Delete app-.py

app-.py

@@ -1,320 +0,0 @@
-import argparse
-import json
-import os
-import threading
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from datetime import datetime
-from pathlib import Path
-from typing import List, Optional
-
-import datasets
-import pandas as pd
-from dotenv import load_dotenv
-from huggingface_hub import login
-import gradio as gr
-
-from scripts.reformulator import prepare_response
-from scripts.run_agents import (
-    get_single_file_description,
-    get_zip_description,
-)
-from scripts.text_inspector_tool import TextInspectorTool
-from scripts.text_web_browser import (
-    ArchiveSearchTool,
-    FinderTool,
-    FindNextTool,
-    PageDownTool,
-    PageUpTool,
-    SearchInformationTool,
-    SimpleTextBrowser,
-    VisitTool,
-)
-from scripts.visual_qa import visualizer
-from tqdm import tqdm
-
-from smolagents import (
-    # MANAGED_AGENT_PROMPT,
-    CodeAgent,
-    HfApiModel,
-    LiteLLMModel,
-    Model,
-    ToolCallingAgent,
-)
-from smolagents.agent_types import AgentText, AgentImage, AgentAudio, handle_agent_output_types
-from smolagents.gradio_ui import pull_messages_from_step  # , handle_agent_output_types
-
-
-AUTHORIZED_IMPORTS = [
-    "requests",
-    "zipfile",
-    "os",
-    "pandas",
-    "numpy",
-    "sympy",
-    "json",
-    "bs4",
-    "pubchempy",
-    "xml",
-    "yahoo_finance",
-    "Bio",
-    "sklearn",
-    "scipy",
-    "pydub",
-    "io",
-    "PIL",
-    "chess",
-    "PyPDF2",
-    "pptx",
-    "torch",
-    "datetime",
-    "fractions",
-    "csv",
-]
-load_dotenv(override=True)
-login(os.getenv("HF_TOKEN"))
-
-append_answer_lock = threading.Lock()
-
-SET = "validation"
-
-custom_role_conversions = {"tool-call": "assistant", "tool-response": "user"}
-
-# skip
-_ = """
-### LOAD EVALUATION DATASET
-
-eval_ds = datasets.load_dataset("gaia-benchmark/GAIA", "2023_all")[SET]
-eval_ds = eval_ds.rename_columns({"Question": "question", "Final answer": "true_answer", "Level": "task"})
-
-
-def preprocess_file_paths(row):
-    if len(row["file_name"]) > 0:
-        row["file_name"] = f"data/gaia/{SET}/" + row["file_name"]
-    return row
-
-
-eval_ds = eval_ds.map(preprocess_file_paths)
-eval_df = pd.DataFrame(eval_ds)
-print("Loaded evaluation dataset:")
-print(eval_df["task"].value_counts())
-# """
-
-user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
-
-BROWSER_CONFIG = {
-    "viewport_size": 1024 * 5,
-    "downloads_folder": "downloads_folder",
-    "request_kwargs": {
-        "headers": {"User-Agent": user_agent},
-        "timeout": 300,
-    },
-    "serpapi_key": os.getenv("SERPAPI_API_KEY"),
-}
-
-os.makedirs(f"./{BROWSER_CONFIG['downloads_folder']}", exist_ok=True)
-
-model = LiteLLMModel(
-    # "gpt-4o",
-    # os.getenv("MODEL_ID", "gpt-4o-mini"),
-    os.getenv("MODEL_ID", "deepseek-ai/DeepSeek-V3"),
-    custom_role_conversions=custom_role_conversions,
-    api_base=os.getenv("OPENAI_API_BASE"),
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
-
-text_limit = 20000
-ti_tool = TextInspectorTool(model, text_limit)
-
-browser = SimpleTextBrowser(**BROWSER_CONFIG)
-
-WEB_TOOLS = [
-    SearchInformationTool(browser),
-    VisitTool(browser),
-    PageUpTool(browser),
-    PageDownTool(browser),
-    FinderTool(browser),
-    FindNextTool(browser),
-    ArchiveSearchTool(browser),
-    TextInspectorTool(model, text_limit),
-]
-
-agent = CodeAgent(
-    model=model,
-    tools=[visualizer] + WEB_TOOLS,
-    max_steps=5,
-    verbosity_level=2,
-    additional_authorized_imports=AUTHORIZED_IMPORTS,
-    planning_interval=4,
-)
-
-document_inspection_tool = TextInspectorTool(model, 20000)
-
-
-# augmented_question = """You have one question to answer. It is paramount that you provide a correct answer.
-# Give it all you can: I know for a fact that you have access to all the relevant tools to solve it and find the correct answer (the answer does exist). Failure or 'I cannot answer' or 'None found' will not be tolerated, success will be rewarded.
-# Run verification steps if that's needed, you must make sure you find the correct answer!
-# Here is the task:
-# """ + example["question"]
-
-# if example["file_name"]:
-#     prompt_use_files = "\n\nTo solve the task above, you will have to use this attached file:"
-#     prompt_use_files += get_single_file_description(
-#         example["file_name"], example["question"], visual_inspection_tool, document_inspection_tool
-#     )
-#     augmented_question += prompt_use_files
-
-
-# final_result = agent.run(augmented_question)
-
-
-def stream_to_gradio(
-    agent,
-    task: str,
-    reset_agent_memory: bool = False,
-    additional_args: Optional[dict] = None,
-):
-    """Runs an agent with the given task and streams the messages from the agent as gradio ChatMessages."""
