Modify Gradio UI

app.py

@@ -1,53 +1,85 @@
-import re
-import requests
-import gradio as gr
+# import re
+# import requests
+# import gradio as gr
+
+# from markdownify import markdownify
+# from requests.exceptions import RequestException
+
+# from utils.preprocessor import Preprocessor
+
+# # https://modal.com/docs/guide/webhook-urls
+# MODAL_ENDPOINT = "https://auto-readme-agent--text-to-speech-gradio-app.modal.run"
+
+# def visit_webpage(url, max_output_length=40000):
+#     """
+#     Fetch the webpage, convert to markdown, and use Preprocessor methods.
+#     """
+#     try:
+#         response = requests.get(url, timeout=20)
+#         response.raise_for_status()
+#         markdown_content = markdownify(response.text).strip()
+#         markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
+#         # if len(markdown_content) > max_output_length:
+#         #     markdown_content = (
+#         #         markdown_content[: max_output_length // 2]
+#         #         + f"\n..._This content has been truncated to stay below {max_output_length} characters_...\n"
+#         #         + markdown_content[-max_output_length // 2 :]
+#         #     )
+#         # Use Preprocessor class methods
+#         section = Preprocessor.extract_section(markdown_content)
+#         dir_paths, files = Preprocessor.extract_dirs_from_text(section)
+#         # Format the result
+#         result = (
+#             f"paths: {dir_paths}\n\n"
+#             f"files: {files}"
+#         )
+#         return result
+#     except requests.exceptions.Timeout:
+#         return "The request timed out. Please try again later or check the URL."
+#     except RequestException as e:
+#         return f"Error fetching the webpage: {str(e)}"
+#     except Exception as e:
+#         return f"An unexpected error occurred: {str(e)}"
 
-from markdownify import markdownify
-from requests.exceptions import RequestException
+# demo = gr.Interface(
+#     fn=visit_webpage,
+#     inputs=[
+#         gr.Textbox(label="Website URL"),
+#         gr.Textbox(label="Files or folders you want to highlight in the README (comma or newline separated)")
+#     ],
+#     outputs=gr.Textbox(label="Extracted Section, Directory Paths, and File Paths", show_copy_button=True),
+#     title="Webpage Section and Path Extractor",
+#     description="Enter a website URL. This tool fetches the page, extracts a markdown section, and lists directory paths and files found in that section. You can also specify files or folders you want to highlight in the generated README."
+# )
 
-from utils.preprocessor import Preprocessor
+# if __name__ == "__main__":
+#     demo.launch(debug=True)
 
-def visit_webpage(url, max_output_length=40000):
-    """
-    Fetch the webpage, convert to markdown, and use Preprocessor methods.
-    """
+import gradio as gr
+import requests
+
+MODAL_API_URL = "https://agents-mcp-hackathon--smolagents-modal-agent-readme-agen-eb6ccb.modal.run"  # Replace with your deployed Modal endpoint
+
+def generate_readme_from_github(repo_url):
     try:
-        response = requests.get(url, timeout=20)
-        response.raise_for_status()
-        markdown_content = markdownify(response.text).strip()
-        markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
-        if len(markdown_content) > max_output_length:
-            markdown_content = (
-                markdown_content[: max_output_length // 2]
-                + f"\n..._This content has been truncated to stay below {max_output_length} characters_...\n"
-                + markdown_content[-max_output_length // 2 :]
-            )
-        # Use Preprocessor class methods
-        section = Preprocessor.extract_section(markdown_content)
-        dir_paths, files = Preprocessor.extract_dirs_from_text(section)
-        # Format the result
-        result = (
-            f"paths: {dir_paths}\n\n"
-            f"files: {files}"
+        response = requests.post(
+            MODAL_API_URL,
+            json={"repo_url": repo_url},
+            timeout=600,
         )
-        return result
-    except requests.exceptions.Timeout:
-        return "The request timed out. Please try again later or check the URL."
-    except RequestException as e:
-        return f"Error fetching the webpage: {str(e)}"
+        if response.status_code == 200:
+            return response.json().get("readme", "No README generated.")
+        else:
+            return f"Error: {response.status_code}\n{response.text}"
     except Exception as e:
-        return f"An unexpected error occurred: {str(e)}"
-
-demo = gr.Interface(
-    fn=visit_webpage,
-    inputs=[
-        gr.Textbox(label="Website URL"),
-        gr.Textbox(label="Files or folders you want to highlight in the README (comma or newline separated)")
-    ],
-    outputs=gr.Textbox(label="Extracted Section, Directory Paths, and File Paths", show_copy_button=True),
-    title="Webpage Section and Path Extractor",
-    description="Enter a website URL. This tool fetches the page, extracts a markdown section, and lists directory paths and files found in that section. You can also specify files or folders you want to highlight in the generated README."
-)
+        return f"Exception: {str(e)}"
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 📝 GitHub Repo → README.md Generator\nPaste a public GitHub repo link to generate a draft README.md using AI.")
+    repo_input = gr.Textbox(label="GitHub Repository URL", placeholder="https://github.com/owner/repo")
+    output = gr.Textbox(label="Generated README.md", lines=20)
+    btn = gr.Button("Generate README")
+    btn.click(generate_readme_from_github, inputs=repo_input, outputs=output)
 
