Files
api/app/core/llm.py
roberto 314780d59a Add LLM configuration options and update deployment workflow
- Introduced new API keys for Anthropic and Google in .env.example and settings.py
- Updated llm.py to retrieve API keys directly from settings
- Modified deploy.yaml to streamline code checkout and improve deployment process
2026-03-03 16:52:56 +01:00

69 lines
2.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""LLM factory — centralised model instantiation via LiteLLM.
Every agent and the orchestrator call ``get_llm()`` or ``get_router_llm()``
instead of directly constructing a provider-specific class. The model string
follows the `LiteLLM model naming convention
<https://docs.litellm.ai/docs/providers>`_:
* OpenAI: ``gpt-4o``, ``gpt-4o-mini``
* Anthropic: ``anthropic/claude-3.5-sonnet``
* Google: ``gemini/gemini-pro``
* Ollama: ``ollama/llama3``
* Bedrock: ``bedrock/anthropic.claude-v2``
Switch providers by changing **LLM_MODEL** / **LLM_ROUTER_MODEL** in ``.env``
— no code changes required.
"""
from __future__ import annotations
from langchain_openai import ChatOpenAI
from litellm import get_supported_openai_params # noqa: F401 validates install
from app.config.settings import settings
def _api_key_for_model(model: str) -> str | None:
"""Return the most appropriate API key for the given LiteLLM model string."""
if model.startswith("anthropic/"):
return settings.ANTHROPIC_API_KEY or None
if model.startswith("gemini/") or model.startswith("google/"):
return settings.GOOGLE_API_KEY or None
# Default: OpenAI-compatible (covers plain model names like "gpt-4o")
return settings.OPENAI_API_KEY or None
def get_llm(
*,
model: str | None = None,
temperature: float = 0,
) -> ChatOpenAI:
"""Return a LangChain chat model backed by LiteLLM.
LiteLLM exposes an OpenAI-compatible API, so we use ``ChatOpenAI`` pointed
at the LiteLLM proxy endpoint. In practice, ``litellm`` patches the
``openai`` client transparently when the model string contains a provider
prefix (``anthropic/…``, ``gemini/…``, etc.).
Parameters
----------
model:
LiteLLM model identifier. Defaults to ``settings.LLM_MODEL``.
temperature:
Sampling temperature. ``0`` = deterministic.
"""
model = model or settings.LLM_MODEL
return ChatOpenAI(
model=model,
temperature=temperature,
api_key=_api_key_for_model(model),
)
def get_router_llm(
*,
temperature: float = 0,
) -> ChatOpenAI:
"""Return the lighter model used for intent classification / routing."""
return get_llm(model=settings.LLM_ROUTER_MODEL, temperature=temperature)