-    for step_log in agent.run(task, stream=True, reset=reset_agent_memory, additional_args=additional_args):
-        for message in pull_messages_from_step(
-            step_log,
-        ):
-            yield message
-
-    final_answer = step_log  # Last log is the run's final_answer
-    final_answer = handle_agent_output_types(final_answer)
-
-    if isinstance(final_answer, AgentText):
-        yield gr.ChatMessage(
-            role="assistant",
-            content=f"**Final answer:**\n{final_answer.to_string()}\n",
-        )
-    elif isinstance(final_answer, AgentImage):
-        yield gr.ChatMessage(
-            role="assistant",
-            content={"path": final_answer.to_string(), "mime_type": "image/png"},
-        )
-    elif isinstance(final_answer, AgentAudio):
-        yield gr.ChatMessage(
-            role="assistant",
-            content={"path": final_answer.to_string(), "mime_type": "audio/wav"},
-        )
-    else:
-        yield gr.ChatMessage(role="assistant", content=f"**Final answer:** {str(final_answer)}")
-
-
-class GradioUI:
-    """A one-line interface to launch your agent in Gradio"""
-
-    def __init__(self, agent, file_upload_folder: str | None = None):
-        self.agent = agent
-        self.file_upload_folder = file_upload_folder
-        if self.file_upload_folder is not None:
-            if not os.path.exists(file_upload_folder):
-                os.mkdir(file_upload_folder)
-
-    def interact_with_agent(self, prompt, messages):
-        messages.append(gr.ChatMessage(role="user", content=prompt))
-        yield messages
-        for msg in stream_to_gradio(self.agent, task=prompt, reset_agent_memory=False):
-            messages.append(msg)
-            yield messages
-        yield messages
-
-    def upload_file(
-        self,
-        file,
-        file_uploads_log,
-        allowed_file_types=[
-            "application/pdf",
-            "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-            "text/plain",
-        ],
-    ):
-        """
-        Handle file uploads, default allowed types are .pdf, .docx, and .txt
-        """
-        if file is None:
-            return gr.Textbox("No file uploaded", visible=True), file_uploads_log
-
-        try:
-            mime_type, _ = mimetypes.guess_type(file.name)
-        except Exception as e:
-            return gr.Textbox(f"Error: {e}", visible=True), file_uploads_log
-
-        if mime_type not in allowed_file_types:
-            return gr.Textbox("File type disallowed", visible=True), file_uploads_log
-
-        # Sanitize file name
-        original_name = os.path.basename(file.name)
-        sanitized_name = re.sub(
-            r"[^\w\-.]", "_", original_name
-        )  # Replace any non-alphanumeric, non-dash, or non-dot characters with underscores
-
-        type_to_ext = {}
-        for ext, t in mimetypes.types_map.items():
-            if t not in type_to_ext:
-                type_to_ext[t] = ext
-
-        # Ensure the extension correlates to the mime type
-        sanitized_name = sanitized_name.split(".")[:-1]
-        sanitized_name.append("" + type_to_ext[mime_type])
-        sanitized_name = "".join(sanitized_name)
-
-        # Save the uploaded file to the specified folder
-        file_path = os.path.join(self.file_upload_folder, os.path.basename(sanitized_name))
-        shutil.copy(file.name, file_path)
-
-        return gr.Textbox(f"File uploaded: {file_path}", visible=True), file_uploads_log + [file_path]
-
-    def log_user_message(self, text_input, file_uploads_log):
-        return (
-            text_input
-            + (
-                f"\nYou have been provided with these files, which might be helpful or not: {file_uploads_log}"
-                if len(file_uploads_log) > 0
-                else ""
-            ),
-            "",
-        )
-
-    def launch(self, **kwargs):
-        with gr.Blocks(theme="ocean", fill_height=True) as demo:
-            gr.Markdown("""# open Deep Research - free the AI agents!
-
-OpenAI just published [Deep Research](https://openai.com/index/introducing-deep-research/), a very nice assistant that can perform deep searches on the web to answer user questions.
-
-However, their agent has a huge downside: it's not open. So we've started a 24-hour rush to replicate and open-source it. Our resulting [open-Deep-Research agent](https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research) took the #1 rank of any open submission on the GAIA leaderboard! ✨
-
-You can try a simplified version below. 👇""")
-            stored_messages = gr.State([])
-            file_uploads_log = gr.State([])
-            chatbot = gr.Chatbot(
-                label="Open-Deep-Research",
-                type="messages",
-                avatar_images=(
-                    None,
-                    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/mascot_smol.png",
-                ),
-                # resizable=True,  # new version
-                resizeable=True,
-                scale=1,
-            )
-            # If an upload folder is provided, enable the upload feature
-            if self.file_upload_folder is not None:
-                upload_file = gr.File(label="Upload a file")
-                upload_status = gr.Textbox(label="Upload Status", interactive=False, visible=False)
-                upload_file.change(
-                    self.upload_file,
-                    [upload_file, file_uploads_log],
-                    [upload_status, file_uploads_log],
-                )
-            text_input = gr.Textbox(lines=1, label="Your request")
-            text_input.submit(
-                self.log_user_message,
-                [text_input, file_uploads_log],
-                [stored_messages, text_input],
-            ).then(self.interact_with_agent, [stored_messages, chatbot], [chatbot])
-
-        demo.launch(debug=True, share=True, **kwargs)
-
-GradioUI(agent).launch()