brainstorm on interface execution

app.py

@@ -8,7 +8,7 @@ source_df, template_df = get_dataframes()
 
 with gr.Blocks() as demo:
     with gr.Column():
-        gr.Markdown("## To begin, upload a Template CSV and a Source CSV file.")
+        gr.Markdown("# Step 1\n### Upload a Template CSV and a Source CSV file.")
         with gr.Row():
             gr.inputs.File(label="Template", type="file", file_count='single')
             gr.inputs.File(label="Source", type="file", file_count='single')

src/core.py

@@ -16,16 +16,11 @@ load_dotenv()
 DATA_DIR_PATH = os.path.join(os.path.dirname(__file__), 'data')
 SYNTHETIC_DATA_DIR_PATH = os.path.join(DATA_DIR_PATH, 'synthetic')
 
-TRANSFORM_MODEL = ChatOpenAI(
+BASE_MODEL = ChatOpenAI(
     model_name='gpt-4',
     temperature=0,
 )
 
-NATURAL_LANGUAGE_MODEL = ChatOpenAI(
-    model_name='gpt-4',
-    temperature=0.1,
-)
-
 def get_dataframes():
     source = pd.read_csv(os.path.join(SYNTHETIC_DATA_DIR_PATH, 'legal_entries_a.csv'))
     template = pd.read_csv(os.path.join(SYNTHETIC_DATA_DIR_PATH, 'legal_template.csv'))
@@ -41,19 +36,19 @@ def get_table_mapping(source_df, template_df) -> TableMapping:
         partial_variables={'format_instructions': table_mapping_parser.get_format_instructions()},
     )
 
-    mapping_chain = analyst_prompt | TRANSFORM_MODEL | table_mapping_parser
+    mapping_chain = analyst_prompt | BASE_MODEL | table_mapping_parser
     return mapping_chain.invoke({"source_1_csv_str": get_data_str_from_df_for_prompt(source_df), "target_csv_str": get_data_str_from_df_for_prompt(template_df)})
 
 
 def get_code_spec(table_mapping: TableMapping) -> str:
     writer_prompt = ChatPromptTemplate.from_template(SPEC_WRITER_PROMPT_STR)
-    writer_chain = writer_prompt | NATURAL_LANGUAGE_MODEL | StrOutputParser()
+    writer_chain = writer_prompt | BASE_MODEL | StrOutputParser()
     return writer_chain.invoke({"table_mapping": str(table_mapping)})
 
 
 def get_mapping_code(spec_str: str) -> str:
     engineer_prompt = ChatPromptTemplate.from_template(ENGINEER_PROMPT_STR)
-    engineer_chain = engineer_prompt | TRANSFORM_MODEL | StrOutputParser()
+    engineer_chain = engineer_prompt | BASE_MODEL | StrOutputParser()
     return engineer_chain.invoke({"spec_str": spec_str})
 
 

