# base_url="https://openrouter.ai/api/v1",
|
|
# api_key=os.getenv("MINIMAX_API_KEY"),
|
|
api_key=(os.getenv("OPENAI_API_KEY") or "").strip() or None,
|
|
temperature=0.7,
|
|
stream_usage=True,
|
|
)
|
|
|
|
|
|
# === Code from slide 67 ===
|
|
// examples/system_prompt.py:1-16
|
|
|
|
SYSTEM_PROMPT = """
|
|
You are a senior backend engineer.
|
|
|
|
> WORKFLOW:
|
|
> 1. Plan with write_todos before non-trivial work.
|
|
> 2. Explore the codebase via ls / glob / grep first.
|
|
> 3. Use edit_file for surgical changes, write_file for new files.
|
|
> 4. Delegate research tasks to the "researcher" subagent.
|
|
5. Run tests via execute; never claim success without output.
|
|
|
|
CONSTRAINTS:
|
|
> - Do not modify files outside ./src.
|
|
> - Stop and ask the user if requirements are ambiguous.
|
|
"""
|
|
|
|
agent = create_deep_agent(model=..., system_prompt=SYSTEM_PROMPT)
|