BerriAI/litellm · error · SambaNovaError

{raw_response.text}

Error message

{raw_response.text}

What it means

For SambaNova embeddings, LiteLLM parses the HTTP response with .json(); on failure it raises SambaNovaError whose message is the raw response body text and whose status/headers come from the original response. The body text is the primary diagnostic: it usually reveals why the server returned non-JSON.

Source

Thrown at litellm/llms/sambanova/embedding/transformation.py:117

            "model": model,
            **optional_params,
        }

    def transform_embedding_response(
        self,
        model: str,
        raw_response: httpx.Response,
        model_response: EmbeddingResponse,
        logging_obj: LiteLLMLoggingObj,
        api_key: str | None,
        request_data: dict,
        optional_params: dict,
        litellm_params: dict,
    ) -> EmbeddingResponse:
        try:
            raw_response_json: Final = raw_response.json()
        except Exception:
            raise SambaNovaError(
                message=raw_response.text,
                status_code=raw_response.status_code,
                headers=raw_response.headers,
            )

        model_response.model = raw_response_json.get("model")
        model_response.data = raw_response_json.get("data")
        model_response.object = raw_response_json.get("object")

        usage: Final = Usage(
            prompt_tokens=raw_response_json.get("usage", {}).get("prompt_tokens", 0),
            total_tokens=raw_response_json.get("usage", {}).get("total_tokens", 0),
        )

        model_response.usage = usage
        return model_response

    def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BaseLLMException:

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Read the body text in the error - an HTML title like '404 Not Found' means the URL path is wrong.
2. Verify api_base: LiteLLM appends /embeddings only when missing, so do not double-append it yourself.
3. Check the API key (SAMBANOVA_API_KEY) is set and valid for that deployment.
4. If 5xx, retry later or check the SambaNova status page / your self-hosted gateway health.

Example fix

# before - path already contains /embeddings and a typo
api_base='https://api.sambanova.ai/v1/embeddingsx'
# after - clean base, /embeddings appended automatically
api_base='https://api.sambanova.ai/v1'

from litellm.llms.sambanova.embeddings import SambaNovaError

try:
    resp = litellm.embedding(model='sambanova/E5-Embeddings-300M', input=texts, api_base=API_BASE)
except SambaNovaError as e:
    log.error('sambanova returned status %s body=%s', e.status_code, e.message)
    raise

When it happens

Trigger: api_base pointing at a wrong path (HTML 404 page), an auth error returned as plain text, a gateway/WAF error page, or an empty body from a 502/503 outage at the SambaNova endpoint.

Common situations: api_base manually set to a URL that already includes /embeddings plus a typo; expired API key producing a text 401; internal SambaNova Enterprise LaunchPad route changed between environments.

Understand the failure class

Background: "Invalid JSON response" and "Failed to parse response" errors: when an API answers 200 but the body isn't the JSON your library expected — this error's family across 28 libraries.

Related errors

• Failed to parse response: {e}
• Mavvrik FOCUS destination: response missing 'url' field: {re
• AgentCore: Failed to read/parse JSON response body: {e}
• No embedding data found in response: {response}
• Error parsing BFL response: {e}

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/cca76b2ecbb2e0cd. Report an issue: GitHub.