crewAIInc/crewAI · error · BedrockValidationError

knowledge_base_id cannot be empty

Error message

knowledge_base_id cannot be empty

What it means

A BedrockValidationError raised in BedrockKBRetrieverTool._validate_parameters when knowledge_base_id is falsy (None or ''). AWS Retrieve requires a knowledge base ID, so the tool refuses to construct without one; like the agent tool, the whole block is re-wrapped as "Parameter validation failed: ..." by the caller's except.

Solutions

1. Copy the Knowledge base ID from the Bedrock console (10 alphanumeric characters, e.g. 'HHTQ7DFZLV') and pass it explicitly.
2. Fail fast on config: knowledge_base_id=os.environ['BEDROCK_KB_ID'] instead of os.environ.get(...) or ''.
3. Check you are not passing the data source ID or collection ARN — those are different fields.

Example fix

# before
tool = BedrockKBRetrieverTool(knowledge_base_id=os.environ.get("BEDROCK_KB_ID", ""))

# after
tool = BedrockKBRetrieverTool(knowledge_base_id=os.environ["BEDROCK_KB_ID"])  # KeyError tells you the var is missing

import os, re

kb_id = os.environ.get("BEDROCK_KB_ID", "")
if not kb_id:
    raise SystemExit("BEDROCK_KB_ID not set — copy the Knowledge base ID from the Bedrock console")

def is_kb_id(v) -> bool:
    return isinstance(v, str) and bool(v)

try:
    tool = BedrockKBRetrieverTool(knowledge_base_id=kb_id)
except BedrockValidationError as e:
    raise ValueError(f"Bad KB config: {e}") from e

When it happens

Trigger: Creating the KB retriever tool with knowledge_base_id='' or None — typically the ID was loaded from a missing env var/config and defaulted to empty.

Common situations: Env var (e.g. BEDROCK_KB_ID) not exported in the runtime environment; wrong attribute copied from the console (knowledge base name instead of the 10-char alphanumeric ID); multi-stage pipelines where the ID is conditionally set and the branch was skipped.

Related errors

• agent_alias_id cannot be empty
• agent_id cannot be empty
• knowledge_base_id must be 10 characters or less
• knowledge_base_id must be a string
• knowledge_base_id must contain only alphanumeric characters

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/fb3d5df6d0020cdb. Report an issue: GitHub.

Appendix: source

Thrown at lib/crewai-tools/src/crewai_tools/aws/bedrock/knowledge_base/retriever_tool.py:93

    def _build_retrieval_configuration(self) -> dict[str, Any]:
        """Build the retrieval configuration based on provided parameters.

        Returns:
            Dict[str, Any]: The constructed retrieval configuration
        """
        vector_search_config = {}

        if self.number_of_results is not None:
            vector_search_config["numberOfResults"] = self.number_of_results

        return {"vectorSearchConfiguration": vector_search_config}

    def _validate_parameters(self) -> None:
        """Validate the parameters according to AWS API requirements."""
        try:
            if not self.knowledge_base_id:
                raise BedrockValidationError("knowledge_base_id cannot be empty")
            if not isinstance(self.knowledge_base_id, str):
                raise BedrockValidationError("knowledge_base_id must be a string")
            if len(self.knowledge_base_id) > 10:
                raise BedrockValidationError(
                    "knowledge_base_id must be 10 characters or less"
                )
            if not all(c.isalnum() for c in self.knowledge_base_id):
                raise BedrockValidationError(
                    "knowledge_base_id must contain only alphanumeric characters"
                )

            if self.next_token:
                if not isinstance(self.next_token, str):
                    raise BedrockValidationError("next_token must be a string")
                if len(self.next_token) < 1 or len(self.next_token) > 2048:
                    raise BedrockValidationError(
                        "next_token must be between 1 and 2048 characters"
                    )

View on GitHub (pinned to 754d7323be)