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
55 lines
2.0 KiB
Python
55 lines
2.0 KiB
Python
"""
|
|
Slide 51: Slide 24
|
|
Section 2: LangGraph 1.0
|
|
Source: slides/section2-langgraph/section2.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-051/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 51 ===
|
|
cfg = {"configurable": {"thread_id": "u1"}}
|
|
# values -- весь state после каждого super-step
|
|
> for snap in app.stream({"messages": []}, cfg, stream_mode="values"):
|
|
print(snap["messages"][-1].content)
|
|
# updates -- delta: только что вернул каждый узел
|
|
> for upd in app.stream({"messages": []}, cfg, stream_mode="updates"):
|
|
print(upd)
|
|
# events -- низкоуровневые события (start, end, error, interrupt)
|
|
> for ev in app.stream({"messages": []}, cfg, stream_mode="events"):
|
|
print(ev["event"], ev["name"])
|
|
# messages -- токены LLM по мере генерации
|
|
> for tok, meta in app.stream({"messages": []}, cfg, stream_mode="messages"):
|
|
print(tok.content, end="|")
|
|
# custom -- только то, что узлы пишут через get_stream_writer()
|
|
> for chunk in app.stream({"messages": []}, cfg, stream_mode="custom"):
|
|
print(chunk)
|