{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "04815d1b-44ee-4bd3-878e-fa0c3bf9fa7f", "metadata": { "id": "04815d1b-44ee-4bd3-878e-fa0c3bf9fa7f", "tags": [] }, "source": [ "# Hackathon Illuminati Question answering app\n", "\n", "This notebook shows how to make this app:" ] }, { "cell_type": "code", "execution_count": 38, "id": "a181568b-9cde-4a55-a853-4d2a41dbfdad", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "a181568b-9cde-4a55-a853-4d2a41dbfdad", "outputId": "0589dcc5-1cf0-42be-a29a-0f75e3bb877d", "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.30.1)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.0)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.1)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.22.4)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2022.10.31)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.27.1)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)\n", "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.3.1)\n", "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.65.0)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers) (2023.4.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers) (4.5.0)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4)\n", "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: easyocr in /usr/local/lib/python3.10/dist-packages (1.7.0)\n", "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from easyocr) (2.0.1+cu118)\n", "Requirement already satisfied: torchvision>=0.5 in /usr/local/lib/python3.10/dist-packages (from easyocr) (0.15.2+cu118)\n", "Requirement already satisfied: opencv-python-headless in /usr/local/lib/python3.10/dist-packages (from easyocr) (4.7.0.72)\n", "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from easyocr) (1.10.1)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from easyocr) (1.22.4)\n", "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from easyocr) (8.4.0)\n", "Requirement already satisfied: scikit-image in /usr/local/lib/python3.10/dist-packages (from easyocr) (0.19.3)\n", "Requirement already satisfied: python-bidi in /usr/local/lib/python3.10/dist-packages (from easyocr) (0.4.2)\n", "Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from easyocr) (6.0)\n", "Requirement already satisfied: Shapely in /usr/local/lib/python3.10/dist-packages (from easyocr) (2.0.1)\n", "Requirement already satisfied: pyclipper in /usr/local/lib/python3.10/dist-packages (from easyocr) (1.3.0.post4)\n", "Requirement already satisfied: ninja in /usr/local/lib/python3.10/dist-packages (from easyocr) (1.11.1)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from torchvision>=0.5->easyocr) (2.27.1)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (3.12.0)\n", "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (4.5.0)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (1.11.1)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (3.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (3.1.2)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch->easyocr) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->easyocr) (3.25.2)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->easyocr) (16.0.5)\n", "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from python-bidi->easyocr) (1.16.0)\n", "Requirement already satisfied: imageio>=2.4.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->easyocr) (2.25.1)\n", "Requirement already satisfied: tifffile>=2019.7.26 in /usr/local/lib/python3.10/dist-packages (from scikit-image->easyocr) (2023.4.12)\n", "Requirement already satisfied: PyWavelets>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->easyocr) (1.4.1)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from scikit-image->easyocr) (23.1)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->easyocr) (2.1.2)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision>=0.5->easyocr) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision>=0.5->easyocr) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision>=0.5->easyocr) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision>=0.5->easyocr) (3.4)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->easyocr) (1.3.0)\n", "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: pdf2image in /usr/local/lib/python3.10/dist-packages (1.16.3)\n", "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from pdf2image) (8.4.0)\n", "Reading package lists... Done\n", "Building dependency tree \n", "Reading state information... Done\n", "poppler-utils is already the newest version (0.86.1-0ubuntu1.1).