{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "75d0658c-fb24-420f-9031-118d0041def9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting PyPDF2\n", " Downloading pypdf2-3.0.1-py3-none-any.whl.metadata (6.8 kB)\n", "Downloading pypdf2-3.0.1-py3-none-any.whl (232 kB)\n", "Installing collected packages: PyPDF2\n", "Successfully installed PyPDF2-3.0.1\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } ], "source": [ "pip install PyPDF2 transformers==4.46.0 faiss-cpu" ] }, { "cell_type": "code", "execution_count": 1, "id": "4cd61927-a7bb-4585-b566-f6dbf5311b90", "metadata": {}, "outputs": [], "source": [ "import os\n", "os.environ[\"KMP_DUPLICATE_LIB_OK\"] = \"TRUE\" # Temporary fix\n", "os.environ[\"FAISS_NO_OPENMP\"] = \"1\" # Prevent FAISS from using OpenMP" ] }, { "cell_type": "code", "execution_count": 2, "id": "55f1b6a7-9dac-4750-80bc-2a56f269673c", "metadata": {}, "outputs": [], "source": [ "from PyPDF2 import PdfReader\n", "from tqdm import tqdm" ] }, { "cell_type": "code", "execution_count": 3, "id": "5f05891d-1467-428d-b837-696a05b4ee73", "metadata": { "scrolled": true }, "outputs": [], "source": [ "path = \"../../volumes/pdfs/2023050195.pdf\"\n", "\n", "pdf_content = PdfReader(path)" ] }, { "cell_type": "code", "execution_count": 4, "id": "f552d64a-006a-47cf-98a2-a859eaeb6c42", "metadata": {}, "outputs": [], "source": [ "def get_pdf_texts(pdf_path):\n", " pdf_text_dict = {}\n", " for page_no, page in enumerate(tqdm(pdf_content.pages), start=1):\n", " text = page.extract_text()\n", " pdf_text_dict[page_no] = text\n", " return pdf_text_dict" ] }, { "cell_type": "code", "execution_count": 5, "id": "bcc8fa60-b3cd-4749-b7d9-0fe794655a28", "metadata": { "scrolled": true }, "outputs": [], "source": [ "# pdf_texts = []\n", "# for page in tqdm(pdf_content.pages):\n", "# text = page.extract_text()\n", "# pdf_texts.append(text)" ] }, { "cell_type": "code", "execution_count": 6, "id": "b79753e3-d19c-4fb9-a7f6-609ce654aaab", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|████████████████████████████████████████████████████████████████████████████████| 404/404 [00:30<00:00, 13.30it/s]\n" ] } ], "source": [ "pdf_text_dict = get_pdf_texts(path)" ] }, { "cell_type": "code", "execution_count": 12, "id": "70bcacf8-5c08-4258-9a2b-4bcbe29d2a00", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "THE CONSTITUTION OF INDIA \n", "(Appendix I) \n", " 368\n", "1 2 3 4 5 6 \n", "43. (i) Chhit Nalgram Sitalkuchi Patgarm 66 49.5 \n", " (ii) Chhit Nalgram \n", "(Fragment) Sitalkuchi Patgarm 66 \n", "44. (i) Batrigachh Dinhata Kaliganj 81 577.37 \n", " (ii) Batrigachh \n", "(Fragment) Dinhata Kaliganj 81 \n", " (iii) Batrigachh \n", "(Fragment) Dinhata Phulbari 9 \n", "45. (i) Karala Dinhata Phulbari 9 269.91 \n", " (ii) Karala (fragment) Dinhata Phulbari 9 \n", " (iii) Karala (fragment) Dinhata Phulbari 8 \n", "46. (i) Sipprasad Mustati Dinhata Phulbari 8 373.2 \n", " (ii) Sipprasad Mustati \n", "(Fragment) Dinhata Phulbari 6 \n", "47. (i) Dakshin \n", "Masaldanga Dinhata Bhurungamari 6 571.38 \n", " (ii) Dakshin \n", "Masaldanga \n", "(Fragment) Dinhata Bhurungamari 6 \n", " (iii) Dakshin \n", "Masaldanga \n", "(Fragment) Dinhata Bhurungamari 6 \n", " (iv) Dakshin \n", "Masaldanga \n", "(Fragment) Dinhata Bhurungamari 6 \n", " (v) Dakshin \n", "Masaldanga \n", "(Fragment) Dinhata Bhurungamari 6 \n", " (vi) Dakshin \n", "Masaldanga \n", "(Fragment) Dinhata Bhurungamari 6 \n" ] } ], "source": [ "print(pdf_text_dict[401])" ] }, { "cell_type": "code", "execution_count": 10, "id": "dd8940af-9978-4b7d-927d-e2f217b1d0fc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\n \\n \\n \\n \\n THE CONSTITUTION OF INDIA \\n[As on May , 2022] \\n2022 \\n '" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pdf_text_dict[1]" ] }, { "cell_type": "code", "execution_count": 11, "id": "801757f0-8321-43cd-99ef-1655acb37e7c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\n \\nPREFACE \\n \\nThis is the fifth pocket size edition of the Constitution of \\nIndia in the diglot form. In this edition, the text of the \\nConstitution of India has been brought up-to-date by \\nincorporating therein all the amendments up to the Constitution \\n(One Hundred and Fifth Amendment) Act, 2021. The foot notes \\nbelow the text indicate the Constitution Amendment Acts by \\nwhich such amendments have been made. \\nThe Constitution (One Hundredth Amendment) Act, 2015 \\ncontaining details of acquired and transferred territories \\nbetween the Governments of India and Bangladesh has been \\nprovided in APPENDIX I. \\nThe Constitution (Application to Jammu and Kashmir) \\nOrder, 2019 and the declaration under article 370(3) of the \\nConstitution have been provided respectively in Appendix II and \\nAppendix III for reference. \\n \\n \\nNew Delhi; Dr. Reeta Vasishta, \\n Secretary to the Government of India. \\n \\n '" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pdf_text_dict[2]" ] }, { "cell_type": "code", "execution_count": 21, "id": "448d302c-4def-4c3a-a707-6d85ebe6f1c9", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "THE CONSTITUTION OF INDIA \n", "(Part XII. —Finance, Property, Contracts and Suits) \n", " 169\n", "Provided that any property which at the date when it would have so \n", "accrued to His Majesty or to the Ruler of an Indian State was in the possession \n", "or under the control of the Government of India or the Government of a State \n", "shall, according as the purposes for which it was then used or held were \n", "purposes of the Union or of a State, vest in the Union or in that State. \n", "Explanation.— In this article, the expressions “Ruler” and “Indian State” \n", "have the same meanings as in article 363. \n", "1[297. Things of value within territorial waters or continental shelf \n", "and resources of the exclusive economic zone to vest in the Union .—(1) All \n", "lands, minerals and other things of value underlying the ocean within the \n", "territorial waters, or the continental shelf, or the exclusive economic zone, of \n", "India shall vest in the Union and be held for the purposes of the Union. \n", "(2) All other resources of the exclusive economic zone of India shall also \n", "vest in the Union and be held for the purposes of the Union. \n", "(3) The limits of the territorial waters, the continental shelf, the exclusive \n", "economic zone, and other maritime zones, of India shall be such as may be \n", "specified, from time to time, by or under any law made by Parliament.] \n", "2[298. Power to carry on trade, etc. —The executive power of the \n", "Union and of each State shall extend to the carrying on of any trade or business \n", "and to the acquisition, holding and disposal of property and the making of \n", "contracts for any purpose: \n", "Provided that— \n", "(a) the said executive power of the Union shall, in so far as such \n", "trade or business or such purpose is not one with respect to which \n", "Parliament may make laws, be subject in each State to legislation by the \n", "State; and \n", "(b) the said executive power of each State shall, in so far as such \n", "trade or business or such purpose is not one with respect to which the \n", "State Legislature may make laws, be subject to legislation by \n", "Parliament.] \n", "______________________________________________ \n", "1. Subs. by the Constitution (Fortieth Amendment) Act, 1976, s. 2 (w.e.f. 27-5-1976). \n", "2. Subs. by the Constitution (Seventh Amendment) Act, 1956, s. 20 (w.e.f. 1-11-1956). \n" ] } ], "source": [ "print(pdf_text_dict[200])" ] }, { "cell_type": "code", "execution_count": null, "id": "74dee5b1-f158-48b4-ae79-0e2aaf54dadd", "metadata": {}, "outputs": [], "source": [ "metadata = {}\n" ] }, { "cell_type": "code", "execution_count": null, "id": "0d3bebdb-38f8-4933-b7a9-87effb9cc4c4", "metadata": {}, "outputs": [], "source": [ "for page_no,text in pdf_text_dict.items()" ] }, { "cell_type": "code", "execution_count": 30, "id": "91aeb2b4-af4f-43d6-bdff-5fa3bbd2e430", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " \n", " \n", " \n", " \n", " \n", " THE CONSTITUTION OF INDIA \n", "[As on May , 2022] \n", "2022 \n", " \n" ] } ], "source": [ "print(pdf_text_dict[1])" ] }, { "cell_type": "code", "execution_count": 31, "id": "4fb24b5d-13f2-4638-ab52-702ee9b6fc5c", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 371APPENDIX III \n", "1DECLRATION UNDER ARTICLE 370(3) OF THE CONSTITUTION \n", "C.O. 273 \n", "In exercise of the powers conferred by clause (3) of article 370 read \n", "with clause (1) of article 370 of the Constitution of India, the President, on the \n", "recommendation of Parliament, is pleased to declare that, as from the 6th \n", "August, 2019, all clauses of the said article 370 shall cease to be operative \n", "except the following which shall read as under, namely :— \n", "“370. All provisions of this Constitution, as amended from time to \n", "time, without any modifications or exceptions, shall apply to the State of \n", "Jammu and Kashmir notwithstanding anything contrary contained in \n", "article 152 or article 308 or any other article of this Constitution or any \n", "other provision of the Constitution of Jammu and Kashmir or any law, \n", "document, judgement, ordinance, order, by-law, rule, regulation, \n", "notification, custom or usage having the force of law in the territory of \n", "India, or any other instrument, treaty or agreement as envisaged under \n", "article 363 or otherwise.”. \n", "______________________________________________ \n", "1.Published with the Ministry of Law and Justice, (Legislative Department) notification \n", "No. G.S.R. 562(E), dated the 6th August, 2019, Gazette of India, Extraordinary, Part II, \n", "Section 3, Sub-section (i). \n" ] } ], "source": [ "print(pdf_text_dict[404])" ] }, { "cell_type": "code", "execution_count": 8, "id": "a58ca47b-8f28-451d-be5d-9756ff9440c9", "metadata": {}, "outputs": [], "source": [ "import numpy as np" ] }, { "cell_type": "code", "execution_count": 9, "id": "fb03fafa-7ea8-473a-818e-0cf3deb0292c", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.9341315\n" ] } ], "source": [ "from transformers import AutoModel\n", "from numpy.linalg import norm\n", "\n", "cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))\n", "model = AutoModel.from_pretrained('../../volumes/models/jina-embeddings-v2-base-en/', trust_remote_code=True) # trust_remote_code is needed to use the encode method\n", "embeddings = model.encode(['How is the weather today?', 'What is the current weather like today?'])\n", "print(cos_sim(embeddings[0], embeddings[1]))" ] }, { "cell_type": "code", "execution_count": 15, "id": "a1e608d8-74bb-41bb-beb8-33766e572c3a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "768" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(embeddings[0])" ] }, { "cell_type": "code", "execution_count": 16, "id": "877bb914-24dd-4775-a354-59dc363e4ee5", "metadata": {}, "outputs": [], "source": [ "def get_embeddings(text:list):\n", " embeddings = model.encode(text)\n", " normalized_embeddings = embeddings/norm(embeddings[0])\n", " return normalized_embeddings" ] }, { "cell_type": "code", "execution_count": 29, "id": "3253b3f3-2861-4663-863a-94e1e5fa4959", "metadata": {}, "outputs": [], "source": [ "def batch_embeddings(texts, batch_size=5):\n", " all_embeddings = []\n", " for i in tqdm(range(0, len(texts), batch_size)):\n", " batch = texts[i:i+batch_size]\n", " embeddings = get_embeddings(batch)\n", " all_embeddings.extend(embeddings.tolist())\n", " return np.array(all_embeddings)" ] }, { "cell_type": "code", "execution_count": 28, "id": "2af58cef-d457-4282-85a6-e158b4c536b4", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:18<00:00, 9.26s/it]\n" ] } ], "source": [ "# res = batch_embeddings(list(pdf_text_dict.values())[0:10], batch_size=5)" ] }, { "cell_type": "code", "execution_count": 31, "id": "c11e61cc-401d-49c3-93a9-79b945ba9ceb", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████████████████████████████████████████| 81/81 [16:37<00:00, 12.31s/it]\n" ] } ], "source": [ "result_embeddings = batch_embeddings(list(pdf_text_dict.values()), batch_size=5)" ] }, { "cell_type": "code", "execution_count": 10, "id": "5103f001-6a77-4381-af8b-22f1e35049ed", "metadata": {}, "outputs": [], "source": [ "# import pickle\n", "\n", "# with open(\"embeddings.pkl\", \"wb\") as p:\n", "# pickle.dump(result_embeddings, p)" ] }, { "cell_type": "code", "execution_count": 24, "id": "0fd12d04-9ed7-4909-95d9-852c016bdfa7", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "[' \\n \\n \\n \\n \\n THE CONSTITUTION OF INDIA \\n[As on May , 2022] \\n2022 \\n ',\n", " ' \\n \\nPREFACE \\n \\nThis is the fifth pocket size edition of the Constitution of \\nIndia in the diglot form. In this edition, the text of the \\nConstitution of India has been brought up-to-date by \\nincorporating therein all the amendments up to the Constitution \\n(One Hundred and Fifth Amendment) Act, 2021. The foot notes \\nbelow the text indicate the Constitution Amendment Acts by \\nwhich such amendments have been made. \\nThe Constitution (One Hundredth Amendment) Act, 2015 \\ncontaining details of acquired and transferred territories \\nbetween the Governments of India and Bangladesh has been \\nprovided in APPENDIX I. \\nThe Constitution (Application to Jammu and Kashmir) \\nOrder, 2019 and the declaration under article 370(3) of the \\nConstitution have been provided respectively in Appendix II and \\nAppendix III for reference. \\n \\n \\nNew Delhi; Dr. Reeta Vasishta, \\n Secretary to the Government of India. \\n \\n ',\n", " ' \\nLIST OF ABBREVIATIONS USED \\n \\n \\nArt., arts. ........................................................ for Article, articles. \\nCl., cls. ........................................................ ″ Clause, clauses. \\nC.O. ........................................................ ″ Constitution Order. \\nIns. ........................................................ ″ Inserted. \\nP., pp. ........................................................ ″ Page, pages. \\nPt. ........................................................ ″ Part. \\nRep. ........................................................ ″ Repealed. \\nSs., ss. .......................................................... ″ Section, sections. \\nSch. ......................................................... ″ Schedule. \\nSubs. ........................................................ ″ Substituted. \\nw.e.f. ......................................................... ″ with effect from. \\nw.r.e.f. ...................................................... ″ with retrospective effect \\nfrom. \\n ',\n", " 'THE CONSTITUTION OF INDIA \\n____________ \\n \\nCONTENTS \\n__________ \\n \\n \\nPREAMBLE \\nPART I \\nTHE UNION AND ITS TERRITORY \\nARTICLES \\n 1. Name and territory of the Union. \\n 2. Admission or establishment of new States. \\n[2A. Sikkim to be associated with the Union. —Omitted.] \\n 3. Formation of new States and alteration of areas, boundaries or \\nnames of existing States. \\n 4. Laws made under articles 2 and 3 to provide for the amendment of \\nthe First and the Fourth Schedules and supplemental, incidental \\nand consequential matters. \\nPART II \\nCITIZENSHIP \\n 5. Citizenship at the commencement of the Constitution. \\n6. Rights of citizenship of certain persons who have migrated to \\nIndia from Pakistan. \\n 7. Rights of citizenship of certain migrants to Pakistan. \\n8. Rights of citizenship of certain persons of Indian origin residing \\noutside India. \\n9. Persons voluntarily acquiring citizenship of a foreign State not to \\nbe citizens. \\n10. Continuance of the rights of citizenship. \\n11. Parliament to regulate the right of citizenship by law. ',\n", " 'Contents \\n \\n ARTICLES (ii)\\nPART III \\nFUNDAMENTAL RIGHTS \\nGeneral \\n12. Definition. \\n13. Laws inconsistent with or in derogation of the fundamental \\nrights. \\n Right to Equality \\n14. Equality before law. \\n15. Prohibition of discrimination on grounds of religion, race, caste, \\nsex or place of birth. \\n16. Equality of opportunity in matters of public employment. \\n17. Abolition of Untouchability. \\n18. Abolition of titles. \\n Right to Freedom \\n19. Protection of certain rights regarding freedom of speech, etc. \\n20. Protection in respect of conviction for offences. \\n21. Protection of life and personal liberty. \\n21A. Right to education. \\n22. Protection against arrest and detention in certain cases. \\n Right against Exploitation \\n23. Prohibition of traffic in human beings and forced labour. \\n24. Prohibition of employment of children in factories, etc. \\n Right to Freedom of Religion \\n25. Freedom of conscience and free profession, practice and \\npropagation of religion. \\n26. Freedom to manage religious affairs. \\n27. Freedom as to payment of taxes for promotion of any particular \\nreligion. \\n28. Freedom as to attendance at religious instruction or religious \\nworship in certain educational institutions. ',\n", " 'Contents \\n \\n ARTICLES (iii) \\n Cultural and Educational Rights \\n29. Protection of interests of minorities. \\n30. Right of minorities to establish and administer educational \\ninstitutions. \\n[31. Compulsory acquisition of property . —Omitted.] \\n Saving of Certain Laws \\n31A. Saving of Laws providing for acquisition of estates, etc. \\n31B. Validation of certain Acts and Regulations. \\n31C. Saving of laws giving effect to certain directive principles. \\n[31D. Saving of laws in respect of anti-national activities. —Omitted.] \\n Right to Constitutional Remedies \\n 32. Remedies for enforcement of rights conferred by this Part. \\n[32A. Constitutional validity of State laws not to be considered in \\nproceedings under article 32. —Omitted.] \\n 33. Power of Parliament to modify the rights conferred by this Part \\nin their application to Forces, etc. \\n 34. Restriction on rights conferred by this Part while martial law is \\nin force in any area. \\n 35. Legislation to give effect to the provisions of this Part. \\n PART IV \\nDIRECTIVE PRINCIPLES OF STATE POLICY \\n 36. Definition. \\n 37. Application of the principles contained in this Part. \\n38. State to secure a social order for the promotion of welfare of the \\npeople. \\n 39. Certain principles of policy to be followed by the State. \\n39A. Equal justice and free legal aid. ',\n", " 'Contents \\n \\n ARTICLES (iv)\\n 40. Organisation of village panchayats. \\n 41. Right to work, to education and to public assistance in certain \\ncases. \\n 42. Provision for just and humane conditions of work and maternity \\nrelief. \\n 43. Living wage, etc., for