src/notebooks/brainstorm4.ipynb

@@ -2,16 +2,24 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "True"
       ]
      },
-     "execution_count": 90,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -35,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -46,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 104,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -60,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -77,7 +85,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 106,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -148,7 +156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 107,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -196,7 +204,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -227,14 +235,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 108,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7874\n",
+      "Running on local URL:  http://127.0.0.1:7938\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -242,7 +250,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7874/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7938/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -255,7 +263,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 17,
+     "execution_count": 108,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -270,16 +278,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 109,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7885\n",
-      "\n",
-      "Thanks for being a Gradio user! If you have questions or feedback, please join our Discord server and chat with us: https://discord.gg/feTf9x3ZSB\n",
+      "Running on local URL:  http://127.0.0.1:7939\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -287,7 +293,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7885/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7939/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -300,7 +306,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 34,
+     "execution_count": 109,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -320,7 +326,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 110,
    "metadata": {},
    "outputs": [
     {
@@ -335,7 +341,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7892\n",
+      "Running on local URL:  http://127.0.0.1:7940\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -343,7 +349,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7892/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7940/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -356,7 +362,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 41,
+     "execution_count": 110,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -377,40 +383,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:18: GradioDeprecationWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your component from gradio.components\n",
-      "  gr.inputs.File(label=\"Template\", type=\"file\", file_count='single')\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:18: GradioDeprecationWarning: `optional` parameter is deprecated, and it has no effect\n",
-      "  gr.inputs.File(label=\"Template\", type=\"file\", file_count='single')\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:18: GradioDeprecationWarning: `keep_filename` parameter is deprecated, and it has no effect\n",
-      "  gr.inputs.File(label=\"Template\", type=\"file\", file_count='single')\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:19: GradioDeprecationWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your component from gradio.components\n",
-      "  gr.inputs.File(label=\"Source\", type=\"file\", file_count='single')\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:19: GradioDeprecationWarning: `optional` parameter is deprecated, and it has no effect\n",
-      "  gr.inputs.File(label=\"Source\", type=\"file\", file_count='single')\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:19: GradioDeprecationWarning: `keep_filename` parameter is deprecated, and it has no effect\n",
-      "  gr.inputs.File(label=\"Source\", type=\"file\", file_count='single')\n",
-      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/gradio/utils.py:841: UserWarning: Expected 1 arguments for function <function generate_code at 0x12cb559d0>, received 0.\n",
+      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_13584/2709196309.py:47: GradioUnusedKwargWarning: You have unused kwarg parameters in UploadButton, please remove them: {'live': True}\n",