\n", "0 upgraded, 0 newly installed, 0 to remove and 38 not upgraded.\n" ] } ], "source": [ "# !pip install transformers\n", "# !pip install easyocr\n", "# !pip install pdf2image\n", "# !apt-get install poppler-utils\n" ] }, { "cell_type": "code", "execution_count": 39, "id": "y_NPBrAUkFxS", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "y_NPBrAUkFxS", "outputId": "2c418c3d-52a7-4f31-fac9-69da8c356571" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: PyPDF2 in /usr/local/lib/python3.10/dist-packages (3.0.1)\n" ] } ], "source": [ "# ! pip install PyPDF2" ] }, { "cell_type": "code", "execution_count": 40, "id": "9a464409-d064-4766-a9cb-5119f6c4b8f5", "metadata": { "id": "9a464409-d064-4766-a9cb-5119f6c4b8f5", "tags": [] }, "outputs": [], "source": [ "import panel as pn\n", "from transformers import pipeline\n", "from PyPDF2 import PdfReader" ] }, { "cell_type": "code", "execution_count": 41, "id": "b2d07ea5-9ff2-4c96-a8dc-92895d870b73", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "id": "b2d07ea5-9ff2-4c96-a8dc-92895d870b73", "outputId": "7d8183bc-c2f2-4e18-cd39-d9788d86c154", "tags": [] }, "outputs": [ { "data": { "application/javascript": "(function(root) {\n function now() {\n return new Date();\n }\n\n var force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, js_modules, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n if (js_modules == null) js_modules = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls.length === 0 && js_modules.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error() {\n console.error(\"failed to load \" + url);\n }\n\n for (var i = 0; i < css_urls.length; i++) {\n var url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error;\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n var skip = [];\n if (window.requirejs) {\n window.requirejs.config({'packages': {}, 'paths': {'Quill': 'https://cdn.quilljs.com/1.3.6/quill', 'gridstack': 'https://cdn.jsdelivr.net/npm/gridstack@4.2.5/dist/gridstack-h5', 'notyf': 'https://cdn.jsdelivr.net/npm/notyf@3/notyf.min'}, 'shim': {'gridstack': {'exports': 'GridStack'}}});\n require([\"Quill\"], function(Quill) {\n\twindow.Quill = Quill\n\ton_load()\n })\n require([\"gridstack\"], function(GridStack) {\n\twindow.GridStack = GridStack\n\ton_load()\n })\n require([\"notyf\"], function() {\n\ton_load()\n })\n root._bokeh_is_loading = css_urls.length + 3;\n } else {\n root._bokeh_is_loading = css_urls.length + js_urls.length + js_modules.length;\n } if (((window['Quill'] !== undefined) && (!(window['Quill'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } if (((window['GridStack'] !== undefined) && (!(window['GridStack'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/gridstack/gridstack@4.2.5/dist/gridstack-h5.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } if (((window['Notyf'] !== undefined) && (!(window['Notyf'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/notificationarea/notyf@3/notyf.min.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } for (var i = 0; i < js_urls.length; i++) {\n var url = js_urls[i];\n if (skip.indexOf(url) >= 0) {\n\tif (!window.requirejs) {\n\t on_load();\n\t}\n\tcontinue;\n }\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n for (var i = 0; i < js_modules.length; i++) {\n var url = js_modules[i];\n if (skip.indexOf(url) >= 0) {\n\tif (!window.requirejs) {\n\t on_load();\n\t}\n\tcontinue;\n }\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n element.type = \"module\";\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n if (!js_urls.length && !js_modules.length) {\n on_load()\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n var js_urls = [\"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-2.4.3.min.js\", \"https://unpkg.com/@holoviz/panel@0.14.4/dist/panel.min.js\"];\n var js_modules = [];\n var css_urls = [\"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.bubble.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.snow.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/widgets.