BerriAI/litellm · error · ValueError
RAG ingestion not supported for provider: {custom_llm_provid
Error message
RAG ingestion not supported for provider: {custom_llm_provider}. Supported providers: {list(provider_map.keys())} What it means
Provider-map lookup failure in the RAG ingestion resolver: the given custom_llm_provider is not one of openai/bedrock/vertex_ai, so no ingestion class exists. A generic guard against unsupported provider strings.
Source
Thrown at litellm/rag/utils.py:38
Returns:
The ingestion class for the provider
Raises:
ValueError: If the provider is not supported
"""
from litellm.llms.vertex_ai.rag_engine.ingestion import VertexAIRAGIngestion
from litellm.rag.ingestion.bedrock_ingestion import BedrockRAGIngestion
from litellm.rag.ingestion.openai_ingestion import OpenAIRAGIngestion
provider_map: Final = {
"openai": OpenAIRAGIngestion,
"bedrock": BedrockRAGIngestion,
"vertex_ai": VertexAIRAGIngestion,
}
ingestion_class: Final = provider_map.get(custom_llm_provider)
if ingestion_class is None:
raise ValueError(
f"RAG ingestion not supported for provider: {custom_llm_provider}. "
f"Supported providers: {list(provider_map.keys())}"
)
return ingestion_class
def get_rag_transformation_class(custom_llm_provider: str):
"""
Get the appropriate RAG transformation class for a provider.
Args:
custom_llm_provider: The LLM provider name
Returns:
The transformation class for the provider, or None if not needed
"""
if custom_llm_provider == "vertex_ai":View on GitHub (pinned to 77b7c6c40c)
Solutions
- Use a supported custom_llm_provider for RAG ingestion (one of the listed provider_map keys).
Defensive patterns
Strategy: validation
When it happens
Trigger: Thrown at litellm/rag/utils.py:38 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/9a62943bd841b5f6.
Report an issue: GitHub.