roberto
8bfce9da00
- Replaced direct instantiation of ChatOpenAI with a centralized get_llm function in CheckpointAgent, NoteAgent, ProjectAgent, and TaskAgent. - Introduced a new llm.py module to handle LLM model instantiation and API key management. - Updated settings.py to include LLM_MODEL and LLM_ROUTER_MODEL configurations. - Modified orchestrator.py to use get_router_llm for intent classification. - Updated requirements.txt to include litellm for LLM management. - Adjusted tests to mock get_llm instead of ChatOpenAI directly.
69 lines
2.3 KiB
Python
69 lines
2.3 KiB
Python
"""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 getattr(settings, "ANTHROPIC_API_KEY", None) or None
|
||
if model.startswith("gemini/") or model.startswith("google/"):
|
||
return getattr(settings, "GOOGLE_API_KEY", None) 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)
|