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/alerts.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/markdown.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/card.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/loading.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/dataframe.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/json.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/debugger.css\"];\n var inline_js = [ function(Bokeh) {\n inject_raw_css(\"\\n .bk.pn-loading.arc:before {\\n background-image: url(\\\"data:image/svg+xml;base64,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\\\");\\n background-size: auto calc(min(50%, 400px));\\n }\\n \");\n }, function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {} // ensure no trailing comma for IE\n ];\n\n function run_inline_js() {\n if ((root.Bokeh !== undefined) || (force === true)) {\n for (var i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, js_modules, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));", "application/vnd.holoviews_load.v0+json": "" }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/javascript": "\nif ((window.PyViz === undefined) || (window.PyViz instanceof HTMLElement)) {\n window.PyViz = {comms: {}, comm_status:{}, kernels:{}, receivers: {}, plot_index: []}\n}\n\n\n function JupyterCommManager() {\n }\n\n JupyterCommManager.prototype.register_target = function(plot_id, comm_id, msg_handler) {\n if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n comm_manager.register_target(comm_id, function(comm) {\n comm.on_msg(msg_handler);\n });\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n window.PyViz.kernels[plot_id].registerCommTarget(comm_id, function(comm) {\n comm.onMsg = msg_handler;\n });\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n google.colab.kernel.comms.registerTarget(comm_id, (comm) => {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n console.log(message)\n var content = {data: message.data, comm_id};\n var buffers = []\n for (var buffer of message.buffers || []) {\n buffers.push(new DataView(buffer))\n }\n var metadata = message.metadata || {};\n var msg = {content, buffers, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n })\n }\n }\n\n JupyterCommManager.prototype.get_client_comm = function(plot_id, comm_id, msg_handler) {\n if (comm_id in window.PyViz.comms) {\n return window.PyViz.comms[comm_id];\n } else if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n var comm = comm_manager.new_comm(comm_id, {}, {}, {}, comm_id);\n if (msg_handler) {\n comm.on_msg(msg_handler);\n }\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n var comm = window.PyViz.kernels[plot_id].connectToComm(comm_id);\n comm.open();\n if (msg_handler) {\n comm.onMsg = msg_handler;\n }\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n var comm_promise = google.colab.kernel.comms.open(comm_id)\n comm_promise.then((comm) => {\n window.PyViz.comms[comm_id] = comm;\n if (msg_handler) {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n var content = {data: message.data};\n var metadata = message.metadata || {comm_id};\n var msg = {content, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n }\n }) \n var sendClosure = (data, metadata, buffers, disposeOnDone) => {\n return comm_promise.then((comm) => {\n comm.send(data, metadata, buffers, disposeOnDone);\n });\n };\n var comm = {\n send: sendClosure\n };\n }\n window.PyViz.comms[comm_id] = comm;\n return comm;\n }\n window.PyViz.comm_manager = new JupyterCommManager();\n \n\n\nvar JS_MIME_TYPE = 'application/javascript';\nvar HTML_MIME_TYPE = 'text/html';\nvar EXEC_MIME_TYPE = 'application/vnd.holoviews_exec.v0+json';\nvar CLASS_NAME = 'output';\n\n/**\n * Render data to the DOM node\n */\nfunction render(props, node) {\n var div = document.createElement(\"div\");\n var script = document.createElement(\"script\");\n node.appendChild(div);\n node.appendChild(script);\n}\n\n/**\n * Handle when a new output is added\n */\nfunction handle_add_output(event, handle) {\n var output_area = handle.output_area;\n var output = handle.output;\n if ((output.data == undefined) || (!output.data.hasOwnProperty(EXEC_MIME_TYPE))) {\n return\n }\n var id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n var toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n if (id !