From eaad48e391cf99d9cb60dfaad3c61459c0d228f5 Mon Sep 17 00:00:00 2001 From: Eduardo Fiuza Cruz Date: Mon, 12 Jan 2026 17:27:17 -0300 Subject: [PATCH] Update invitees.mdx Qwen2.5-Coder-32B-Instruct does not support ToolCalling while Qwen3-Coder-30B-A3B-Instruct do support it. When trying to use Qwen2.5-Coder-32B-Instruct during this RAG project the following error kept showing up: Bad request: {'code': '422', 'error_type': 'UNSUPPORTED_OPENAI_PARAMS', 'message': 'The following parameters are not supported for this model: tools', 'param': 'tools'} --- units/en/unit3/agentic-rag/invitees.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/units/en/unit3/agentic-rag/invitees.mdx b/units/en/unit3/agentic-rag/invitees.mdx index 294f39ad3..74aef7ea2 100644 --- a/units/en/unit3/agentic-rag/invitees.mdx +++ b/units/en/unit3/agentic-rag/invitees.mdx @@ -325,7 +325,7 @@ from llama_index.core.agent.workflow import AgentWorkflow from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI # Initialize the Hugging Face model -llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct") +llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen3-Coder-30B-A3B-Instruct") # Create Alfred, our gala agent, with the guest info tool alfred = AgentWorkflow.from_tools_or_functions(