+      "  upload_template_btn = gr.UploadButton(label=\"Upload Template File\", file_types = ['.csv'], live=True, file_count = \"single\")\n",
+      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_13584/2709196309.py:51: GradioUnusedKwargWarning: You have unused kwarg parameters in UploadButton, please remove them: {'live': True}\n",
+      "  upload_source_button = gr.UploadButton(label=\"Upload Source File\", file_types = ['.csv'], live=True, file_count = \"single\")\n",
+      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/gradio/utils.py:841: UserWarning: Expected 1 arguments for function <function generate_code at 0x12ba74f70>, received 0.\n",
       "  warnings.warn(\n",
-      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/gradio/utils.py:845: UserWarning: Expected at least 1 arguments for function <function generate_code at 0x12cb559d0>, received 0.\n",
-      "  warnings.warn(\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:39: GradioUnusedKwargWarning: You have unused kwarg parameters in Button, please remove them: {'trigger': 'transform_source'}\n",
-      "  gr.Button(value=\"Transform Source\", variant=\"primary\", trigger=\"transform_source\")\n",
-      "/var/folders/lx/3ksh07r96gn2v7b8mb__3mpc0000gn/T/ipykernel_94012/2180252060.py:40: GradioUnusedKwargWarning: You have unused kwarg parameters in Button, please remove them: {'trigger': 'save_code'}\n",
-      "  gr.Button(value=\"Save Code\", variant=\"secondary\", trigger=\"save_code\")\n"
+      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/gradio/utils.py:845: UserWarning: Expected at least 1 arguments for function <function generate_code at 0x12ba74f70>, received 0.\n",
+      "  warnings.warn(\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7934\n",
+      "Running on local URL:  http://127.0.0.1:7881\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -418,7 +412,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7934/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7881/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -431,62 +425,255 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 89,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/andybryant/Desktop/projects/zero-mapper/venv/lib/python3.9/site-packages/gradio/helpers.py:735: UserWarning: Unexpected argument. Filling with None.\n",
+      "  warnings.warn(\"Unexpected argument. Filling with None.\")\n"
+     ]
     }
    ],
    "source": [
     "def _sanitize_python_output(text: str):\n",
     "    _, after = text.split(\"```python\")\n",
     "    return after.split(\"```\")[0]\n",
+    "file_val = None\n",
+    "def do_stuff(file, extra):\n",
+    "    assert False, (file, extra)\n",
+    "    return pd.read_csv(file.name)\n",
+    "    file_val = file\n",
     "\n",
-    "def do_stuff(val):\n",
-    "    print(val)\n",
-    "\n",
+    "import io\n",
     "def generate_code(val):\n",
     "    return '# check this out'\n",
     "\n",
-    "def save_csv_file(df, filename):\n",
-    "    df.to_csv(os.path.join(data_dir_path, 'output', filename) + '.csv')\n",
+    "def export_csv(d):\n",
+    "    filepath = \"output.csv\"\n",
+    "    d.to_csv(filepath)\n",
+    "    return gr.File.update(value=filepath, visible=True)\n",
     "\n",
-    "with gr.Blocks() as demo:\n",
-    "    with gr.Column():\n",
-    "        gr.Markdown(\"## To begin, upload a Template CSV and a Source CSV file.\")\n",
-    "        with gr.Row():\n",
-    "            gr.inputs.File(label=\"Template\", type=\"file\", file_count='single')\n",
-    "            gr.inputs.File(label=\"Source\", type=\"file\", file_count='single')\n",
-    "\n",
-    "    with gr.Column():\n",
-    "        gr.Markdown(\"## Mapping from Source to Template\")\n",
-    "        with gr.Row():\n",
-    "            table_mapping_df = pd.DataFrame(table_mapping.dict()['table_mappings'])\n",
-    "            gr.DataFrame(value=table_mapping_df)\n",
-    "            save_mapping_btn = gr.Button(value=\"Save Mapping\", variant=\"secondary\")\n",
-    "            save_mapping_btn.click(fn=lambda : save_csv_file(table_mapping_df, 'table_mapping'))\n",
+    "def get_table_mapping(source_df, template_df):\n",
+    "    # table_mapping_df = pd.DataFrame(table_mapping.dict()['table_mappings'])\n",
+    "    return pd.DataFrame({'a': [1,2,3], 'b': [4,5,6]})\n",
     "\n",
+    "def process_csv_text(temp_file):\n",
+    "    if isinstance(temp_file, str):\n",
+    "      df = pd.read_csv(io.StringIO(temp_file))\n",