== undefined) {\n var nchildren = toinsert.length;\n var html_node = toinsert[nchildren-1].children[0];\n html_node.innerHTML = output.data[HTML_MIME_TYPE];\n var scripts = [];\n var nodelist = html_node.querySelectorAll(\"script\");\n for (var i in nodelist) {\n if (nodelist.hasOwnProperty(i)) {\n scripts.push(nodelist[i])\n }\n }\n\n scripts.forEach( function (oldScript) {\n var newScript = document.createElement(\"script\");\n var attrs = [];\n var nodemap = oldScript.attributes;\n for (var j in nodemap) {\n if (nodemap.hasOwnProperty(j)) {\n attrs.push(nodemap[j])\n }\n }\n attrs.forEach(function(attr) { newScript.setAttribute(attr.name, attr.value) });\n newScript.appendChild(document.createTextNode(oldScript.innerHTML));\n oldScript.parentNode.replaceChild(newScript, oldScript);\n });\n if (JS_MIME_TYPE in output.data) {\n toinsert[nchildren-1].children[1].textContent = output.data[JS_MIME_TYPE];\n }\n output_area._hv_plot_id = id;\n if ((window.Bokeh !== undefined) && (id in Bokeh.index)) {\n window.PyViz.plot_index[id] = Bokeh.index[id];\n } else {\n window.PyViz.plot_index[id] = null;\n }\n } else if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n var bk_div = document.createElement(\"div\");\n bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n var script_attrs = bk_div.children[0].attributes;\n for (var i = 0; i < script_attrs.length; i++) {\n toinsert[toinsert.length - 1].childNodes[1].setAttribute(script_attrs[i].name, script_attrs[i].value);\n }\n // store reference to server id on output_area\n output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n }\n}\n\n/**\n * Handle when an output is cleared or removed\n */\nfunction handle_clear_output(event, handle) {\n var id = handle.cell.output_area._hv_plot_id;\n var server_id = handle.cell.output_area._bokeh_server_id;\n if (((id === undefined) || !(id in PyViz.plot_index)) && (server_id !== undefined)) { return; }\n var comm = window.PyViz.comm_manager.get_client_comm(\"hv-extension-comm\", \"hv-extension-comm\", function () {});\n if (server_id !== null) {\n comm.send({event_type: 'server_delete', 'id': server_id});\n return;\n } else if (comm !== null) {\n comm.send({event_type: 'delete', 'id': id});\n }\n delete PyViz.plot_index[id];\n if ((window.Bokeh !== undefined) & (id in window.Bokeh.index)) {\n var doc = window.Bokeh.index[id].model.document\n doc.clear();\n const i = window.Bokeh.documents.indexOf(doc);\n if (i > -1) {\n window.Bokeh.documents.splice(i, 1);\n }\n }\n}\n\n/**\n * Handle kernel restart event\n */\nfunction handle_kernel_cleanup(event, handle) {\n delete PyViz.comms[\"hv-extension-comm\"];\n window.PyViz.plot_index = {}\n}\n\n/**\n * Handle update_display_data messages\n */\nfunction handle_update_output(event, handle) {\n handle_clear_output(event, {cell: {output_area: handle.output_area}})\n handle_add_output(event, handle)\n}\n\nfunction register_renderer(events, OutputArea) {\n function append_mime(data, metadata, element) {\n // create a DOM node to render to\n var toinsert = this.create_output_subarea(\n metadata,\n CLASS_NAME,\n EXEC_MIME_TYPE\n );\n this.keyboard_manager.register_events(toinsert);\n // Render to node\n var props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n render(props, toinsert[0]);\n element.append(toinsert);\n return toinsert\n }\n\n events.on('output_added.OutputArea', handle_add_output);\n events.on('output_updated.OutputArea', handle_update_output);\n events.on('clear_output.CodeCell', handle_clear_output);\n events.on('delete.Cell', handle_clear_output);\n events.on('kernel_ready.Kernel', handle_kernel_cleanup);\n\n OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n safe: true,\n index: 0\n });\n}\n\nif (window.Jupyter !== undefined) {\n try {\n var events = require('base/js/events');\n var OutputArea = require('notebook/js/outputarea').OutputArea;\n if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n register_renderer(events, OutputArea);\n }\n } catch(err) {\n }\n}\n", "application/vnd.holoviews_load.v0+json": "" }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "pn.extension('texteditor', template=\"bootstrap\", sizing_mode='stretch_width')\n", "pn.state.template.param.update(\n", " main_max_width=\"690px\",\n", " header_background=\"#F08080\",\n", ")" ] }, { "cell_type": "code", "execution_count": 42, "id": "763db4d0-3436-41d3-8b0f-e66ce16468cd", "metadata": { "id": "763db4d0-3436-41d3-8b0f-e66ce16468cd", "tags": [] }, "outputs": [], "source": [ "file_input = pn.widgets.FileInput(width=300)\n", "\n", "prompt = pn.widgets.TextEditor(\n", " value=\"\", placeholder=\"Enter your questions here...