Spaces:
Sleeping
Sleeping
File size: 6,374 Bytes
e39ab22 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "ylbT549oymIl"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/vasim/Khatir/Programming/ML Projects/gemini-pro with docs/.venv/lib/python3.10/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": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"from langchain.document_loaders import (\n",
" PyPDFLoader,\n",
" TextLoader,\n",
" Docx2txtLoader\n",
")\n",
"\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"# from PyPDF2 import PdfReader\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
"import google.generativeai as genai\n",
"from langchain.vectorstores import FAISS\n",
"from langchain_google_genai import ChatGoogleGenerativeAI\n",
"from langchain.chains.question_answering import load_qa_chain\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.memory import ConversationBufferMemory\n",
"from dotenv import load_dotenv\n",
"load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"os.chdir(\"../\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from src.utils import (\n",
" process_files, answer_query, extract_text_from_file\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"background_save": true
},
"id": "a8tNUutJB9EA"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7862\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7862/\" 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"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Text extracted\n",
"Chunks splitted\n",
"Document search created\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/vasim/Khatir/Programming/ML Projects/gemini-pro with docs/.venv/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
" warn_deprecated(\n"
]
}
],
"source": [
"# Gradio App\n",
"import gradio as gr\n",
"\n",
"gr.close_all()\n",
"\n",
"title = \"\"\n",
"description = f\"Chat with any docs\"\n",
"\n",
"# def answer_query(message, history):\n",
"# docs = db.similarity_search(message)\n",
"# message = agent(\n",
"# {\"input_documents\":docs, \"question\": message}\n",
"# ,return_only_outputs=True)\n",
"# return message['output_text']\n",
"\n",
"\n",
"chatbot = gr.Chatbot(label=\"ExploreText\")\n",
"\n",
"with gr.Blocks(\n",
" title=\"ExploreText\",\n",
" ) as textbot:\n",
"\n",
" gr.Markdown(\"# <center> Welcome to ExploreDoc Web App</center>\")\n",
" \n",
" with gr.Accordion(\"Upload a file here\", open=False):\n",
" file_output = gr.File()\n",
" upload_button = gr.UploadButton(\"Click to Upload a File\", file_types=[\"txt\",\"doc\",\"pdf\"])\n",
" upload_button.upload(process_files, upload_button, file_output)\n",
"\n",
" # with gr.Row(\"Chat with Text\"):\n",
" gr.ChatInterface(fn=answer_query, chatbot=chatbot, submit_btn=\"Ask\", undo_btn=None, retry_btn=None, clear_btn=None)\n",
" gr.Markdown(\"<center> Developed by <a href='https://92-vasim.github.io' target='_blank'>Mohammed Vasim<a/> | AI Engineer & Computer Vision Engineer @ ZestIoT. </center>\")\n",
" \n",
"\n",
"if __name__ == \"__main__\":\n",
" textbot.queue().launch()\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|