Update src/streamlit_app.py

src/streamlit_app.py

@@ -9,6 +9,27 @@ MODEL = "Qwen/Qwen3-Embedding-0.6B"
 # remembers session
 if "response" not in st.session_state:
     st.session_state.response = ""
+
+# source: https://medium.com/@james.irving.phd/creating-your-personal-chatbot-using-hugging-face-spaces-and-streamlit-596a54b9e3ed
+def get_llm(model_id=MODEL, max_new_tokens=130, temperature=0.7):
+    """
+    Returns a language model for HuggingFace inference.
+
+    Parameters:
+    - model_id (str): The ID of the HuggingFace model repository.
+    - max_new_tokens (int): The maximum number of new tokens to generate.
+    - temperature (float): The temperature for sampling from the model.
+
+    Returns:
+    - llm (HuggingFaceEndpoint): The language model for HuggingFace inference.
+    """
+    llm = HuggingFaceEndpoint(
+        repo_id=model_id,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        token = os.getenv("HF_TOKEN")
+    )
+    return llm
     
 # create llm
 llm = get_llm()
@@ -103,23 +124,3 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
-# source: https://medium.com/@james.irving.phd/creating-your-personal-chatbot-using-hugging-face-spaces-and-streamlit-596a54b9e3ed
-def get_llm(model_id=MODEL, max_new_tokens=130, temperature=0.7):
-    """
-    Returns a language model for HuggingFace inference.
-
-    Parameters:
-    - model_id (str): The ID of the HuggingFace model repository.
-    - max_new_tokens (int): The maximum number of new tokens to generate.
-    - temperature (float): The temperature for sampling from the model.
-
-    Returns:
-    - llm (HuggingFaceEndpoint): The language model for HuggingFace inference.
-    """
-    llm = HuggingFaceEndpoint(
-        repo_id=model_id,
-        max_new_tokens=max_new_tokens,
-        temperature=temperature,
-        token = os.getenv("HF_TOKEN")
-    )
-    return llm