\", height=160, toolbar=False\n", ")\n", "run_button = pn.widgets.Button(name=\"Run\")\n", "\n", "widgets = pn.Row(\n", " pn.Column(prompt, run_button, margin=5), width = 630\n", ")" ] }, { "cell_type": "code", "execution_count": 43, "id": "9b83cc06-3401-498f-8f84-8a98370f3121", "metadata": { "id": "9b83cc06-3401-498f-8f84-8a98370f3121", "tags": [] }, "outputs": [], "source": [ "def qa(file, query):\n", " text = ''\n", " reader = PdfReader(file)\n", " for i in range(len(reader.pages)):\n", " # creating a page object\n", " pageObj = reader.pages[i]\n", " # extracting text from page\n", " text=text+pageObj.extract_text()\n", " model = pipeline(\"question-answering\", model='deepset/roberta-base-squad2')\n", " context = text\n", " result = model(question=query, context=context)\n", " print(f\"Answer: {result['answer']}\")\n", " return result" ] }, { "cell_type": "code", "execution_count": 44, "id": "60e1b3d3-c0d2-4260-ae0c-26b03f1b8824", "metadata": { "id": "60e1b3d3-c0d2-4260-ae0c-26b03f1b8824" }, "outputs": [], "source": [ "convos = [] # list of all panel objects\n", "\n", "def qa_result(_):\n", " # saving pdf as a temp file\n", " if file_input.value is not None:\n", " file_input.save(\"/.cache/temp.pdf\")\n", "\n", " prompt_text = prompt.value\n", " if prompt_text:\n", " result = qa(file=\"/.cache/temp.pdf\", query=prompt_text)\n", " convos.extend([\n", " pn.Row(\n", " pn.panel(\"Q: \", width=10),\n", " prompt_text,\n", " width=600\n", " ),\n", " pn.Row(\n", " pn.panel(\"A: \", width=10),\n", " pn.Column(\n", " result[\"answer\"],\n", " )\n", " )\n", " ])\n", " #return convos\n", " return pn.Column(*convos, margin=15, width=575, min_height=400)\n" ] }, { "cell_type": "code", "execution_count": 45, "id": "c3a70857-0b98-4f62-a9c0-b62ca42b474c", "metadata": { "id": "c3a70857-0b98-4f62-a9c0-b62ca42b474c", "tags": [] }, "outputs": [], "source": [ "qa_interactive = pn.panel(\n", " pn.bind(qa_result, run_button),\n", " loading_indicator=True,\n", ")" ] }, { "cell_type": "code", "execution_count": 46, "id": "228e2b42-b1ed-43af-b923-031a70241ab0", "metadata": { "id": "228e2b42-b1ed-43af-b923-031a70241ab0", "tags": [] }, "outputs": [], "source": [ "output = pn.WidgetBox('*Output will show up here:*', qa_interactive, width=630, scroll=True)" ] }, { "cell_type": "code", "execution_count": 47, "id": "1b0ec253-2bcd-4f91-96d8-d8456e900a58", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "1b0ec253-2bcd-4f91-96d8-d8456e900a58", "outputId": "f7cee6f1-c6a7-438c-ec93-8c41c9fa6665", "tags": [] }, "outputs": [ { "data": { "application/javascript": "(function(root) {\n function now() {\n return new Date();\n }\n\n var force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, js_modules, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n if (js_modules == null) js_modules = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls.length === 0 && js_modules.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error() {\n console.error(\"failed to load \" + url);\n }\n\n for (var i = 0; i < css_urls.length; i++) {\n var url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error;\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n var skip = [];\n if (window.requirejs) {\n window.requirejs.config({'packages': {}, 'paths': {'Quill': 'https://cdn.quilljs.com/1.3.6/quill', 'gridstack': 'https://cdn.jsdelivr.net/npm/gridstack@4.2.5/dist/gridstack-h5', 'notyf': 'https://cdn.jsdelivr.net/npm/notyf@3/notyf.min'}, 'shim': {'gridstack': {'exports': 'GridStack'}}});\n require([\"Quill\"], function(Quill) {\n\twindow.Quill = Quill\n\ton_load()\n })\n require([\"gridstack\"], function(GridStack) {\n\twindow.GridStack = GridStack\n\ton_load()\n })\n require([\"notyf\"], function() {\n\ton_load()\n })\n root._bokeh_is_loading = css_urls.length + 3;\n } else {\n root._bokeh_is_loading = css_urls.length + js_urls.length + js_modules.length;\n } if (((window['Quill'] !