BerriAI/litellm · error · ValueError

RSS feed missing element

Error message

RSS feed missing <channel> element

What it means

get_llm_provider() (litellm_core_utils/get_llm_provider_logic.py) opens with early validation: if the model argument is None it immediately raises ValueError('model parameter is required but was None. Please provide a valid model name.') before any provider detection runs. Its job is resolving 'azure/foo' or 'openrouter/bar' prefixes to a provider, and None makes that impossible.

Solutions

1. Find where the model value originates (env var, config, function arg) and make it a required, validated string.
2. For Router/proxy configs, ensure every model_list entry has litellm_params.model set to a valid name like 'azure/my-deployment'.
3. Fail fast at config load: validate all model strings before entering request paths.
4. Use a sentinel/default model explicitly instead of letting None propagate.

Example fix

# before
model = os.getenv("MODEL")          # None when unset
litellm.completion(model=model, messages=msgs)

# after
model = os.environ["MODEL"]          # KeyError at startup, not mid-request
litellm.completion(model=model, messages=msgs)

import xml.etree.ElementTree as ET
root = ET.fromstring(xml_text)
assert root.find("channel") is not None, "document is not an RSS 2.0 feed; refusing to parse"
posts = RssClient.parse_rss_to_posts(xml_text)

def is_rss2_feed(xml_text: str) -> bool:
    try:
        return ET.fromstring(xml_text).find("channel") is not None
    except ET.ParseError:
        return False

try:
    posts = RssClient.parse_rss_to_posts(xml_text)
except ValueError as e:
    if "missing <channel>" in str(e):
        log.warning("feed shape changed or was blocked; skipping blog posts")
        posts = []
    else:
        raise

When it happens

Trigger: litellm.completion(model=None, ...) or Router/get_llm_provider calls where the model string never got set: template/env-driven config leaving it blank, a dict key mismatch (using 'model_name' vs 'model'), or a deployment entry whose model field is absent.

Common situations: Dynamic code building the model string that yields None (env var unset, lookup miss); LiteLLM Proxy model_list entries missing 'litellm_params.model'; refactors renaming the variable passed as model; optional model args defaulting to None.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• Cisco AI Defense guardrail: invalid rule definition
• Event hook is not in the supported event hooks
• Event hook is not in the supported event hooks
• max_bytes_per_call must be >= 0 (0 disables the cap…
• api_base is required

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/8430eed166b0f799. Report an issue: GitHub.

Appendix: source

Thrown at litellm/litellm_core_utils/get_blog_posts.py:78

        Fetch RSS XML from a remote URL.

        Returns the raw XML text. Raises on network errors.
        """
        response: Final = httpx.get(url, timeout=timeout)
        response.raise_for_status()
        return response.text

    @staticmethod
    def parse_rss_to_posts(xml_text: str, max_posts: int = 1) -> list[dict[str, str]]:
        """
        Parse RSS XML and return a list of blog post dicts.

        Extracts title, description, date (YYYY-MM-DD), and url from each <item>.
        """
        root: Final = ET.fromstring(xml_text)
        channel: Final = root.find("channel")
        if channel is None:
            raise ValueError("RSS feed missing <channel> element")

        posts: Final[list[dict[str, str]]] = []
        for item in channel.findall("item"):
            if len(posts) >= max_posts:
                break

            title_el = item.find("title")
            link_el = item.find("link")
            desc_el = item.find("description")
            pub_date_el = item.find("pubDate")

            if title_el is None or link_el is None:
                continue

            # Parse RFC 2822 date to YYYY-MM-DD
            date_str = ""
            if pub_date_el is not None and pub_date_el.text:
                try:

View on GitHub (pinned to 77b7c6c40c)