workers. \\n43A. Participation of workers in management of Industries. \\n43B. Promotion of co-operative societies. \\n 44. Uniform civil code for the citizens. \\n 45. Provision for early childhood care and educat ion to children \\nbelow the age of six years. \\n 46. Promotion of educational and economic interests of Scheduled \\nCastes, Scheduled Tribes and other weaker sections. \\n 47. Duty of the State to raise the level of nutrition and the standard \\nof living and to improve public health. \\n 48. Organisation of agriculture and animal husbandry. \\n48A. Protection and improvement of environment and safeguarding of \\nforests and wild life. \\n 49. Protection of monuments and places and objects of national \\nimportance. \\n 50. Separation of judiciary from executive. \\n 51. Promotion of international peace and security. \\n PART IVA \\nFUNDAMENTAL DUTIES \\n51A. Fundamental duties. \\n \\n \\n \\n \\n PART V \\nTHE UNION \\nCHAPTER I.\\uf0beTHE EXECUTIVE \\nThe President and Vice-President \\n52. The President of India. \\n53. Executive power of the Union. \\n54. Election of President. ',\n", " 'Contents \\n \\n ARTICLES (v) \\n55. Manner of election of President. \\n56. Term of office of President. \\n57. Eligibility for re-election. \\n58. Qualifications for election as President. \\n59. Conditions of President’s office. \\n60. Oath or affirmation by the President. \\n61. Procedure for impeachment of the President. \\n62. Time of holding election to fill vacancy in the office of President \\nand the term of office of person elected to fill casual vacancy. \\n63. The Vice-President of India. \\n64. The Vice-President to be ex officio Chairman of the Council of \\nStates. \\n65. The Vice-President to act as President or to discharge his \\nfunctions during casual vacancies in the office, or during the \\nabsence, of President. \\n66. Election of Vice-President. \\n67. Term of office of Vice-President. \\n68. Time of holding election to fill vacancy in the office of Vice-President \\nand the term of office of person elected to fill casual vacancy. \\n69. Oath or affirmation by the Vice-President. \\n70. Discharge of President’s functions in other contingencies. \\n71. Matters relating to, or connected with, the election of a President \\nor Vice-President. \\n72. Power of President to grant pardons, etc., and to suspend, remit \\nor commute sentences in certain cases. \\n73. Extent of executive power of the Union. \\n Council of Ministers \\n74. Council of Ministers to aid and advise President . \\n75. Other provisions as to Ministers. \\n The Attorney-General for India \\n76. Attorney-General for India. ',\n", " 'Contents \\n \\n ARTICLES (vi)\\n Conduct of Government Business \\n77. Conduct of business of the Government of India. \\n78. Duties of Prime Minister as respects the furnishing of \\ninformation to the President, etc. \\n CHAPTER II. \\uf0bePARLIAMENT \\nGeneral \\n79. Constitution of Parliament. \\n80. Composition of the Council of States. \\n81. Composition of the House of the People. \\n82. Readjustment after each census. \\n83. Duration of Houses of Parliament. \\n84. Qualification for membership of Parliament. \\n85. Sessions of Parliament, prorogation and dissolution. \\n86. Right of President to address and send messages to Houses. \\n87. Special address by the President. \\n88. Rights of Ministers and Attorney-General as respects Houses. \\n \\nOfficers of Parliament \\n89. The Chairman and Deputy Chairman of the Council of States. \\n90. Vacation and resignation of, and removal from, the office of \\nDeputy Chairman. \\n91. Power of the Deputy Chairman or other person to perform the \\nduties of the office of, or to act as, Chairman. \\n92. The Chairman or the Deputy