== undefined) && (!(window['Quill'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } if (((window['GridStack'] !== undefined) && (!(window['GridStack'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/gridstack/gridstack@4.2.5/dist/gridstack-h5.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } if (((window['Notyf'] !== undefined) && (!(window['Notyf'] instanceof HTMLElement))) || window.requirejs) {\n var urls = ['https://cdn.holoviz.org/panel/0.14.4/dist/bundled/notificationarea/notyf@3/notyf.min.js'];\n for (var i = 0; i < urls.length; i++) {\n skip.push(urls[i])\n }\n } for (var i = 0; i < js_urls.length; i++) {\n var url = js_urls[i];\n if (skip.indexOf(url) >= 0) {\n\tif (!window.requirejs) {\n\t on_load();\n\t}\n\tcontinue;\n }\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n for (var i = 0; i < js_modules.length; i++) {\n var url = js_modules[i];\n if (skip.indexOf(url) >= 0) {\n\tif (!window.requirejs) {\n\t on_load();\n\t}\n\tcontinue;\n }\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n element.type = \"module\";\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n if (!js_urls.length && !js_modules.length) {\n on_load()\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n var js_urls = [\"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-2.4.3.min.js\", \"https://unpkg.com/@holoviz/panel@0.14.4/dist/panel.min.js\"];\n var js_modules = [];\n var css_urls = [\"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.bubble.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/bundled/quillinput/1.3.6/quill.snow.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/widgets.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/alerts.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/markdown.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/card.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/loading.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/dataframe.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/json.css\", \"https://cdn.holoviz.org/panel/0.14.4/dist/css/debugger.css\"];\n var inline_js = [ function(Bokeh) {\n inject_raw_css(\"\\n .bk.pn-loading.arc:before {\\n background-image: url(\\\"data:image/svg+xml;base64,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\\\");\\n background-size: auto calc(min(50%, 400px));\\n }\\n \");\n }, function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {} // ensure no trailing comma for IE\n ];\n\n function run_inline_js() {\n if ((root.Bokeh !== undefined) || (force === true)) {\n for (var i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, js_modules, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));", "application/vnd.holoviews_load.v0+json": "" }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/javascript": "\nif ((window.PyViz === undefined) || (window.PyViz instanceof HTMLElement)) {\n window.PyViz = {comms: {}, comm_status:{}, kernels:{}, receivers: {}, plot_index: []}\n}\n\n\n function JupyterCommManager() {\n }\n\n JupyterCommManager.prototype.register_target = function(plot_id, comm_id, msg_handler) {\n if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n comm_manager.register_target(comm_id, function(comm) {\n comm.on_msg(msg_handler);\n });\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n window.PyViz.kernels[plot_id].registerCommTarget(comm_id, function(comm) {\n comm.onMsg = msg_handler;\n });\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n google.colab.kernel.comms.registerTarget(comm_id, (comm) => {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n console.log(message)\n var content = {data: message.data, comm_id};\n var buffers = []\n for (var buffer of message.buffers || []) {\n buffers.push(new DataView(buffer))\n }\n var metadata = message.metadata || {};\n var msg = {content, buffers, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n })\n }\n }\n\n JupyterCommManager.prototype.get_client_comm = function(plot_id, comm_id, msg_handler) {\n if (comm_id in window.PyViz.comms) {\n return window.PyViz.comms[comm_id];\n } else if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n var comm = comm_manager.new_comm(comm_id, {}, {}, {}, comm_id);\n if (msg_handler) {\n comm.on_msg(msg_handler);\n }\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n var comm = window.PyViz.kernels[plot_id].connectToComm(comm_id);\n comm.open();\n if (msg_handler) {\n comm.onMsg = msg_handler;\n }\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n var comm_promise = google.colab.kernel.comms.open(comm_id)\n comm_promise.then((comm) => {\n window.PyViz.comms[comm_id] = comm;\n if (msg_handler) {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n var content = {data: message.data};\n var metadata = message.metadata || {comm_id};\n var msg = {content, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n }\n }) \n var sendClosure = (data, metadata, buffers, disposeOnDone) => {\n return comm_promise.then((comm) => {\n comm.send(data, metadata, buffers, disposeOnDone);\n });\n };\n var comm = {\n send: sendClosure\n };\n }\n window.PyViz.comms[comm_id] = comm;\n return comm;\n }\n window.PyViz.comm_manager = new JupyterCommManager();\n \n\n\nvar JS_MIME_TYPE = 'application/javascript';\nvar HTML_MIME_TYPE = 'text/html';\nvar EXEC_MIME_TYPE = 'application/vnd.holoviews_exec.v0+json';\nvar CLASS_NAME = 'output';\n\n/**\n * Render data to the DOM node\n */\nfunction render(props, node) {\n var div = document.createElement(\"div\");\n var script = document.createElement(\"script\");\n node.appendChild(div);\n node.appendChild(script);\n}\n\n/**\n * Handle when a new output is added\n */\nfunction handle_add_output(event, handle) {\n var output_area = handle.output_area;\n var output = handle.output;\n if ((output.data == undefined) || (!output.data.hasOwnProperty(EXEC_MIME_TYPE))) {\n return\n }\n var id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n var toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n if (id !== undefined) {\n var nchildren = toinsert.length;\n var html_node = toinsert[nchildren-1].children[0];\n html_node.innerHTML = output.data[HTML_MIME_TYPE];\n var scripts = [];\n var nodelist = html_node.querySelectorAll(\"script\");\n for (var i in nodelist) {\n if (nodelist.hasOwnProperty(i)) {\n scripts.push(nodelist[i])\n }\n }\n\n scripts.forEach( function (oldScript) {\n var newScript = document.createElement(\"script\");\n var attrs = [];\n var nodemap = oldScript.attributes;\n for (var j in nodemap) {\n if (nodemap.hasOwnProperty(j)) {\n attrs.push(nodemap[j])\n }\n }\n attrs.forEach(function(attr) { newScript.setAttribute(attr.name, attr.value) });\n newScript.appendChild(document.createTextNode(oldScript.innerHTML));\n oldScript.parentNode.replaceChild(newScript, oldScript);\n });\n if (JS_MIME_TYPE in output.data) {\n toinsert[nchildren-1].children[1].textContent = output.data[JS_MIME_TYPE];\n }\n output_area._hv_plot_id = id;\n if ((window.Bokeh !== undefined) && (id in Bokeh.index)) {\n window.PyViz.plot_index[id] = Bokeh.index[id];\n } else {\n window.PyViz.plot_index[id] = null;\n }\n } else if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n var bk_div = document.createElement(\"div\");\n bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n var script_attrs = bk_div.children[0].attributes;\n for (var i = 0; i < script_attrs.length; i++) {\n toinsert[toinsert.length - 1].childNodes[1].setAttribute(script_attrs[i].name, script_attrs[i].value);\n }\n // store reference to server id on output_area\n output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n }\n}\n\n/**\n * Handle when an output is cleared or removed\n */\nfunction handle_clear_output(event, handle) {\n var id = handle.cell.output_area._hv_plot_id;\n var server_id = handle.cell.output_area._bokeh_server_id;\n if (((id === undefined) || !(id in PyViz.plot_index)) && (server_id !== undefined)) { return; }\n var comm = window.PyViz.comm_manager.get_client_comm(\"hv-extension-comm\", \"hv-extension-comm\", function () {});\n if (server_id !== null) {\n comm.send({event_type: 'server_delete', 'id': server_id});\n return;\n } else if (comm !== null) {\n comm.send({event_type: 'delete', 'id': id});\n }\n delete PyViz.plot_index[id];\n if ((window.Bokeh !