Update app.py

app.py

@@ -1,6 +1,5 @@
 import os
 import requests
-import json
 import pandas as pd
 import gradio as gr
 
@@ -9,76 +8,44 @@ from langchain.docstore.document import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.retrievers import BM25Retriever
 
-from smolagents import Tool, CodeAgent
-
+from smolagents import Tool, CodeAgent, InferenceClientModel
 from huggingface_hub.inference_api import InferenceApi
 
-# Load HF token from environment
+
+# Load your HF API token from environment
 hf_token = os.getenv("HUGGINGFACE_API_KEY")
-print("Token from env var:", hf_token)
-if hf_token:
-    os.environ["HUGGINGFACE_API_KEY"] = hf_token
-    print("Set HUGGINGFACE_API_KEY in env.")
-else:
-    print("No HUGGINGFACE_API_KEY found in env.")
+if not hf_token:
+    raise ValueError("HUGGINGFACE_API_KEY not set in environment variables")
+os.environ["HUGGINGFACE_API_KEY"] = hf_token
+
 
+# Define the HuggingFaceInferenceWrapper class correctly
 class HuggingFaceInferenceWrapper:
     def __init__(self, inference_api):
         self.inference_api = inference_api
 
     def generate(self, prompt: str, **kwargs) -> str:
-        response = self.inference_api(inputs=prompt, raw_response=True)
-
-        # Handle response based on type
-        if hasattr(response, "content"):
-            # requests.Response-like object
-            json_data = json.loads(response.content)
-        else:
-            # Sometimes response might be a string already
-            try:
-                json_data = json.loads(response)
-            except Exception:
-                # Fallback: return raw string response
-                return str(response)
-
-        # Extract generated_text from json
-        if isinstance(json_data, dict) and "generated_text" in json_data:
-            return json_data["generated_text"].strip()
-        elif (
-            isinstance(json_data, list)
-            and len(json_data) > 0
-            and "generated_text" in json_data[0]
-        ):
-            return json_data[0]["generated_text"].strip()
-        else:
-            # fallback: return entire json as string
-            return str(json_data)
+        # Call inference API - returns string directly
+        response = self.inference_api(inputs=prompt)
+        return response.strip()
+
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")  # For linking repo code
+    space_id = os.getenv("SPACE_ID")
 
-    if profile:
-        username = f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
+    if not profile:
         return "Please Login to Hugging Face with the button.", None
+    username = profile.username
 
-    api_url = "https://agents-course-unit4-scoring.hf.space"  # Change if needed
+    api_url = "https://agents-course-unit4-scoring.hf.space"
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
     try:
-        # Load knowledge base and filter for retriever
+        # Load dataset and filter for docs
         knowledge_base = datasets.load_dataset("m-ric/huggingface_doc", split="train")
-        knowledge_base = knowledge_base.filter(
-            lambda row: row["source"].startswith("huggingface/transformers")
-        )
-
-        source_docs = [
-            Document(page_content=doc["text"], metadata={"source": doc["source"].split("/")[1]})
-            for doc in knowledge_base
-        ]
+        knowledge_base = knowledge_base.filter(lambda row: row["source"].startswith("huggingface/transformers"))
+        source_docs = [Document(page_content=doc["text"], metadata={"source": doc["source"].split("/")[1]}) for doc in knowledge_base]
 
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=500,
@@ -92,16 +59,9 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         class RetrieverTool(Tool):
             name = "retriever"
             description = (
-                "Uses lexical search to retrieve relevant parts of transformers docs."
+                "Uses lexical search to retrieve relevant parts of transformers documentation."
             )
-            inputs = {
-                "query": {
-                    "type": "string",
-                    "description": (
-                        "The query to perform. Should be lexically close to your target documents."
-                    ),
-                }
-            }
+            inputs = {"query": {"type": "string", "description": "Search query"}}
             output_type = "string"
 
             def __init__(self, docs, **kwargs):
@@ -109,35 +69,32 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
                 self.retriever = BM25Retriever.from_documents(docs, k=10)
 
             def forward(self, query: str) -> str:
-                assert isinstance(query, str), "Your search query must be a string"
                 docs = self.retriever.invoke(query)
                 return "\nRetrieved documents:\n" + "".join(
-                    [f"\n\n===== Document {i} =====\n" + doc.page_content for i, doc in enumerate(docs)]
+                    [f"\n\n===== Document {i} =====\n{doc.page_content}" for i, doc in enumerate(docs)]
                 )
 
         retriever_tool = RetrieverTool(docs_processed)
 
-        # Instantiate HuggingFace Inference API wrapper
+        # Instantiate HuggingFace InferenceApi
         inference_api = InferenceApi(repo_id="Qwen/Qwen2.5-VL-7B-Instruct", token=hf_token)
-        model_wrapper = HuggingFaceInferenceWrapper(inference_api)
+        hf_wrapper = HuggingFaceInferenceWrapper(inference_api)
 
-        # Instantiate the agent with our wrapped model
+        # Use the wrapper with CodeAgent
         agent = CodeAgent(
             tools=[retriever_tool],
-            model=model_wrapper,
+            model=hf_wrapper,
             max_steps=4,
             verbosity_level=2,
-            stream_outputs=False,  # must be False for this wrapper
+            stream_outputs=False,  # MUST be False for this wrapper
         )
 
     except Exception as e:
         return f"Error initializing agent: {e}", None
 
-    agent_code = (
-        f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Code repo URL not available"
-    )
-    print(agent_code)
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Code repo URL not available"
 
+    # Fetch questions
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
@@ -147,6 +104,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
+    # Run agent on questions
     results_log = []
     answers_payload = []
 
@@ -165,9 +123,10 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     if not answers_payload:
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
+    # Prepare submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting {len(answers_payload)} answers...")
 
+    # Submit answers
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -182,31 +141,22 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except Exception as e:
-        status_message = f"Submission Failed: {e}"
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission failed: {e}", pd.DataFrame(results_log)
 
 
-# Gradio UI code unchanged from your original snippet
+# Gradio Interface
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **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.
-        ---
-        **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 asynchronously.
+        1. Log in to your Hugging Face account using the button below.
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, and submit answers.
         """
     )
 
     gr.LoginButton()
-
     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)
 
@@ -217,24 +167,4 @@ with gr.Blocks() as demo:
 
 
 if __name__ == "__main__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    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")
-    else:
-        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)