config.py

import os

HF_TOKEN = os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN")
HF_MODEL = "Qwen/Qwen2.5-7B-Instruct"

_use_ollama = False
_ollama_mod = None
_hf_client = None
_llm_available = False

if os.environ.get("FORCE_HF", "1") != "1":
    try:
        if not os.environ.get("SPACE_ID"):
            import ollama as _ollama_mod
            _ollama_mod.list()
            _use_ollama = True
            _llm_available = True
    except Exception:
        _use_ollama = False

if _use_ollama:
    print("[startup] Using Ollama locally with qwen2.5:1.5b")
else:
    try:
        from huggingface_hub import InferenceClient
        _hf_client = InferenceClient(model=HF_MODEL, token=HF_TOKEN)
        _llm_available = bool(HF_TOKEN) or bool(os.environ.get("SPACE_ID"))
        print(f"[startup] HF Inference API — model={HF_MODEL}, token={'yes' if HF_TOKEN else 'space/default'}")
    except Exception as exc:
        print(f"[startup] HF client init failed: {exc}")
        _hf_client = None
        _llm_available = False


def llm_available() -> bool:
    return _llm_available and (_use_ollama or _hf_client is not None)


def call_llm(prompt: str, system: str = "") -> str:
    if not llm_available():
        return "[LLM Error: Model unavailable — using rule-based fallback]"

    messages = []
    if system:
        messages.append({"role": "system", "content": system})
    messages.append({"role": "user", "content": prompt})
    try:
        if _use_ollama:
            resp = _ollama_mod.chat(model="qwen2.5:1.5b", messages=messages)
            return resp["message"]["content"]
        resp = _hf_client.chat_completion(messages, max_tokens=2048, temperature=0.1)
        return resp.choices[0].message.content
    except Exception as e:
        return f"[LLM Error: {e}]"