Update app.py

app.py

@@ -2,82 +2,75 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-import base64
 from dotenv import load_dotenv
-from groq import Groq
+from langchain_openai import ChatOpenAI
+from langchain_nvidia_ai_endpoints import ChatNVIDIA
+from langchain_groq import ChatGroq
+from langchain_google_genai import ChatGoogleGenerativeAI
 
 # Load environment variables
 load_dotenv()
 
-# --- Groq Multimodal Agent ---
-class GroqMultimodalAgent:
-    def __init__(self):
-        self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
-        self.llava_model = "llava-v1.5-7b-4096-preview"  # For image Q&A
-        self.llama_model = "meta-llama/llama-4-scout-17b-16e-instruct"            # For text Q&A
-        self.whisper_model = "whisper-large-v3"          # For audio transcription
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Basic Agent Definition ---
+class BasicAgent:
+    def __init__(self, provider="nvidia"):
+        self.provider = provider.lower()
+        if self.provider == "nvidia":
+            self.llm = ChatNVIDIA(
+                model="meta/llama-3.3-70b-instruct",
+                nvidia_api_key=os.getenv("NVIDIA_API_KEY")
+            )
+        elif self.provider == "groq":
+            self.llm = ChatGroq(
+                model="llama3-70b-8192",
+                api_key=os.getenv("GROQ_API_KEY")
+            )
+        elif self.provider == "google":
+            self.llm = ChatGoogleGenerativeAI(
+                model="gemini-2.0-flash",
+                temperature=0.1,
+                max_tokens=1024,
+                api_key=os.getenv("GOOGLE_API_KEY"),
+                streaming=False
+            )
+        elif self.provider == "openai":
+            self.llm = ChatOpenAI(
+                model="gpt-3.5-turbo",
+                api_key=os.getenv("OPENAI_API_KEY")
+            )
+        else:
+            raise ValueError("Unsupported provider. Choose from: nvidia, groq, google, openai.")
+
         self.instructions = (
-            "You are a helpful assistant. For every question or media, reply with only the answer—no explanation, "
+            "You are a helpful assistant. For every question, reply with only the answer—no explanation, "
             "no units, and no extra words. If the answer is a number, just return the number. "
             "If it is a word or phrase, return only that. If it is a list, return a comma-separated list with no extra words. "
             "Do not include any prefix, suffix, or explanation."
         )
+        print(f"BasicAgent initialized with provider: {self.provider}")
 
-    def _encode_image(self, image_path):
-        with open(image_path, "rb") as img_file:
-            return base64.b64encode(img_file.read()).decode("utf-8")
-
-    def _process_image(self, image_path, question):
-        base64_image = self._encode_image(image_path)
-        prompt = f"{self.instructions}\n\n{question}"
-        chat_completion = self.client.chat.completions.create(
-            model=self.llava_model,
-            messages=[
-                {"role": "user", "content": [
-                    {"type": "text", "text": prompt},
-                    {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}
-                ]}
-            ]
-        )
-        answer = chat_completion.choices[0].message.content.strip()
-        return self._extract_final_answer(answer)
-
-    def _process_audio(self, audio_path):
-        with open(audio_path, "rb") as audio_file:
-            transcript = self.client.audio.transcriptions.create(
-                model=self.whisper_model,
-                file=audio_file
-            )
-        return transcript.text.strip()
-
-    def _process_text(self, question):
+    def __call__(self, question: str) -> str:
         prompt = f"{self.instructions}\n\n{question}"
-        chat_completion = self.client.chat.completions.create(
-            model=self.llama_model,
-            messages=[{"role": "user", "content": prompt}]
-        )
-        answer = chat_completion.choices[0].message.content.strip()
-        return self._extract_final_answer(answer)
-
-    def _extract_final_answer(self, llm_output: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        response = self.llm.invoke(prompt)
+        answer = response.content.strip() if hasattr(response, "content") else str(response)
+        # Remove "FINAL ANSWER:" or similar prefixes if present
         for prefix in ["FINAL ANSWER:", "Final answer:", "final answer:"]:
-            if llm_output.lower().startswith(prefix.lower()):
-                return llm_output[len(prefix):].strip()
-        return llm_output
-
-    def __call__(self, question: str, image_path: str = None, audio_path: str = None) -> str:
-        if image_path:
-            return self._process_image(image_path, question)
-        elif audio_path:
-            return self._process_audio(audio_path)
-        else:
-            return self._process_text(question)
+            if answer.lower().startswith(prefix.lower()):
+                answer = answer[len(prefix):].strip()
+        print(f"Agent returning answer: {answer}")
+        return answer
+
+def run_and_submit_all(profile: gr.OAuthProfile | None, provider="nvidia"):
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    """
+    space_id = os.getenv("SPACE_ID")  # For codebase link
 
-# --- Gradio Leaderboard Submission App ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
     if profile:
         username = f"{profile.username}"
         print(f"User logged in: {username}")
@@ -89,8 +82,9 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
+    # 1. Instantiate Agent
     try:
-        agent = GroqMultimodalAgent()
+        agent = BasicAgent(provider=provider)
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -98,6 +92,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
+    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -118,19 +113,18 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
-        image_path = item.get("image_path", None)
-        audio_path = item.get("audio_path", None)
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text, image_path=image_path, audio_path=audio_path)
+            submitted_answer = agent(question_text)
             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:
@@ -141,10 +135,11 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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 
     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)
-
+    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -195,23 +190,30 @@ with gr.Blocks() as demo:
         **Instructions:**
         1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
         2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        3.  Select your preferred provider and click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
         ---
         **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 separate action or even to answer the questions in async.
+        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 separate action or even to answer the questions in async.
         """
     )
 
     gr.LoginButton()
 
+    provider_dropdown = gr.Dropdown(
+        choices=["nvidia", "groq", "google", "openai"],
+        value="nvidia",
+        label="Choose LLM Provider"
+    )
+
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
-        fn=run_and_submit_all,
+        fn=lambda profile, provider: run_and_submit_all(profile, provider),
+        inputs=[gr.OAuthProfile(), provider_dropdown],
         outputs=[status_output, results_table]
     )
 
@@ -237,3 +239,4 @@ if __name__ == "__main__":
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)
+