== undefined) & (id in window.Bokeh.index)) {\n var doc = window.Bokeh.index[id].model.document\n doc.clear();\n const i = window.Bokeh.documents.indexOf(doc);\n if (i > -1) {\n window.Bokeh.documents.splice(i, 1);\n }\n }\n}\n\n/**\n * Handle kernel restart event\n */\nfunction handle_kernel_cleanup(event, handle) {\n delete PyViz.comms[\"hv-extension-comm\"];\n window.PyViz.plot_index = {}\n}\n\n/**\n * Handle update_display_data messages\n */\nfunction handle_update_output(event, handle) {\n handle_clear_output(event, {cell: {output_area: handle.output_area}})\n handle_add_output(event, handle)\n}\n\nfunction register_renderer(events, OutputArea) {\n function append_mime(data, metadata, element) {\n // create a DOM node to render to\n var toinsert = this.create_output_subarea(\n metadata,\n CLASS_NAME,\n EXEC_MIME_TYPE\n );\n this.keyboard_manager.register_events(toinsert);\n // Render to node\n var props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n render(props, toinsert[0]);\n element.append(toinsert);\n return toinsert\n }\n\n events.on('output_added.OutputArea', handle_add_output);\n events.on('output_updated.OutputArea', handle_update_output);\n events.on('clear_output.CodeCell', handle_clear_output);\n events.on('delete.Cell', handle_clear_output);\n events.on('kernel_ready.Kernel', handle_kernel_cleanup);\n\n OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n safe: true,\n index: 0\n });\n}\n\nif (window.Jupyter !== undefined) {\n try {\n var events = require('base/js/events');\n var OutputArea = require('notebook/js/outputarea').OutputArea;\n if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n register_renderer(events, OutputArea);\n }\n } catch(err) {\n }\n}\n", "application/vnd.holoviews_load.v0+json": "" }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Beyond the Buzz - Assignment 2
\n", "Rishi Agarwal, Shivam Sharma, Varun Tokas
\n", "May 2023
\n", "1 MNIST Classifier
\n", "You’ll be making a GAN to generate pictures of random digits, which is trained on the MNIST dataset. You
\n", "are allowed to use pytorch, or any other framework you want.
\n", "Here are some instructions to get started-
\n", "•In a file, say models.py, define your Generator and Discriminator models. Keep them simple for this
\n", "task, no more than 2 hidden layers are required. Keep the input and output of the models according
\n", "to how I described today.
\n", "•In another file, say train.py, import the MNIST data using a torchvision library. Before importing,
\n", "also define the transform which normalizes the MNIST data with 0.5 mean and 0.5 std. deviation.
\n", "•After getting the normalized dataset, create two separate Adam optmizers for the Generator and the
\n", "Discriminator with a suitable learning rate.
\n", "•Use the nn.BCELoss as your criterion, read its documentation and think about how you would generate
\n", "the loss functions for the Generator and Discriminator from this.
\n", "•Set up the training loop with a suitable number of epochs.
\n", "For the evaluation, keep a directory with a the images your generator as examples, also document the
\n", "code in the README with the instructions on how it works and how to run it.
\n", "1
\n", "Answer: nn.BCELoss
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.holoviews_exec.v0+json": "", "text/html": [ "
\n", "
\n", "
\n", "" ], "text/plain": [ "Column(sizing_mode='stretch_width')\n", " [0] Markdown(str, sizing_mode='stretch_width')\n", " [1] Row(sizing_mode='stretch_width')\n", " [0] FileInput(width=300)\n", " [2] WidgetBox(scroll=True, width=630)\n", " [0] Markdown(str, sizing_mode='stretch_width')\n", " [1] ParamFunction(function, _pane=Column, loading_indicator=True, sizing_mode='stretch_width')\n", " [3] Row(width=630)\n", " [0] Column(margin=5, sizing_mode='stretch_width')\n", " [0] TextEditor(height=160, placeholder='Enter your questions h..., sizing_mode='stretch_width', toolbar=False)\n", " [1] Button(name='Run', sizing_mode='stretch_width')" ] }, "execution_count": 47, "metadata": { "application/vnd.holoviews_exec.v0+json": { "id": "1146" } }, "output_type": "execute_result" } ], "source": [ "# layout\n", "pn.Column(\n", " pn.pane.Markdown(\"\"\"\n", " Question Answering with your PDF file!\n", "\n", " 1) Upload a PDF. \\n\n", " 2) Type a question and click \"Run\".\n", "\n", " \"\"\"),\n", " pn.Row(file_input),\n", " output,\n", " widgets\n", "\n", ").servable()" ] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "T4", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.10" } }, "nbformat": 4, "nbformat_minor": 5 }