+    "    else:\n",
+    "      df = pd.read_csv(temp_file.name)\n",
+    "    return df\n",
+    "\n",
+    "def generate_step_markdown(step_number: int, subtitle: str):\n",
+    "    return gr.Markdown(f\"# Step {step_number}\\n\\n ### {subtitle}\")\n",
+    "\n",
+    "def export_csv(d):\n",
+    "    d.to_csv(\"output.csv\")\n",
+    "    return gr.File.update(value=\"output.csv\", visible=True)\n",
+    "\n",
+    "def export_code(val):\n",
+    "    with open(\"output.py\", \"w\") as f:\n",
+    "        f.write(val)\n",
+    "    return gr.File.update(value=\"output.py\", visible=True)\n",
+    "\n",
+    "with gr.Blocks() as demo:\n",
+    "    # STEP 1\n",
+    "    generate_step_markdown(1, \"Upload a Template CSV (target schema) and a Source CSV.\")\n",
+    "    with gr.Row():\n",
+    "        with gr.Column():\n",
+    "            upload_template_btn = gr.UploadButton(label=\"Upload Template File\", file_types = ['.csv'], live=True, file_count = \"single\")\n",
+    "            template_df = gr.Dataframe(type=\"pandas\")\n",
+    "            upload_template_btn.upload(fn=process_csv_text, inputs=upload_template_btn, outputs=template_df)\n",
+    "        with gr.Column():\n",
+    "            upload_source_button = gr.UploadButton(label=\"Upload Source File\", file_types = ['.csv'], live=True, file_count = \"single\")\n",
+    "            source_df = gr.Dataframe(type=\"pandas\")\n",
+    "            upload_source_button.upload(fn=process_csv_text, inputs=upload_source_button, outputs=source_df)\n",
+    "    \n",
+    "    # STEP 2\n",
+    "    generate_step_markdown(2, \"Generate mapping from Source to Template. Once generated, you can edit the values directly in the table below.\")\n",
+    "    with gr.Row():\n",
+    "        generate_mapping_btn = gr.Button(value=\"Generate Mapping\", variant=\"primary\")\n",
+    "    with gr.Row():\n",
+    "        table_mapping_df = gr.DataFrame(type=\"pandas\")\n",
+    "        generate_mapping_btn.click(fn=get_table_mapping, inputs=[source_df, template_df], outputs=[table_mapping_df])\n",
+    "    \n",
+    "    # STEP 3\n",
+    "    generate_step_markdown(3, \"Save mapping to CSV and download (optional).\")\n",
+    "    with gr.Row():\n",
+    "        save_mapping_btn = gr.Button(value=\"Save Mapping\", variant=\"secondary\")\n",
+    "    with gr.Row():\n",
+    "        csv = gr.File(interactive=False, visible=False)\n",
+    "        save_mapping_btn.click(export_csv, table_mapping_df, csv)\n",
+    "        mapping_file = gr.File(label=\"Downloaded File\", visible=False)\n",
+    "        mapping_file.change(lambda x: x, mapping_file, table_mapping_df)\n",
+    "    # STEP 4\n",
+    "    generate_step_markdown(4, \"Generate python code to transform Source to Template, using the generated mapping.\")\n",
     "    with gr.Row():\n",
-    "        test = gr.Markdown()\n",
     "        generate_code_btn = gr.Button(value=\"Generate Code from Mapping\", variant=\"primary\")\n",
-    "        generate_code_btn.click(fn=generate_code, outputs=test)\n",
-    "\n",
-    "    with gr.Column():\n",
-    "        gr.Markdown(\"## Here is the code that will be used to transform the source file into the template schema:\")\n",
-    "        gr.Code(language=\"python\", value=_sanitize_python_output(transform_code))\n",
+    "    with gr.Row():\n",
+    "        code_block = gr.Code(language=\"python\")\n",
+    "        generate_code_btn.click(fn=generate_code, outputs=[code_block])\n",
     "\n",
+    "    # STEP 5\n",
+    "    generate_step_markdown(5, \"Save transformation code (optional).\")\n",
     "    with gr.Row():\n",
-    "        gr.Button(value=\"Transform Source\", variant=\"primary\", trigger=\"transform_source\")\n",
-    "        gr.Button(value=\"Save Code\", variant=\"secondary\", trigger=\"save_code\")\n",
+    "        save_code_btn = gr.Button(value=\"Save Code\", variant=\"secondary\")\n",
+    "    with gr.Row():\n",
+    "        text = gr.File(interactive=False, visible=False)\n",
+    "        save_code_btn.click(export_code, code_block, text)\n",
+    "        code_file = gr.File(label=\"Downloaded File\", visible=False)\n",
+    "        code_file.change(lambda x: x, code_file, code_block)\n",
+    "\n",
+    "    # with gr.Row():\n",
+    "    #     gr.Button(value=\"Transform Source\", variant=\"primary\", trigger=\"transform_source\")\n",
+    "    #     gr.Button(value=\"Save Code\", variant=\"secondary\", trigger=\"save_code\")\n",