 if __name__ == "__main__":
     demo.launch()

modal/config.py

@@ -0,0 +1,20 @@
+MODEL_DIR = "/model"
+BASE_MODEL="mistralai/Mistral-7B-Instruct-v0.1"
+
+
+# Name the stub (it should all be in lower case)
+STUB_NAME=f"{BASE_MODEL.lower()}-deployement"
+
+### Server level default configs
+# Keep warm: is the warm pool size or the minimum number of containers that will always be up for your serverless function to get executed (Modal will scale up more containers from there based on need or demand)
+
+KEEP_WARM = 1
+
+# num of concurrent requests: is the number of concurrent requests a container should handle 
+NUM_CONCURRENT_REQUESTS = 10
+
+# timeout: This is the server timeout after which it would be shutdown the server. 
+TIMEOUT = 600
+
+# Number of GPUs to use
+GPU_COUNT = 1

modal/engine.py

@@ -0,0 +1,103 @@
+import os 
+import asyncio
+
+from queue import Empty
+from typing import List, Union, List
+
+# Import modal's required imports
+from modal import Image, Stub, gpu, method, enter, exit
+
+# Import the constants defined in constants.py
+from config import (
+    MODEL_DIR, 
+    BASE_MODEL,
+    STUB_NAME,
+    NUM_CONCURRENT_REQUESTS,
+    TIMEOUT,
+    GPU_COUNT
+)
+
+# Define our GPU Config 
+
+if BASE_MODEL == "mistralai/Mistral-7B-Instruct-v0.1":
+    GPU_CONFIG = gpu.A100(count=GPU_COUNT, memory=80)
+else:
+    GPU_CONFIG = gpu.Any(count=GPU_COUNT)
+    
+stub = Stub(name=STUB_NAME)
+
+def download_model_to_folder():
+    from transformers.utils import move_cache
+    from huggingface_hub import snapshot_download
+
+    os.makedirs(MODEL_DIR, exist_ok=True)
+
+    snapshot_download(
+        BASE_MODEL,
+        local_dir=MODEL_DIR,
+        ignore_patterns=["*.pt"],  # Using safetensors
+    )
+    
+    move_cache()
+    
+HF_DOCKER_IMAGE = (
+    Image.from_registry("nvidia/cuda:12.1.0-base-ubuntu22.04", add_python="3.10").pip_install_from_requirements("./requirements.txt")
+    .env({"HF_HUB_ENABLE_HF_TRANSFER": "1"})
+    .run_function(download_model_to_folder)
+)
+
+@stub.cls(
+    gpu=GPU_CONFIG,
+    timeout=TIMEOUT,
+    container_idle_timeout=TIMEOUT,
+    allow_concurrent_inputs=NUM_CONCURRENT_REQUESTS,
+    image=HF_DOCKER_IMAGE,
+)
+class HFEngine:
+    model_name_or_path: str = MODEL_DIR
+    device: str = "cuda"
+
+    @enter()
+    def start_engine(self):
+        from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer 
+        
+        self.model = AutoModelForCausalLM.from_pretrained(self.model_name_or_path, trust_remote_code=True).to(self.device)
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name_or_path, trust_remote_code=True)
+        self.streamer = TextIteratorStreamer(self.tokenizer)
+        return self
+    
+    @exit()
+    def terminate_engine(self):
+        import gc 
+        import torch
+
+        del self.model
+        torch.cuda.synchronize()
+        gc.collect()
+    
+    @method()
+    async def stream(self, chat_input: Union[str, List[dict]], generation_kwargs: dict):
+        from threading import Thread
+
+        if isinstance(chat_input, str):
+            chat_input = [{"role": "user", "content": chat_input}]
+        input_ids = self.tokenizer.apply_chat_template(
+            conversation=chat_input, tokenize=True, return_tensors="pt"
+        ).to(self.device)
+
+        gen_kwargs = dict(
+            input_ids=input_ids,
+            streamer=self.streamer,
+            pad_token_id=self.tokenizer.eos_token_id,
+            **generation_kwargs
+        )
+
+        thread = Thread(target=self.model.generate, kwargs=gen_kwargs)
+        thread.start()
+
+        for next_token in self.streamer:
+            try:
+                if next_token is not None:
+                    yield next_token
+            except Empty:
+                await asyncio.sleep(0.001)

