gongzhiyongandClaude Opus 4.6
efb3c53623
- Add complete Python backend (Litestar + LangGraph) with chat, conversations, tickets APIs - Add GitHub Actions workflow for auto-deploying backend to Azure Web App (soc-backend) - Add gunicorn to requirements.txt for production serving - Update CLAUDE.md and EXTERNAL_SERVICES.md with latest config - Remove obsolete claudehd.md (merged into gpthd.md) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
"""LangGraph node functions."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from langchain_openai import AzureChatOpenAI
|
|
|
|
from app.config import settings
|
|
from app.graph.state import ChatState
|
|
|
|
# Model parameter presets
|
|
MODEL_PARAMS: dict[str, dict] = {
|
|
"flash": {"max_tokens": 500, "temperature": 0.2},
|
|
"pro": {"max_tokens": 4096, "temperature": 0.3},
|
|
}
|
|
|
|
|
|
def _get_llm(model: str) -> AzureChatOpenAI:
|
|
"""Create an AzureChatOpenAI instance with preset parameters."""
|
|
params = MODEL_PARAMS.get(model, MODEL_PARAMS["flash"])
|
|
return AzureChatOpenAI(
|
|
azure_endpoint=settings.azure_openai_endpoint,
|
|
api_key=settings.azure_openai_api_key,
|
|
api_version=settings.azure_openai_api_version,
|
|
azure_deployment=settings.azure_openai_deployment,
|
|
max_tokens=params["max_tokens"],
|
|
temperature=params["temperature"],
|
|
streaming=True,
|
|
)
|
|
|
|
|
|
async def call_model(state: ChatState) -> dict:
|
|
"""Invoke the LLM with the current message history."""
|
|
model = state.get("model", "flash")
|
|
llm = _get_llm(model)
|
|
response = await llm.ainvoke(state["messages"])
|
|
return {"messages": [response]}
|