     "    \n",
+    "    # with gr.Row():\n",
+    "    #     with gr.Column():\n",
+    "    #         gr.Dataframe(label='Target (template)', type='pandas', value=template_df)\n",
+    "    #     with gr.Column():\n",
+    "    #         gr.Dataframe(label='Source (transformed)', type='pandas', value=PythonAstREPLTool(locals={'source_df': table_1_df}).run(transform_code))\n",
+    "\n",
+    "            \n",
+    "            \n",
+    "\n",
+    "\n",
+    "\n",
+    "# def mock_ocr(f):\n",
+    "#     return [[1, 2, 3], [4, 5, 6]]\n",
+    "\n",
+    "\n",
+    "\n",
+    "# with gr.Blocks() as demo:\n",
+    "#     with gr.Row():\n",
+    "#         file = gr.File(label=\"PDF file\", file_types=[\".pdf\"])\n",
+    "#         dataframe = gr.Dataframe()\n",
+    "        \n",
+    "#         with gr.Column():\n",
+    "#             button = gr.Button(\"Export\")\n",
+    "#             csv = gr.File(interactive=False, visible=False)\n",
+    "            \n",
+    "            \n",
+    "#     file.change(mock_ocr, file, dataframe)\n",
+    "#     button.click(export_csv, dataframe, csv)\n",
+    "        \n",
+    "# demo.launch()\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "    # with gr.Column():\n",
+    "    #     gr.Markdown(\"## Mapping from Source to Template\")\n",
+    "    #     with gr.Row():\n",
+    "    #         table_mapping_df = pd.DataFrame(table_mapping.dict()['table_mappings'])\n",
+    "    #         gr.DataFrame(value=table_mapping_df)\n",
+    "    #         save_mapping_btn = gr.Button(value=\"Save Mapping\", variant=\"secondary\")\n",
+    "    #         save_mapping_btn.click(fn=lambda : save_csv_file(table_mapping_df, 'table_mapping'))\n",
+    "\n",
+    "    # with gr.Row():\n",
+    "    #     test = gr.Markdown()\n",
+    "    #     generate_code_btn = gr.Button(value=\"Generate Code from Mapping\", variant=\"primary\")\n",
+    "    #     generate_code_btn.click(fn=generate_code, outputs=test)\n",
+    "\n",
+    "    # with gr.Column():\n",
+    "    #     gr.Markdown(\"## Here is the code that will be used to transform the source file into the template schema:\")\n",
+    "    #     gr.Code(language=\"python\", value=_sanitize_python_output(transform_code))\n",
+    "\n",
+    "    # with gr.Row():\n",
+    "    #     gr.Button(value=\"Transform Source\", variant=\"primary\", trigger=\"transform_source\")\n",
+    "    #     gr.Button(value=\"Save Code\", variant=\"secondary\", trigger=\"save_code\")\n",
+    "    \n",
+    "    # with gr.Row():\n",
+    "    #     with gr.Column():\n",
+    "    #         gr.Dataframe(label='Target (template)', type='pandas', value=template_df)\n",
+    "    #     with gr.Column():\n",
+    "    #         gr.Dataframe(label='Source (transformed)', type='pandas', value=PythonAstREPLTool(locals={'source_df': table_1_df}).run(transform_code))\n",
+    "\n",
+    "demo.launch()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7866\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7866/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "\n",
+    "def mock_ocr(f):\n",
+    "    return [[1, 2, 3], [4, 5, 6]]\n",
+    "\n",
+    "def export_csv(d):\n",
+    "    d.to_csv(\"output.csv\")\n",
+    "    return gr.File.update(value=\"output.csv\", visible=True)\n",
+    "\n",
+    "with gr.Blocks() as demo:\n",
     "    with gr.Row():\n",
+    "        file = gr.File(label=\"PDF file\", file_types=[\".pdf\"])\n",
+    "        dataframe = gr.Dataframe()\n",
+    "        \n",
     "        with gr.Column():\n",
-    "            gr.Dataframe(label='Target (template)', type='pandas', value=template_df)\n",
-    "        with gr.Column():\n",
-    "            gr.Dataframe(label='Source (transformed)', type='pandas', value=PythonAstREPLTool(locals={'source_df': table_1_df}).run(transform_code))\n",
-    "\n",
+    "            button = gr.Button(\"Export\")\n",
+    "            csv = gr.File(interactive=False, visible=False)\n",
+    "            \n",
+    "            \n",
+    "    file.change(mock_ocr, file, dataframe)\n",
+    "    button.click(export_csv, dataframe, csv)\n",
+    "        \n",
     "demo.launch()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 176,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "dataframe\n"
+     ]
+    }
+   ],
+   "source": [
+    "source_df"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

src/notebooks/output.csv

@@ -0,0 +1,2 @@
+,1,2,3
+0,,,

src/notebooks/output.py

@@ -0,0 +1 @@
+# check this out