diff --git a/units/en/unit2/llama-index/agents.mdx b/units/en/unit2/llama-index/agents.mdx
index 927a1645..65661f2f 100644
--- a/units/en/unit2/llama-index/agents.mdx
+++ b/units/en/unit2/llama-index/agents.mdx
@@ -42,7 +42,11 @@ def multiply(a: int, b: int) -> int:
     return a * b
 
 # initialize llm
-llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
+# Check available providers: https://huggingface.co/inference/models
+llm = HuggingFaceInferenceAPI(
+    model_name="Qwen/Qwen2.5-Coder-32B-Instruct",
+    provider="auto"
+)
 
 # initialize agent
 agent = AgentWorkflow.from_tools_or_functions(
diff --git a/units/en/unit2/llama-index/components.mdx b/units/en/unit2/llama-index/components.mdx
index 29549831..be211574 100644
--- a/units/en/unit2/llama-index/components.mdx
+++ b/units/en/unit2/llama-index/components.mdx
@@ -159,7 +159,12 @@ We also pass in an LLM to the query engine to use for the response.
 ```python
 from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
 
-llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
+# Check available providers: https://huggingface.co/inference/models
+llm = HuggingFaceInferenceAPI(
+    model_name="Qwen/Qwen2.5-Coder-32B-Instruct",
+    provider="auto"
+)
+
 query_engine = index.as_query_engine(
     llm=llm,
     response_mode="tree_summarize",
diff --git a/units/en/unit2/llama-index/workflows.mdx b/units/en/unit2/llama-index/workflows.mdx
index 70926e40..462b07d3 100644
--- a/units/en/unit2/llama-index/workflows.mdx
+++ b/units/en/unit2/llama-index/workflows.mdx
@@ -201,7 +201,11 @@ def multiply(a: int, b: int) -> int:
     """Multiply two numbers."""
     return a * b
 
-llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
+# Check available providers: https://huggingface.co/inference/models
+llm = HuggingFaceInferenceAPI(
+    model_name="Qwen/Qwen2.5-Coder-32B-Instruct",
+    provider="auto"
+)
 
 # we can pass functions directly without FunctionTool -- the fn/docstring are parsed for the name/description
 multiply_agent = ReActAgent(
diff --git a/units/en/unit3/agentic-rag/agent.mdx b/units/en/unit3/agentic-rag/agent.mdx
index 396db87e..8278663d 100644
--- a/units/en/unit3/agentic-rag/agent.mdx
+++ b/units/en/unit3/agentic-rag/agent.mdx
@@ -69,7 +69,11 @@ Now, let's combine all these tools into a single agent:
 
 ```python
 # Initialize the Hugging Face model
-llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
+# Check available providers: https://huggingface.co/inference/models
+llm = HuggingFaceInferenceAPI(
+    model_name="Qwen/Qwen2.5-Coder-32B-Instruct",
+    provider="auto"
+)
 
 # Create Alfred with all the tools
 alfred = AgentWorkflow.from_tools_or_functions(
@@ -90,7 +94,8 @@ from langgraph.graph import START, StateGraph
 from langgraph.prebuilt import tools_condition
 from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 
-from tools import DuckDuckGoSearchRun, weather_info_tool, hub_stats_tool
+from langchain_community.tools import DuckDuckGoSearchRun
+from tools import weather_info_tool, hub_stats_tool
 from retriever import guest_info_tool
 ```