modal/server.py

@@ -0,0 +1,103 @@
+import modal
+
+image = (
+    modal.Image.debian_slim(python_version="3.12")
+    .pip_install(
+        "smolagents[toolkit]",
+        "huggingface_hub",
+        "transformers",
+        "duckduckgo-search",
+        "fastapi",
+        "uvicorn",
+        "PyGithub",
+        "gitpython"
+    )
+)
+
+app = modal.App("smolagents-modal-agent-readme")
+
+HF_SECRET_NAME = "hf-secret"
+MODEL_ID = "mistralai/Mistral-7B-Instruct-v0.2"
+
+@app.function(
+    image=image,
+    gpu="A10G",
+    secrets=[modal.Secret.from_name(HF_SECRET_NAME)],
+    timeout=600,
+)
+@modal.fastapi_endpoint()
+def agent_server():
+    import os
+    from fastapi import FastAPI, HTTPException, Request
+    import uvicorn
+    from huggingface_hub import login as hf_login
+    from smolagents import CodeAgent, WebSearchTool, InferenceClientModel
+    import tempfile
+    import shutil
+    import subprocess
+
+    hf_token = os.environ.get("HF_TOKEN")
+    hf_login(token=hf_token)
+
+    model = InferenceClientModel(
+        model_id=MODEL_ID,
+        provider="huggingface",
+        token=hf_token,
+    )
+
+    agent = CodeAgent(
+        tools=[WebSearchTool()],
+        model=model,
+        stream_outputs=True,
+    )
+
+    app = FastAPI()
+
+    @app.post("/generate_readme")
+    async def generate_readme(request: Request):
+        try:
+            data = await request.json()
+            repo_url = data.get("repo_url")
+            if not repo_url:
+                raise HTTPException(status_code=400, detail="Missing 'repo_url' in request body")
+
+            temp_dir = tempfile.mkdtemp()
+            try:
+                subprocess.run(
+                    ["git", "clone", "--depth", "1", "--branch", "main", repo_url, temp_dir],
+                    check=True
+                )
+
+                repo_summary = []
+                for root, dirs, files in os.walk(temp_dir):
+                    depth = root[len(temp_dir):].count(os.sep)
+                    if depth > 2:
+                        continue
+                    rel_root = os.path.relpath(root, temp_dir)
+                    repo_summary.append(f"Directory: {rel_root}")
+                    for file in files:
+                        if file.endswith((".py", ".md", ".txt", ".json", ".yaml", ".yml")):
+                            file_path = os.path.join(root, file)
+                            try:
+                                with open(file_path, "r", encoding="utf-8") as f:
+                                    content = f.read(500)
+                            except Exception:
+                                content = "[Could not read file content]"
+                            repo_summary.append(f"File: {file} Content Preview: {content}")
+
+                prompt = (
+                    "You are an AI assistant that drafts a detailed README.md for a GitHub repository. "
+                    "Based on the following repository structure and code snippets, create a comprehensive README.md content. "
+                    "Repository summary:\n" + "\n".join(repo_summary)
+                )
+
+                readme_text = agent.run(prompt)
+                return {"readme": readme_text}
+            finally:
+                shutil.rmtree(temp_dir)
+
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=str(e))
+
+    # Start Uvicorn in blocking mode
+    uvicorn.run(app, host="0.0.0.0", port=8000)

modal_app.py

@@ -1,12 +0,0 @@
-import modal
-
-app = modal.App("auto-readme-agent")
-
-@app.function()
-def square(x):
-    print("This code is running on a remote worker!")
-    return x**2
-
-@app.local_entrypoint()
-def main():
-    print("the square is", square.remote(42))

pyproject.toml

@@ -9,4 +9,5 @@ dependencies = [
     "markdownify>=1.1.0",
     "modal>=1.0.3",
     "smolagents>=1.17.0",
+    "transformers>=4.52.4",
 ]

requirements.txt

@@ -1 +1,12 @@
-markdownify
+markdownify
+smolagents[toolkit]
+huggingface_hub
+transformers
+duckduckgo-search
+fastapi
+uvicorn
+PyGithub
+gitpython
+modal
+gradio
+requests

uv.lock

@@ -15,6 +15,7 @@ dependencies = [
     { name = "markdownify" },
     { name = "modal" },
     { name = "smolagents" },
+    { name = "transformers" },
 ]
 
 [package.metadata]
@@ -23,6 +24,7 @@ requires-dist = [
     { name = "markdownify", specifier = ">=1.1.0" },
     { name = "modal", specifier = ">=1.0.3" },
     { name = "smolagents", specifier = ">=1.17.0" },
+    { name = "transformers", specifier = ">=4.52.4" },
 ]
 
 [[package]]
@@ -1265,6 +1267,59 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fa/de/02b54f42487e3d3c6efb3f89428677074ca7bf43aae402517bc7cca949f3/PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563", size = 156446 },
 ]
 
