BerriAI/litellm · error · ValueError

vertex_project is required for Vertex AI RAG ingestion. Set

Error message

vertex_project is required for Vertex AI RAG ingestion. Set it in vector_store config.

What it means

Raised at the start of the Vertex AI RAG ingestion flow when the vector_store config lacks the mandatory 'vertex_project' setting; without a GCP project id no RAG corpus endpoint can be addressed, so ingestion aborts before any API call.

Source

Thrown at litellm/rag/ingestion/vertex_ai_ingestion.py:98

        Store content in Vertex AI RAG corpus.

        Vertex AI workflow:
        1. Create RAG corpus (if not provided)
        2. Upload file using RAG API (Vertex AI handles chunking/embedding)

        Args:
            file_content: Raw file bytes
            filename: Name of the file
            content_type: MIME type
            chunks: Ignored - Vertex AI handles chunking
            embeddings: Ignored - Vertex AI handles embedding
            existing_file_id: Existing provider file ID, unsupported for Vertex AI

        Returns:
            Tuple of (rag_corpus_id, file_id)
        """
        if not self.project_id:
            raise ValueError("vertex_project is required for Vertex AI RAG ingestion. Set it in vector_store config.")

        # Get or create RAG corpus
        rag_corpus_id = self.vector_store_config.get("vector_store_id")
        if not rag_corpus_id:
            rag_corpus_id = await self._create_rag_corpus(
                display_name=self.ingest_name or "litellm-rag-corpus",
                description=self.vector_store_config.get("description"),
            )

        # Upload file to RAG corpus
        result_file_id = None
        if file_content and filename and rag_corpus_id:
            result_file_id = await self._upload_file_to_corpus(
                rag_corpus_id=rag_corpus_id,
                filename=filename,
                file_content=file_content,
                content_type=content_type,
            )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set vertex_project in the vector store config.

When it happens

Trigger: Thrown at litellm/rag/ingestion/vertex_ai_ingestion.py:98 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/7b2a615f08dfc5c8. Report an issue: GitHub.