Update llama4 models

app.py

@@ -7,12 +7,13 @@ import pandas as pd
 import requests
 import rich
 import wikipediaapi
-from basic_agent import BasicAgent
-from get_model import get_model
 from mcp import StdioServerParameters
 from smolagents import DuckDuckGoSearchTool, FinalAnswerTool, Tool, ToolCollection, VisitWebpageTool
 from ycecream import y
 
+from basic_agent import BasicAgent
+from get_model import get_model
+
 y.configure(sln=1)
 print = rich.get_console().print
 
@@ -37,13 +38,14 @@ class BasicAgent:
         return fixed_answer
 # """
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """Fetch all questions, run the BasicAgent on them, submit all answers, and display the results."""
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -56,12 +58,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent(
-            model=get_model(cat="gemini"),
+            # model=get_model(cat="gemini"),
+            model=get_model(cat="llama"),
             tools=[
                 DuckDuckGoSearchTool(),
                 VisitWebpageTool(),
-                FinalAnswerTool(),
-            ]
+                # FinalAnswerTool(),
+            ],
         )
     except Exception as e:
         print(f"Error instantiating agent: {e}")
@@ -77,17 +80,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
 
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -107,8 +110,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -125,13 +128,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
+        final_status = f"Submission Successful!\nUser: {result_data.get('username')}\nOverall Score: {result_data.get('score', 'N/A')}% ({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\nMessage: {result_data.get('message', 'No message received.')}"
         print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
@@ -177,7 +174,10 @@ with gr.Blocks() as demo:
         ---
         **Disclaimers:**
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        This space provides a basic setup and is intentionally sub-optimal to encourage you
+        to develop your own, more robust solution. For instance for the delay process of the
+        submit button, a solution could be to cache the answers and submit in a seperate
+        action or even to answer the questions in async.
         """
     )
 
@@ -189,16 +189,13 @@ with gr.Blocks() as demo:
     # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -206,14 +203,14 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)

get_gemini_keys.py

@@ -11,7 +11,7 @@ from loguru import logger
 def get_gemini_keys(file=r".env-gemini", dotenv=False):
     """Get gemini keys."""
     if not Path(file).exists():
-        logger.debug(f"{file} does not exit, returing [] ")
+        logger.debug(f"{file} does not exit, returning [] ")
         return []
 
     if Path(file).name.startswith(".env"):

get_model.py

@@ -1,12 +1,14 @@
 """Create and return a model."""
+# ruff: noqa: F841
 
 import os
 import re
 from platform import node
 
-from get_gemini_keys import get_gemini_keys
 from loguru import logger
-from smolagents import HfApiModel, LiteLLMRouterModel
+from smolagents import HfApiModel, LiteLLMRouterModel, OpenAIServerModel
+
+from get_gemini_keys import get_gemini_keys
 
 
 def get_model(cat: str = "hf", provider=None, model_id=None):
@@ -14,13 +16,26 @@ def get_model(cat: str = "hf", provider=None, model_id=None):
     Create and return a model.
 
     Args:
-        cat: category
+        cat: category, hf, gemin, llama (default and fallback: hf)
         provider: for HfApiModel (cat='hf')
         model_id: model name
 
     if no gemini_api_keys, return HfApiModel()
 
     """
+    if cat.lower() in ["hf"]:
+        logger.info(" usiing HfApiModel, make sure you set HF_TOKEN")
+        return HfApiModel(provider=provider, model_id=model_id)
+
+    # setup proxy for gemini and for golay (local tetsin)
+    if "golay" in node() and cat.lower() in ["gemini", "llama"]:
+        os.environ.update(
+            HTTPS_PROXY="http://localhost:8081",
+            HTTP_PROXY="http://localhost:8081",
+            ALL_PROXY="http://localhost:8081",
+            NO_PROXY="localhost,127.0.0.1",
+        )
+
     if cat.lower() in ["gemini"]:
         # get gemini_api_keys
         # dedup
@@ -33,15 +48,6 @@ def get_model(cat: str = "hf", provider=None, model_id=None):
             logger.info(" set gemini but return HfApiModel()")
             return HfApiModel()
 
-        # setup proxy for gemini and for golay (local)
-        if "golay" in node():
-            os.environ.update(
-                HTTPS_PROXY="http://localhost:8081",
-                HTTP_PROXY="http://localhost:8081",
-                ALL_PROXY="http://localhost:8081",
-                NO_PROXY="localhost,127.0.0.1,oracle",
-            )
-
         if model_id is None:
             model_id = "gemini-2.5-flash-preview-04-17"
 
@@ -69,27 +75,27 @@ def get_model(cat: str = "hf", provider=None, model_id=None):
                 },
             },
         ]
-        
+
         # gemma-3-27b-it
         llm_loadbalancer_model_list_gemma = [
             {
                 "model_name": "model-group-3",
                 "litellm_params": {
-                    "model": f"gemini/gemma-3-27b-it",
+                    "model": "gemini/gemma-3-27b-it",
                     "api_key": os.getenv("GEMINI_API_KEY")                },
             },
         ]
-            
+
         fallbacks = []
         model_list = llm_loadbalancer_model_list_gemini
         if os.getenv("SILICONFLOW_API_KEY"):
             fallbacks = [{"model-group-1": "model-group-2"}]
             model_list += llm_loadbalancer_model_list_siliconflow
-        
+
         model_list += llm_loadbalancer_model_list_gemma
         fallbacks13 = [{"model-group-1": "model-group-3"}]
         fallbacks31 = [{"model-group-3": "model-group-1"}]
-        
+
         model = LiteLLMRouterModel(
             model_id="model-group-1",
             model_list=model_list,
@@ -108,6 +114,24 @@ def get_model(cat: str = "hf", provider=None, model_id=None):
 
         return model
 
+    if cat.lower() in ["llama"]:
+        api_key = os.getenv("LLAMA_API_KEY")
+        if api_key is None:
+            logger.warning(" LLAMA_API_EY not set, using HfApiModel(), make sure you set HF_TOKEN")
+            return HfApiModel()
+
+        # default model_id
+        if model_id is None:
+            model_id = "Llama-4-Maverick-17B-128E-Instruct-FP8"
+            model_id = "Llama-4-Scout-17B-16E-Instruct-FP8"
+        model_llama = OpenAIServerModel(
+            model_id,
+            api_base="https://api.llama.com/compat/v1",
+            api_key=api_key,
+            # temperature=0.,
+        )
+        return model_llama
+
     logger.info(" default return default HfApiModel(provider=None, model_id=None)")
     # if cat.lower() in ["hf"]:  default
     return HfApiModel(provider=provider, model_id=model_id)