+[[package]]
+name = "regex"
+version = "2024.11.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/8e/5f/bd69653fbfb76cf8604468d3b4ec4c403197144c7bfe0e6a5fc9e02a07cb/regex-2024.11.6.tar.gz", hash = "sha256:7ab159b063c52a0333c884e4679f8d7a85112ee3078fe3d9004b2dd875585519", size = 399494 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/58/7e4d9493a66c88a7da6d205768119f51af0f684fe7be7bac8328e217a52c/regex-2024.11.6-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:5478c6962ad548b54a591778e93cd7c456a7a29f8eca9c49e4f9a806dcc5d638", size = 482669 },
+    { url = "https://files.pythonhosted.org/packages/34/4c/8f8e631fcdc2ff978609eaeef1d6994bf2f028b59d9ac67640ed051f1218/regex-2024.11.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2c89a8cc122b25ce6945f0423dc1352cb9593c68abd19223eebbd4e56612c5b7", size = 287684 },
+    { url = "https://files.pythonhosted.org/packages/c5/1b/f0e4d13e6adf866ce9b069e191f303a30ab1277e037037a365c3aad5cc9c/regex-2024.11.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:94d87b689cdd831934fa3ce16cc15cd65748e6d689f5d2b8f4f4df2065c9fa20", size = 284589 },
+    { url = "https://files.pythonhosted.org/packages/25/4d/ab21047f446693887f25510887e6820b93f791992994f6498b0318904d4a/regex-2024.11.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1062b39a0a2b75a9c694f7a08e7183a80c63c0d62b301418ffd9c35f55aaa114", size = 792121 },
+    { url = "https://files.pythonhosted.org/packages/45/ee/c867e15cd894985cb32b731d89576c41a4642a57850c162490ea34b78c3b/regex-2024.11.6-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:167ed4852351d8a750da48712c3930b031f6efdaa0f22fa1933716bfcd6bf4a3", size = 831275 },
+    { url = "https://files.pythonhosted.org/packages/b3/12/b0f480726cf1c60f6536fa5e1c95275a77624f3ac8fdccf79e6727499e28/regex-2024.11.6-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2d548dafee61f06ebdb584080621f3e0c23fff312f0de1afc776e2a2ba99a74f", size = 818257 },
+    { url = "https://files.pythonhosted.org/packages/bf/ce/0d0e61429f603bac433910d99ef1a02ce45a8967ffbe3cbee48599e62d88/regex-2024.11.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a19f302cd1ce5dd01a9099aaa19cae6173306d1302a43b627f62e21cf18ac0", size = 792727 },
+    { url = "https://files.pythonhosted.org/packages/e4/c1/243c83c53d4a419c1556f43777ccb552bccdf79d08fda3980e4e77dd9137/regex-2024.11.6-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bec9931dfb61ddd8ef2ebc05646293812cb6b16b60cf7c9511a832b6f1854b55", size = 780667 },
+    { url = "https://files.pythonhosted.org/packages/c5/f4/75eb0dd4ce4b37f04928987f1d22547ddaf6c4bae697623c1b05da67a8aa/regex-2024.11.6-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9714398225f299aa85267fd222f7142fcb5c769e73d7733344efc46f2ef5cf89", size = 776963 },
+    { url = "https://files.pythonhosted.org/packages/16/5d/95c568574e630e141a69ff8a254c2f188b4398e813c40d49228c9bbd9875/regex-2024.11.6-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:202eb32e89f60fc147a41e55cb086db2a3f8cb82f9a9a88440dcfc5d37faae8d", size = 784700 },
+    { url = "https://files.pythonhosted.org/packages/8e/b5/f8495c7917f15cc6fee1e7f395e324ec3e00ab3c665a7dc9d27562fd5290/regex-2024.11.6-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:4181b814e56078e9b00427ca358ec44333765f5ca1b45597ec7446d3a1ef6e34", size = 848592 },
+    { url = "https://files.pythonhosted.org/packages/1c/80/6dd7118e8cb212c3c60b191b932dc57db93fb2e36fb9e0e92f72a5909af9/regex-2024.11.6-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:068376da5a7e4da51968ce4c122a7cd31afaaec4fccc7856c92f63876e57b51d", size = 852929 },
+    { url = "https://files.pythonhosted.org/packages/11/9b/5a05d2040297d2d254baf95eeeb6df83554e5e1df03bc1a6687fc4ba1f66/regex-2024.11.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ac10f2c4184420d881a3475fb2c6f4d95d53a8d50209a2500723d831036f7c45", size = 781213 },
+    { url = "https://files.pythonhosted.org/packages/26/b7/b14e2440156ab39e0177506c08c18accaf2b8932e39fb092074de733d868/regex-2024.11.6-cp311-cp311-win32.whl", hash = "sha256:c36f9b6f5f8649bb251a5f3f66564438977b7ef8386a52460ae77e6070d309d9", size = 261734 },
+    { url = "https://files.pythonhosted.org/packages/80/32/763a6cc01d21fb3819227a1cc3f60fd251c13c37c27a73b8ff4315433a8e/regex-2024.11.6-cp311-cp311-win_amd64.whl", hash = "sha256:02e28184be537f0e75c1f9b2f8847dc51e08e6e171c6bde130b2687e0c33cf60", size = 274052 },
