Update app.py

app.py

@@ -1,97 +1,114 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from typing import Optional, Dict, Any
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# 
 
-
-class BasicAgent:
+class LLMClient:
     """
-    Default: Meta-Llama-3-8B-Instruct
+    Pluggable LLM client that avoids Hugging Face Inference API.
+    Supported providers:
+      - openai: uses OpenAI Chat Completions API
+      - together: uses Together.ai Chat Completions API (OpenAI-compatible)
     """
 
-    # In __init__ of BasicAgent
-    def __init__(self, model_id: str = "HuggingFaceH4/zephyr-7b-beta"):
-        model_id_env = os.getenv("HF_MODEL_ID")
-        self.model_id = model_id_env.strip() if model_id_env else model_id
-        
-        self.api_url = f"https://huggingface.co/api/models/{self.model_id}" #https://api-inference.huggingface.co/models/
-        self.api_token = os.getenv("HF_TOKEN")
-        if not self.api_token:
-            raise ValueError("❌ Hugging Face API token not found. Please set 'HF_TOKEN' as env variable.")
-        self.headers = {"Authorization": f"Bearer {self.api_token}"}
-        # ... keep session/retries as you have ...
-
-    def __call__(self, question: str, 
-                 max_new_tokens: int = 512, 
-                 temperature: float = 0.6, 
-                 top_p: float = 0.9) -> str:
-        """
-        Takes a question, sends it to the LLM via the Inference API, and returns the answer.
-        """
-        print(f"📝 Agent received question (preview): {question[:80]}...")
+    def __init__(self):
+        self.provider = (os.getenv("LLM_PROVIDER") or "openai").strip().lower()
+
+        if self.provider == "openai":
+            self.api_key = os.getenv("OPENAI_API_KEY")
+            if not self.api_key:
+                raise ValueError("OPENAI_API_KEY is required when LLM_PROVIDER=openai.")
+            # Default small, fast, and cheap model
+            self.model = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+            self.base_url = os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1")
+            self.headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
+            }
 
-        # Prompt formatting for Llama-3 style
-        payload = {
-            "inputs": (
-                f"<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n"
-                f"{question}\n<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
-            ),
-            "parameters": {
-                "max_new_tokens": max_new_tokens,
-                "return_full_text": False,
-                "temperature": temperature,
-                "top_p": top_p,
+        elif self.provider == "together":
+            self.api_key = os.getenv("TOGETHER_API_KEY")
+            if not self.api_key:
+                raise ValueError("TOGETHER_API_KEY is required when LLM_PROVIDER=together.")
+            # Good instruct model on Together
+            self.model = os.getenv("TOGETHER_MODEL", "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo")
+            self.base_url = os.getenv("TOGETHER_BASE_URL", "https://api.together.xyz/v1")
+            self.headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
             }
+
+        else:
+            raise ValueError("LLM_PROVIDER must be one of: openai, together")
+
+    def generate(self, prompt: str, max_tokens: int = 512, temperature: float = 0.6, top_p: float = 0.9) -> str:
+        """
+        Uses Chat Completions-style API to generate text.
+        """
+        url = f"{self.base_url}/chat/completions"
+        payload: Dict[str, Any] = {
+            "model": self.model,
+            "messages": [
+                {"role": "system", "content": "You are a helpful, precise assistant."},
+                {"role": "user", "content": prompt},
+            ],
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+            "top_p": top_p,
         }
 
         try:
-            print("🚀 Querying Hugging Face Inference API...")
-            response = requests.post(self.api_url, headers=self.headers, json=payload, timeout=16)
-            response.raise_for_status()  # Raise an error for bad status codes
-            
-            result = response.json()
-
-            # Handle error response from HF
-            if isinstance(result, dict) and "error" in result:
-                print(f"⚠️ HF API Error: {result['error']}")
-                return f"Error: {result['error']}"
-
-            # Normal expected case: list of dicts
-            if isinstance(result, list) and result:
-                answer = result[0].get("generated_text", "")
-            else:
-                answer = f"Error: Unexpected API response format: {result}"
-
-            print(f"🤖 Agent returning answer (preview): {answer.strip()[:80]}...")
-            return answer.strip()
-
+            resp = requests.post(url, headers=self.headers, json=payload, timeout=120)
+            if resp.status_code == 404:
+                return (
+                    f"Error: 404 from {self.provider} API. Check model name and base URL.\n"
+                    f"Requested URL: {url}\nModel: {self.model}"
+                )
+            resp.raise_for_status()
+            data = resp.json()
+            text = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+            return (text or "").strip()
         except requests.exceptions.RequestException as e:
-            print(f"❌ API request error: {e}")
-            return f"Error: Could not connect to the Inference API. Details: {e}"
+            return f"Error: Could not connect to {self.provider} API. Details: {e}"
         except Exception as e:
-            print(f"🔥 Unexpected error in agent: {e}")
             return f"Error: Unexpected failure while processing. Details: {e}"
 
 
-            
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+class BasicAgent:
+    """
+    Agent that delegates to a pluggable non-HF provider (OpenAI or Together).
+    """
+
+    def __init__(self):
+        self.client = LLMClient()
+        print(f"✅ BasicAgent initialized with provider: {self.client.provider}, model: {self.client.model}")
+
+    def __call__(self, question: str, max_new_tokens: int = 512, temperature: float = 0.6, top_p: float = 0.9) -> str:
+        print(f"📝 Agent received question (preview): {question[:80]}...")
+        answer = self.client.generate(
+            prompt=question,
+            max_tokens=max_new_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+        print(f"🤖 Agent returning answer (preview): {answer[:80]}...")
+        return answer
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays 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")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -101,13 +118,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -118,16 +135,16 @@ 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
@@ -147,14 +164,14 @@ 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.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. Prepare Submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
@@ -226,7 +243,6 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -236,9 +252,8 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     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")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -246,7 +261,7 @@ 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(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")
@@ -254,6 +269,5 @@ if __name__ == "__main__":
         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
-
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)