BerriAI/litellm · error · ValueError

LLM router not initialized

Error message

LLM router not initialized

What it means

_stream_llm_competitor_names needs the proxy's llm_router to dispatch the enrichment LLM call; when the router is None (proxy started without models configured), it raises ValueError, which the endpoint surfaces as a server error. At-fault condition is missing LLM infrastructure, not user input.

Source

Thrown at litellm/proxy/management_endpoints/policy_endpoints/endpoints.py:781

        "no numbering, no explanations. If the instruction asks to remove names, "
        "return nothing."
    )


async def _stream_llm_competitor_names(
    prompt: str,
    model: str,
    existing: list[str],
) -> AsyncIterator[tuple[str | None, bool]]:
    """
    Stream competitor names from LLM. Yields (name, is_error) tuples.

    Deduplicates against existing names (case-insensitive).
    """
    from litellm.proxy.proxy_server import llm_router

    if llm_router is None:
        raise ValueError("LLM router not initialized")

    existing_lower: Final = {n.lower() for n in existing}
    response: Final = await llm_router.acompletion(
        model=model,
        messages=[{"role": "user", "content": prompt}],
        temperature=COMPETITOR_LLM_TEMPERATURE,
        stream=True,
    )
    buffer = ""
    count = len(existing)
    async for chunk in response:
        delta = chunk.choices[0].delta.content or ""
        buffer += delta
        while "\n" in buffer:
            line, buffer = buffer.split("\n", 1)
            name = _clean_competitor_line(line)
            if name and name.lower() not in existing_lower and count < MAX_COMPETITOR_NAMES:
                existing_lower.add(name.lower())

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Configure models on the proxy so the LLM router initializes.

When it happens

Trigger: Thrown at litellm/proxy/management_endpoints/policy_endpoints/endpoints.py:781 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/77fa9e2a141590e7. Report an issue: GitHub.