+    { url = "https://files.pythonhosted.org/packages/ba/30/9a87ce8336b172cc232a0db89a3af97929d06c11ceaa19d97d84fa90a8f8/regex-2024.11.6-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:52fb28f528778f184f870b7cf8f225f5eef0a8f6e3778529bdd40c7b3920796a", size = 483781 },
+    { url = "https://files.pythonhosted.org/packages/01/e8/00008ad4ff4be8b1844786ba6636035f7ef926db5686e4c0f98093612add/regex-2024.11.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fdd6028445d2460f33136c55eeb1f601ab06d74cb3347132e1c24250187500d9", size = 288455 },
+    { url = "https://files.pythonhosted.org/packages/60/85/cebcc0aff603ea0a201667b203f13ba75d9fc8668fab917ac5b2de3967bc/regex-2024.11.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:805e6b60c54bf766b251e94526ebad60b7de0c70f70a4e6210ee2891acb70bf2", size = 284759 },
+    { url = "https://files.pythonhosted.org/packages/94/2b/701a4b0585cb05472a4da28ee28fdfe155f3638f5e1ec92306d924e5faf0/regex-2024.11.6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b85c2530be953a890eaffde05485238f07029600e8f098cdf1848d414a8b45e4", size = 794976 },
+    { url = "https://files.pythonhosted.org/packages/4b/bf/fa87e563bf5fee75db8915f7352e1887b1249126a1be4813837f5dbec965/regex-2024.11.6-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bb26437975da7dc36b7efad18aa9dd4ea569d2357ae6b783bf1118dabd9ea577", size = 833077 },
+    { url = "https://files.pythonhosted.org/packages/a1/56/7295e6bad94b047f4d0834e4779491b81216583c00c288252ef625c01d23/regex-2024.11.6-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:abfa5080c374a76a251ba60683242bc17eeb2c9818d0d30117b4486be10c59d3", size = 823160 },
+    { url = "https://files.pythonhosted.org/packages/fb/13/e3b075031a738c9598c51cfbc4c7879e26729c53aa9cca59211c44235314/regex-2024.11.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b7fa6606c2881c1db9479b0eaa11ed5dfa11c8d60a474ff0e095099f39d98e", size = 796896 },
+    { url = "https://files.pythonhosted.org/packages/24/56/0b3f1b66d592be6efec23a795b37732682520b47c53da5a32c33ed7d84e3/regex-2024.11.6-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0c32f75920cf99fe6b6c539c399a4a128452eaf1af27f39bce8909c9a3fd8cbe", size = 783997 },
+    { url = "https://files.pythonhosted.org/packages/f9/a1/eb378dada8b91c0e4c5f08ffb56f25fcae47bf52ad18f9b2f33b83e6d498/regex-2024.11.6-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:982e6d21414e78e1f51cf595d7f321dcd14de1f2881c5dc6a6e23bbbbd68435e", size = 781725 },
+    { url = "https://files.pythonhosted.org/packages/83/f2/033e7dec0cfd6dda93390089864732a3409246ffe8b042e9554afa9bff4e/regex-2024.11.6-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a7c2155f790e2fb448faed6dd241386719802296ec588a8b9051c1f5c481bc29", size = 789481 },
+    { url = "https://files.pythonhosted.org/packages/83/23/15d4552ea28990a74e7696780c438aadd73a20318c47e527b47a4a5a596d/regex-2024.11.6-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:149f5008d286636e48cd0b1dd65018548944e495b0265b45e1bffecce1ef7f39", size = 852896 },
+    { url = "https://files.pythonhosted.org/packages/e3/39/ed4416bc90deedbfdada2568b2cb0bc1fdb98efe11f5378d9892b2a88f8f/regex-2024.11.6-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:e5364a4502efca094731680e80009632ad6624084aff9a23ce8c8c6820de3e51", size = 860138 },
+    { url = "https://files.pythonhosted.org/packages/93/2d/dd56bb76bd8e95bbce684326302f287455b56242a4f9c61f1bc76e28360e/regex-2024.11.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:0a86e7eeca091c09e021db8eb72d54751e527fa47b8d5787caf96d9831bd02ad", size = 787692 },
+    { url = "https://files.pythonhosted.org/packages/0b/55/31877a249ab7a5156758246b9c59539abbeba22461b7d8adc9e8475ff73e/regex-2024.11.6-cp312-cp312-win32.whl", hash = "sha256:32f9a4c643baad4efa81d549c2aadefaeba12249b2adc5af541759237eee1c54", size = 262135 },
+    { url = "https://files.pythonhosted.org/packages/38/ec/ad2d7de49a600cdb8dd78434a1aeffe28b9d6fc42eb36afab4a27ad23384/regex-2024.11.6-cp312-cp312-win_amd64.whl", hash = "sha256:a93c194e2df18f7d264092dc8539b8ffb86b45b899ab976aa15d48214138e81b", size = 273567 },
