Duplicate from sophiamyang/Panel_PDF_QA

Co-authored-by: Sophia Yang <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+RUN python3 -m pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["panel", "serve", "/code/LangChain_QA_Panel_App.ipynb", "--address", "0.0.0.0", "--port", "7860", "--allow-websocket-origin", "sophiamyang-panel-pdf-qa.hf.space",  "--allow-websocket-origin", "0.0.0.0:7860"]
+
+RUN mkdir /.cache
+RUN chmod 777 /.cache
+RUN mkdir .chroma
+RUN chmod 777 .chroma

LangChain_QA_Panel_App.ipynb

@@ -0,0 +1,255 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "04815d1b-44ee-4bd3-878e-fa0c3bf9fa7f",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# LangChain QA Panel App\n",
+    "\n",
+    "This notebook shows how to make this app:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a181568b-9cde-4a55-a853-4d2a41dbfdad",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#!pip install langchain openai chromadb tiktoken pypdf panel\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a464409-d064-4766-a9cb-5119f6c4b8f5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os \n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "from langchain.document_loaders import PyPDFLoader\n",
+    "from langchain.indexes import VectorstoreIndexCreator\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chroma\n",
+    "import panel as pn\n",
+    "import tempfile\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2d07ea5-9ff2-4c96-a8dc-92895d870b73",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "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": null,
+   "id": "763db4d0-3436-41d3-8b0f-e66ce16468cd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "file_input = pn.widgets.FileInput(width=300)\n",
+    "\n",
+    "openaikey = pn.widgets.PasswordInput(\n",
+    "    value=\"\", placeholder=\"Enter your OpenAI API Key here...\", 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",
+    "select_k = pn.widgets.IntSlider(\n",
+    "    name=\"Number of relevant chunks\", start=1, end=5, step=1, value=2\n",
+    ")\n",
+    "select_chain_type = pn.widgets.RadioButtonGroup(\n",
+    "    name='Chain type', \n",
+    "    options=['stuff', 'map_reduce', \"refine\", \"map_rerank\"]\n",
+    ")\n",
+    "\n",
+    "widgets = pn.Row(\n",
+    "    pn.Column(prompt, run_button, margin=5),\n",
+    "    pn.Card(\n",
+    "        \"Chain type:\",\n",
+    "        pn.Column(select_chain_type, select_k),\n",
+    "        title=\"Advanced settings\", margin=10\n",
+    "    ), width=600\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9b83cc06-3401-498f-8f84-8a98370f3121",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def qa(file, query, chain_type, k):\n",
+    "    # load document\n",
+    "    loader = PyPDFLoader(file)\n",
+    "    documents = loader.load()\n",
+    "    # split the documents into chunks\n",
+    "    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "    texts = text_splitter.split_documents(documents)\n",
+    "    # select which embeddings we want to use\n",
+    "    embeddings = OpenAIEmbeddings()\n",
+    "    # create the vectorestore to use as the index\n",
+    "    db = Chroma.from_documents(texts, embeddings)\n",
+    "    # expose this index in a retriever interface\n",
+    "    retriever = db.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": k})\n",
+    "    # create a chain to answer questions \n",
+    "    qa = RetrievalQA.from_chain_type(\n",
+    "        llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)\n",
+    "    result = qa({\"query\": query})\n",
+    "    print(result['result'])\n",
+    "    return result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2722f43b-daf6-4d17-a842-41203ae9b140",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# result = qa(\"example.pdf\", \"what is the total number of AI publications?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60e1b3d3-c0d2-4260-ae0c-26b03f1b8824",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "convos = []  # store all panel objects in a list\n",
+    "\n",
+    "def qa_result(_):\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = openaikey.value\n",
+    "    \n",
+    "    # save pdf file to 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, chain_type=select_chain_type.value, k=select_k.value)\n",
+    "            convos.extend([\n",
+    "                pn.Row(\n",
+    "                    pn.panel(\"\\U0001F60A\", width=10),\n",
+    "                    prompt_text,\n",
+    "                    width=600\n",
+    "                ),\n",
+    "                pn.Row(\n",
+    "                    pn.panel(\"\\U0001F916\", width=10),\n",
+    "                    pn.Column(\n",
+    "                        result[\"result\"],\n",
+    "                        \"Relevant source text:\",\n",
+    "                        pn.pane.Markdown('\\n--------------------------------------------------------------------\\n'.join(doc.page_content for doc in result[\"source_documents\"]))\n",
+    "                    )\n",
+    "                )\n",
+    "            ])\n",
+    "            #return convos\n",
+    "    return pn.Column(*convos, margin=15, width=575, min_height=400)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3a70857-0b98-4f62-a9c0-b62ca42b474c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa_interactive = pn.panel(\n",
+    "    pn.bind(qa_result, run_button),\n",
+    "    loading_indicator=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "228e2b42-b1ed-43af-b923-031a70241ab0",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "output = pn.WidgetBox('*Output will show up here:*', qa_interactive, width=630, scroll=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1b0ec253-2bcd-4f91-96d8-d8456e900a58",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# layout\n",
+    "pn.Column(\n",
+    "    pn.pane.Markdown(\"\"\"\n",
+    "    ## \\U0001F60A! Question Answering with your PDF file\n",
+    "    \n",
+    "    1) Upload a PDF. 2) Enter OpenAI API key. This costs $. Set up billing at [OpenAI](https://platform.openai.com/account). 3) Type a question and click \"Run\".\n",
+    "    \n",
+    "    \"\"\"),\n",
+    "    pn.Row(file_input,openaikey),\n",
+    "    output,\n",
+    "    widgets\n",
+    "\n",
+    ").servable()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "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
+}

README.md

@@ -0,0 +1,11 @@
+---
+title: Panel PDF QA
+emoji: 📈
+colorFrom: pink
+colorTo: red
+sdk: docker
+pinned: false
+duplicated_from: sophiamyang/Panel_PDF_QA
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+openai
+chromadb
+pypdf
+tiktoken
+panel
+notebook