File size: 5,627 Bytes
59c3706
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9CrIbR0AK3d1",
        "outputId": "8624a380-d370-43b0-969c-1b21e275b322"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: typing_extensions in /usr/local/lib/python3.10/dist-packages (4.9.0)\n"
          ]
        }
      ],
      "source": [
        "# !pip install openai sentence-transformers\n",
        "# !pip install langchain\n",
        "!pip install typing_extensions\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import openai\n",
        "from langchain_community.document_loaders import TextLoader, PyPDFLoader, CSVLoader, DirectoryLoader\n",
        "from transformers import AutoModel\n",
        "from langchain_community.embeddings.sentence_transformer import (\n",
        "    SentenceTransformerEmbeddings,\n",
        ")\n",
        "from langchain_community.vectorstores import Chroma\n",
        "import torch\n",
        "import json"
      ],
      "metadata": {
        "id": "xOFM83MoLQ-B"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('new_articles')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WMvNDl83M7Xb",
        "outputId": "d59ab804-42ce-4b10-fee6-f01f19d60b38"
      },
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at new_articles; to attempt to forcibly remount, call drive.mount(\"new_articles\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def document_loader(directory):\n",
        "  documents = {}\n",
        "  for filename in os.listdir(directory):\n",
        "    file_path = os.path.join(directory, filename)\n",
        "    if filename.endswith(\".csv\"):\n",
        "      loader = CSVLoader(file_path)\n",
        "    elif filename.endswith(\".pdf\"):\n",
        "      loader = PyPDFLoader(file_path)\n",
        "    elif filename.endswith(\".txt\"):\n",
        "      loader = TextLoader(file_path)\n",
        "    else:\n",
        "      break\n",
        "\n",
        "    document = loader.load()\n",
        "    documents[filename] = document\n",
        "  return (documents)\n"
      ],
      "metadata": {
        "id": "QxVY8IyNL3Zp"
      },
      "execution_count": 54,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "openai.api_key = \"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\"\n",
        "JSON_DATA = []\n",
        "directory = \"/content/new_articles/MyDrive/new_articles\"\n",
        "documents = document_loader(directory)\n",
        "for filename, document in documents.items():\n",
        "    doc = document[0].page_content\n",
        "    # print(filename)\n",
        "    # print(document)\n",
        "    response = openai.chat.completions.create(\n",
        "    model=\"gpt-3.5-turbo\",\n",
        "    messages = [\n",
        "    {\"role\": \"system\", \"content\": f\"Generate one Question, Answer,Reference_Article:(use {filename}), Reference_Text from(use block of text which you've used to generate answer {doc})\"},\n",
        "  ], temperature = 0.3\n",
        "  )\n",
        "    #print(response)\n",
        "    result = response.choices[0].message.content.split(\"\\n\")\n",
        "    # print(result)\n",
        "    json_data = {\n",
        "    \"Question\": result[0].split(\"Question: \")[1].strip() if len(result) > 0 and \"Question:\" in result[0] else \"Not provided\",\n",
        "    \"Answer\": result[2].split(\"Answer: \")[1].strip() if len(result) > 2 and \"Answer:\" in result[2] else \"Not provided\",\n",
        "    \"Reference_article\": result[4].split(\"Reference_article: \")[1].strip() if len(result) > 4 and \"Reference_article:\" in result[4] else \"Not provided\",\n",
        "    \"Reference_text\": result[6].split(\"Reference_text: \")[1].strip() if len(result) > 6 and \"Reference_text:\" in result[6] else \"Not provided\",\n",
        "  }\n",
        "\n",
        "    # print(json_data)\n",
        "\n",
        "    JSON_DATA.append(json_data)\n",
        "\n",
        "with open('question_and_answer_list.json', 'w') as json_file:\n",
        "    json.dump(JSON_DATA, json_file, indent=2)\n",
        "\n",
        "print(\"JSON data saved to question_and_answer_list.json\")\n",
        "\n",
        "print(JSON_DATA)\n"
      ],
      "metadata": {
        "id": "LO9imR5SMA1u"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "eOAr3cy6iA9J"
      },
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "E86P5xBqizsG"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}