+    { url = "https://files.pythonhosted.org/packages/90/73/bcb0e36614601016552fa9344544a3a2ae1809dc1401b100eab02e772e1f/regex-2024.11.6-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:a6ba92c0bcdf96cbf43a12c717eae4bc98325ca3730f6b130ffa2e3c3c723d84", size = 483525 },
+    { url = "https://files.pythonhosted.org/packages/0f/3f/f1a082a46b31e25291d830b369b6b0c5576a6f7fb89d3053a354c24b8a83/regex-2024.11.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:525eab0b789891ac3be914d36893bdf972d483fe66551f79d3e27146191a37d4", size = 288324 },
+    { url = "https://files.pythonhosted.org/packages/09/c9/4e68181a4a652fb3ef5099e077faf4fd2a694ea6e0f806a7737aff9e758a/regex-2024.11.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:086a27a0b4ca227941700e0b31425e7a28ef1ae8e5e05a33826e17e47fbfdba0", size = 284617 },
+    { url = "https://files.pythonhosted.org/packages/fc/fd/37868b75eaf63843165f1d2122ca6cb94bfc0271e4428cf58c0616786dce/regex-2024.11.6-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bde01f35767c4a7899b7eb6e823b125a64de314a8ee9791367c9a34d56af18d0", size = 795023 },
+    { url = "https://files.pythonhosted.org/packages/c4/7c/d4cd9c528502a3dedb5c13c146e7a7a539a3853dc20209c8e75d9ba9d1b2/regex-2024.11.6-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b583904576650166b3d920d2bcce13971f6f9e9a396c673187f49811b2769dc7", size = 833072 },
+    { url = "https://files.pythonhosted.org/packages/4f/db/46f563a08f969159c5a0f0e722260568425363bea43bb7ae370becb66a67/regex-2024.11.6-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1c4de13f06a0d54fa0d5ab1b7138bfa0d883220965a29616e3ea61b35d5f5fc7", size = 823130 },
+    { url = "https://files.pythonhosted.org/packages/db/60/1eeca2074f5b87df394fccaa432ae3fc06c9c9bfa97c5051aed70e6e00c2/regex-2024.11.6-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3cde6e9f2580eb1665965ce9bf17ff4952f34f5b126beb509fee8f4e994f143c", size = 796857 },
+    { url = "https://files.pythonhosted.org/packages/10/db/ac718a08fcee981554d2f7bb8402f1faa7e868c1345c16ab1ebec54b0d7b/regex-2024.11.6-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0d7f453dca13f40a02b79636a339c5b62b670141e63efd511d3f8f73fba162b3", size = 784006 },
+    { url = "https://files.pythonhosted.org/packages/c2/41/7da3fe70216cea93144bf12da2b87367590bcf07db97604edeea55dac9ad/regex-2024.11.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:59dfe1ed21aea057a65c6b586afd2a945de04fc7db3de0a6e3ed5397ad491b07", size = 781650 },
+    { url = "https://files.pythonhosted.org/packages/a7/d5/880921ee4eec393a4752e6ab9f0fe28009435417c3102fc413f3fe81c4e5/regex-2024.11.6-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:b97c1e0bd37c5cd7902e65f410779d39eeda155800b65fc4d04cc432efa9bc6e", size = 789545 },
+    { url = "https://files.pythonhosted.org/packages/dc/96/53770115e507081122beca8899ab7f5ae28ae790bfcc82b5e38976df6a77/regex-2024.11.6-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f9d1e379028e0fc2ae3654bac3cbbef81bf3fd571272a42d56c24007979bafb6", size = 853045 },
+    { url = "https://files.pythonhosted.org/packages/31/d3/1372add5251cc2d44b451bd94f43b2ec78e15a6e82bff6a290ef9fd8f00a/regex-2024.11.6-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:13291b39131e2d002a7940fb176e120bec5145f3aeb7621be6534e46251912c4", size = 860182 },
+    { url = "https://files.pythonhosted.org/packages/ed/e3/c446a64984ea9f69982ba1a69d4658d5014bc7a0ea468a07e1a1265db6e2/regex-2024.11.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f51f88c126370dcec4908576c5a627220da6c09d0bff31cfa89f2523843316d", size = 787733 },
+    { url = "https://files.pythonhosted.org/packages/2b/f1/e40c8373e3480e4f29f2692bd21b3e05f296d3afebc7e5dcf21b9756ca1c/regex-2024.11.6-cp313-cp313-win32.whl", hash = "sha256:63b13cfd72e9601125027202cad74995ab26921d8cd935c25f09c630436348ff", size = 262122 },
+    { url = "https://files.pythonhosted.org/packages/45/94/bc295babb3062a731f52621cdc992d123111282e291abaf23faa413443ea/regex-2024.11.6-cp313-cp313-win_amd64.whl", hash = "sha256:2b3361af3198667e99927da8b84c1b010752fa4b1115ee30beaa332cabc3ef1a", size = 273545 },
+]
+
 [[package]]
 name = "requests"
 version = "2.32.3"
@@ -1330,6 +1385,28 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4d/c0/1108ad9f01567f66b3154063605b350b69c3c9366732e09e45f9fd0d1deb/safehttpx-0.1.6-py3-none-any.whl", hash = "sha256:407cff0b410b071623087c63dd2080c3b44dc076888d8c5823c00d1e58cb381c", size = 8692 },
 ]
 
