tool_runtime.rag_tool.insert not working

[maxeramax]

Hello,

I'm experiencing some incompatibility issues with the interaction between client and server, both installed from PyPy, version 0.3.2

An example of such is the following call:

client.tool_runtime.rag_tool.insert( documents=documents, vector_db_id=vs.id, chunk_size_in_tokens=512, )

which raises the error:

lib/python3.12/site-packages/llama_stack_client/_base_client.py", line 1054, in request raise self._make_status_error_from_response(err.response) from None llama_stack_client.BadRequestError: Error code: 400 - {'error': {'detail': {'errors': [{'loc': ['body', 'vector_store_id'], 'msg': 'Field required', 'type': 'missing'}]}}}

By looking at the API, the arguments passed to the client should be correct:

`insert(*, chunk_size_in_tokens: 'int', documents: 'Iterable[Document]', vector_db_id: 'str', extra_headers: 'Headers | None' = None, extra_query: 'Query | None' = None, extra_body: 'Body | None' = None, timeout: 'float | httpx.Timeout | None | NotGiven' = NOT_GIVEN) -> 'None' method of llama_stack_client.resources.tool_runtime.rag_tool.RagToolResource instance
Index documents so they can be used by the RAG system.

Args:
  chunk_size_in_tokens: (Optional) Size in tokens for document chunking during indexing

  documents: List of documents to index in the RAG system

  vector_db_id: ID of the vector database to store the document embeddings

  extra_headers: Send extra headers

  extra_query: Add additional query parameters to the request

  extra_body: Add additional JSON properties to the request

  timeout: Override the client-level default timeout for this request, in seconds

~`

System:
Linux ai 6.14.0-36-generic #36~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 15 15:45:17 UTC 2 x86_64 x86_64 x86_64 GNU/Linux Python 3.12.3

[maxeramax]

Same problem also in version 0.3.3