Update app.py

app.py

@@ -1,197 +1,5 @@
-import os
-import requests
-import pandas as pd
-import gradio as gr
+from huggingface_hub import InferenceApi
 
-import datasets
-from langchain.docstore.document import Document
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.retrievers import BM25Retriever
-
-from smolagents import Tool, CodeAgent, InferenceClientModel
-from huggingface_hub.inference_api import InferenceApi
-
-
-# Load your HF API token from environment
-hf_token = os.getenv("HUGGINGFACE_API_KEY")
-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
-import json
-
-class HuggingFaceInferenceWrapper:
-    def __init__(self, inference_api):
-        self.inference_api = inference_api
-
-    def generate(self, prompt: str, **kwargs) -> str:
-        # Call inference API with raw_response=True to get the raw Response object
-        response = self.inference_api(inputs=prompt, raw_response=True)
-
-        # Check if the response is a string
-        if isinstance(response, str):
-            return response.strip()
-
-        # Parse the JSON response if the response is not a string
-        if hasattr(response, 'json'):
-            json_response = response.json()
-            # Extract the relevant information from the JSON response
-            # This depends on the structure of the JSON response from the API
-            # For example, if the response contains a 'generated_text' field:
-            if isinstance(json_response, list) and len(json_response) > 0:
-                return json_response[0].get('generated_text', '').strip()
-            elif isinstance(json_response, dict):
-                return json_response.get('generated_text', '').strip()
-
-        # Fallback: return the raw response text if JSON parsing fails
-        if hasattr(response, 'text'):
-            return response.text.strip()
-
-        # If none of the above conditions are met, return an empty string or handle the error appropriately
-        return ""
-
-
-
-
-
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
-
-    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"
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
-    try:
-        # 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]
-
-        text_splitter = RecursiveCharacterTextSplitter(
-            chunk_size=500,
-            chunk_overlap=50,
-            add_start_index=True,
-            strip_whitespace=True,
-            separators=["\n\n", "\n", ".", " ", ""],
-        )
-        docs_processed = text_splitter.split_documents(source_docs)
-
-        class RetrieverTool(Tool):
-            name = "retriever"
-            description = (
-                "Uses lexical search to retrieve relevant parts of transformers documentation."
-            )
-            inputs = {"query": {"type": "string", "description": "Search query"}}
-            output_type = "string"
-
-            def __init__(self, docs, **kwargs):
-                super().__init__(**kwargs)
-                self.retriever = BM25Retriever.from_documents(docs, k=10)
-
-            def forward(self, query: str) -> str:
-                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)]
-                )
-
-        retriever_tool = RetrieverTool(docs_processed)
-
-        # Instantiate HuggingFace InferenceApi
-        inference_api = InferenceApi(repo_id="Qwen/Qwen2.5-VL-7B-Instruct", token=hf_token)
-        hf_wrapper = HuggingFaceInferenceWrapper(inference_api)
-
-        # Use the wrapper with CodeAgent
-        agent = CodeAgent(
-            tools=[retriever_tool],
-            model=hf_wrapper,
-            max_steps=4,
-            verbosity_level=2,
-            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"
-
-    # Fetch questions
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-        if not questions_data:
-            return "Fetched questions list is empty or invalid format.", None
-    except Exception as e:
-        return f"Error fetching questions: {e}", None
-
-    # Run agent on questions
-    results_log = []
-    answers_payload = []
-
-    for item in questions_data:
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or question_text is None:
-            continue
-        try:
-            submitted_answer = agent.run(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:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
-    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}
-
-    # Submit answers
-    try:
-        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.')}"
-        )
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except Exception as e:
-        return f"Submission failed: {e}", pd.DataFrame(results_log)
-
-
-# Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-        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)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
-
-
-if __name__ == "__main__":
-    demo.launch(debug=True, share=False)
+inference_api = InferenceApi(repo_id="Qwen/Qwen1.5-1.8B-Chat", token="hf_your_token")
+llm = HuggingFaceInferenceWrapper(inference_api)
+print(llm.generate("What is the capital of France?"))