+[[package]]
+name = "safetensors"
+version = "0.5.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/71/7e/2d5d6ee7b40c0682315367ec7475693d110f512922d582fef1bd4a63adc3/safetensors-0.5.3.tar.gz", hash = "sha256:b6b0d6ecacec39a4fdd99cc19f4576f5219ce858e6fd8dbe7609df0b8dc56965", size = 67210 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/18/ae/88f6c49dbd0cc4da0e08610019a3c78a7d390879a919411a410a1876d03a/safetensors-0.5.3-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:bd20eb133db8ed15b40110b7c00c6df51655a2998132193de2f75f72d99c7073", size = 436917 },
+    { url = "https://files.pythonhosted.org/packages/b8/3b/11f1b4a2f5d2ab7da34ecc062b0bc301f2be024d110a6466726bec8c055c/safetensors-0.5.3-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:21d01c14ff6c415c485616b8b0bf961c46b3b343ca59110d38d744e577f9cce7", size = 418419 },
+    { url = "https://files.pythonhosted.org/packages/5d/9a/add3e6fef267658075c5a41573c26d42d80c935cdc992384dfae435feaef/safetensors-0.5.3-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:11bce6164887cd491ca75c2326a113ba934be596e22b28b1742ce27b1d076467", size = 459493 },
+    { url = "https://files.pythonhosted.org/packages/df/5c/bf2cae92222513cc23b3ff85c4a1bb2811a2c3583ac0f8e8d502751de934/safetensors-0.5.3-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4a243be3590bc3301c821da7a18d87224ef35cbd3e5f5727e4e0728b8172411e", size = 472400 },
+    { url = "https://files.pythonhosted.org/packages/58/11/7456afb740bd45782d0f4c8e8e1bb9e572f1bf82899fb6ace58af47b4282/safetensors-0.5.3-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8bd84b12b1670a6f8e50f01e28156422a2bc07fb16fc4e98bded13039d688a0d", size = 522891 },
+    { url = "https://files.pythonhosted.org/packages/57/3d/fe73a9d2ace487e7285f6e157afee2383bd1ddb911b7cb44a55cf812eae3/safetensors-0.5.3-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:391ac8cab7c829452175f871fcaf414aa1e292b5448bd02620f675a7f3e7abb9", size = 537694 },
+    { url = "https://files.pythonhosted.org/packages/a6/f8/dae3421624fcc87a89d42e1898a798bc7ff72c61f38973a65d60df8f124c/safetensors-0.5.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cead1fa41fc54b1e61089fa57452e8834f798cb1dc7a09ba3524f1eb08e0317a", size = 471642 },
+    { url = "https://files.pythonhosted.org/packages/ce/20/1fbe16f9b815f6c5a672f5b760951e20e17e43f67f231428f871909a37f6/safetensors-0.5.3-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1077f3e94182d72618357b04b5ced540ceb71c8a813d3319f1aba448e68a770d", size = 502241 },
+    { url = "https://files.pythonhosted.org/packages/5f/18/8e108846b506487aa4629fe4116b27db65c3dde922de2c8e0cc1133f3f29/safetensors-0.5.3-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:799021e78287bac619c7b3f3606730a22da4cda27759ddf55d37c8db7511c74b", size = 638001 },
+    { url = "https://files.pythonhosted.org/packages/82/5a/c116111d8291af6c8c8a8b40628fe833b9db97d8141c2a82359d14d9e078/safetensors-0.5.3-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:df26da01aaac504334644e1b7642fa000bfec820e7cef83aeac4e355e03195ff", size = 734013 },
+    { url = "https://files.pythonhosted.org/packages/7d/ff/41fcc4d3b7de837963622e8610d998710705bbde9a8a17221d85e5d0baad/safetensors-0.5.3-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:32c3ef2d7af8b9f52ff685ed0bc43913cdcde135089ae322ee576de93eae5135", size = 670687 },
+    { url = "https://files.pythonhosted.org/packages/40/ad/2b113098e69c985a3d8fbda4b902778eae4a35b7d5188859b4a63d30c161/safetensors-0.5.3-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:37f1521be045e56fc2b54c606d4455573e717b2d887c579ee1dbba5f868ece04", size = 643147 },
+    { url = "https://files.pythonhosted.org/packages/0a/0c/95aeb51d4246bd9a3242d3d8349c1112b4ee7611a4b40f0c5c93b05f001d/safetensors-0.5.3-cp38-abi3-win32.whl", hash = "sha256:cfc0ec0846dcf6763b0ed3d1846ff36008c6e7290683b61616c4b040f6a54ace", size = 296677 },
+    { url = "https://files.pythonhosted.org/packages/69/e2/b011c38e5394c4c18fb5500778a55ec43ad6106126e74723ffaee246f56e/safetensors-0.5.3-cp38-abi3-win_amd64.whl", hash = "sha256:836cbbc320b47e80acd40e44c8682db0e8ad7123209f69b093def21ec7cafd11", size = 308878 },
+]
+
 [[package]]
 name = "semantic-version"
 version = "2.10.0"
@@ -1429,6 +1506,31 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/35/8a/fd0a54e4bc7d09e6296efc7e9712f16e0001e82a13a90acb1e5729d34b39/synchronicity-0.9.13-py3-none-any.whl", hash = "sha256:762bb5f84def464b2c7dbb944d4f19c3336a12ed7046bc5d9646f0b4a3f6a0d5", size = 36974 },
 ]
 
+[[package]]
+name = "tokenizers"
+version = "0.21.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "huggingface-hub" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/92/76/5ac0c97f1117b91b7eb7323dcd61af80d72f790b4df71249a7850c195f30/tokenizers-0.21.1.tar.gz", hash = "sha256:a1bb04dc5b448985f86ecd4b05407f5a8d97cb2c0532199b2a302a604a0165ab", size = 343256 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a5/1f/328aee25f9115bf04262e8b4e5a2050b7b7cf44b59c74e982db7270c7f30/tokenizers-0.21.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:e78e413e9e668ad790a29456e677d9d3aa50a9ad311a40905d6861ba7692cf41", size = 2780767 },
+    { url = "https://files.pythonhosted.org/packages/ae/1a/4526797f3719b0287853f12c5ad563a9be09d446c44ac784cdd7c50f76ab/tokenizers-0.21.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:cd51cd0a91ecc801633829fcd1fda9cf8682ed3477c6243b9a095539de4aecf3", size = 2650555 },
+    { url = "https://files.pythonhosted.org/packages/4d/7a/a209b29f971a9fdc1da86f917fe4524564924db50d13f0724feed37b2a4d/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28da6b72d4fb14ee200a1bd386ff74ade8992d7f725f2bde2c495a9a98cf4d9f", size = 2937541 },
+    { url = "https://files.pythonhosted.org/packages/3c/1e/b788b50ffc6191e0b1fc2b0d49df8cff16fe415302e5ceb89f619d12c5bc/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34d8cfde551c9916cb92014e040806122295a6800914bab5865deb85623931cf", size = 2819058 },
+    { url = "https://files.pythonhosted.org/packages/36/aa/3626dfa09a0ecc5b57a8c58eeaeb7dd7ca9a37ad9dd681edab5acd55764c/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aaa852d23e125b73d283c98f007e06d4595732104b65402f46e8ef24b588d9f8", size = 3133278 },
+    { url = "https://files.pythonhosted.org/packages/a4/4d/8fbc203838b3d26269f944a89459d94c858f5b3f9a9b6ee9728cdcf69161/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a21a15d5c8e603331b8a59548bbe113564136dc0f5ad8306dd5033459a226da0", size = 3144253 },
+    { url = "https://files.pythonhosted.org/packages/d8/1b/2bd062adeb7c7511b847b32e356024980c0ffcf35f28947792c2d8ad2288/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2fdbd4c067c60a0ac7eca14b6bd18a5bebace54eb757c706b47ea93204f7a37c", size = 3398225 },
+    { url = "https://files.pythonhosted.org/packages/8a/63/38be071b0c8e06840bc6046991636bcb30c27f6bb1e670f4f4bc87cf49cc/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd9a0061e403546f7377df940e866c3e678d7d4e9643d0461ea442b4f89e61a", size = 3038874 },
+    { url = "https://files.pythonhosted.org/packages/ec/83/afa94193c09246417c23a3c75a8a0a96bf44ab5630a3015538d0c316dd4b/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:db9484aeb2e200c43b915a1a0150ea885e35f357a5a8fabf7373af333dcc8dbf", size = 9014448 },
+    { url = "https://files.pythonhosted.org/packages/ae/b3/0e1a37d4f84c0f014d43701c11eb8072704f6efe8d8fc2dcdb79c47d76de/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ed248ab5279e601a30a4d67bdb897ecbe955a50f1e7bb62bd99f07dd11c2f5b6", size = 8937877 },
+    { url = "https://files.pythonhosted.org/packages/ac/33/ff08f50e6d615eb180a4a328c65907feb6ded0b8f990ec923969759dc379/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:9ac78b12e541d4ce67b4dfd970e44c060a2147b9b2a21f509566d556a509c67d", size = 9186645 },
+    { url = "https://files.pythonhosted.org/packages/5f/aa/8ae85f69a9f6012c6f8011c6f4aa1c96154c816e9eea2e1b758601157833/tokenizers-0.21.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:e5a69c1a4496b81a5ee5d2c1f3f7fbdf95e90a0196101b0ee89ed9956b8a168f", size = 9384380 },
+    { url = "https://files.pythonhosted.org/packages/e8/5b/a5d98c89f747455e8b7a9504910c865d5e51da55e825a7ae641fb5ff0a58/tokenizers-0.21.1-cp39-abi3-win32.whl", hash = "sha256:1039a3a5734944e09de1d48761ade94e00d0fa760c0e0551151d4dd851ba63e3", size = 2239506 },
+    { url = "https://files.pythonhosted.org/packages/e6/b6/072a8e053ae600dcc2ac0da81a23548e3b523301a442a6ca900e92ac35be/tokenizers-0.21.1-cp39-abi3-win_amd64.whl", hash = "sha256:0f0dcbcc9f6e13e675a66d7a5f2f225a736745ce484c1a4e07476a89ccdad382", size = 2435481 },
+]
+
 [[package]]
 name = "toml"
 version = "0.10.2"
@@ -1459,6 +1561,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2", size = 78540 },
 ]
 
+[[package]]
+name = "transformers"
+version = "4.52.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "filelock" },
+    { name = "huggingface-hub" },
+    { name = "numpy" },
+    { name = "packaging" },
+    { name = "pyyaml" },
+    { name = "regex" },
+    { name = "requests" },
+    { name = "safetensors" },
+    { name = "tokenizers" },
+    { name = "tqdm" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/da/a9/275037087f9d846580b02f2d7cae0e0a6955d46f84583d0151d6227bd416/transformers-4.52.4.tar.gz", hash = "sha256:aff3764441c1adc192a08dba49740d3cbbcb72d850586075aed6bd89b98203e6", size = 8945376 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/96/f2/25b27b396af03d5b64e61976b14f7209e2939e9e806c10749b6d277c273e/transformers-4.52.4-py3-none-any.whl", hash = "sha256:203f5c19416d5877e36e88633943761719538a25d9775977a24fe77a1e5adfc7", size = 10460375 },
+]
+
 [[package]]
 name = "typer"
 version = "0.16.0"