Chairman not to preside while a \\nresolution for his removal from office is under consideration. \\n93. The Speaker and Deputy Speaker of the House of the People. \\n94. Vacation and resignation of, and removal from, the offices of \\nSpeaker and Deputy Speaker. \\n95. Power of the Deputy Speaker or other person to perform the \\nduties of the office of, or to act as, Speaker. ',\n", " 'Contents \\n \\n ARTICLES (vii)\\n96. The Speaker or the Deputy Speaker not to preside while a \\nresolution for his removal from office is under consideration. \\n97. Salaries and allowances of the Chairman and Deputy Chairman \\nand the Speaker and Deputy Speaker. \\n98. Secretariat of Parliament. \\n \\nConduct of Business \\n 99. Oath or affirmation by members. \\n100. Voting in Houses, power of Houses to act notwithstanding \\nvacancies and quorum. \\n \\nDisqualifications of Members \\n101. Vacation of seats. \\n102. Disqualifications for membership. \\n103. Decision on questions as to disqualifications of members. \\n104. Penalty for sitting and voting before making oath or affirmation \\nunder article 99 or when not qualified or when disqualified. \\n \\nPowers, Privileges and Immunities of Parliament and its \\nMembers \\n105. Powers, privileges, etc., of the Houses of Parliament and of the \\nmembers and committees thereof. \\n106. Salaries and allowances of members. \\n Legislative Procedure \\n107. Provisions as to introduction and passing of Bills. \\n108. Joint sitting of both Houses in certain cases. \\n109. Special procedure in respect of Money Bills. \\n110. Definition of “Money Bills”. \\n111. Assent to Bills. \\n Procedure in Financial Matters \\n112. Annual financial statement. \\n113. Procedure in Parliament with respect to estimates. \\n114. Appropriation Bills. ']" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10]" ] }, { "cell_type": "code", "execution_count": 25, "id": "1f63bb3a-c198-4c8a-8738-51eaba6e7de1", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\n \\nPREFACE \\n \\nThis is the fifth pocket size edition of the Constitution of \\nIndia in the diglot form. In this edition, the text of the \\nConstitution of India has been brought up-to-date by \\nincorporating therein all the amendments up to the Constitution \\n(One Hundred and Fifth Amendment) Act, 2021. The foot notes \\nbelow the text indicate the Constitution Amendment Acts by \\nwhich such amendments have been made. \\nThe Constitution (One Hundredth Amendment) Act, 2015 \\ncontaining details of acquired and transferred territories \\nbetween the Governments of India and Bangladesh has been \\nprovided in APPENDIX I. \\nThe Constitution (Application to Jammu and Kashmir) \\nOrder, 2019 and the declaration under article 370(3) of the \\nConstitution have been provided respectively in Appendix II and \\nAppendix III for reference. \\n \\n \\nNew Delhi; Dr. Reeta Vasishta, \\n Secretary to the Government of India. \\n \\n '" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][1]" ] }, { "cell_type": "code", "execution_count": 26, "id": "f1cdcbf2-89b4-4310-b255-824beda23ed7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'THE CONSTITUTION OF INDIA \\n____________ \\n \\nCONTENTS \\n__________ \\n \\n \\nPREAMBLE \\nPART I \\nTHE UNION AND ITS TERRITORY \\nARTICLES \\n 1. Name and territory of the Union. \\n 2. Admission or establishment of new States. \\n[2A. Sikkim to be associated with the Union. —Omitted.] \\n 3. Formation of new States and alteration of areas, boundaries or \\nnames of existing States. \\n 4. Laws made under articles 2 and 3 to provide for the amendment of \\nthe First and the Fourth Schedules and supplemental, incidental \\nand consequential matters. \\nPART II \\nCITIZENSHIP \\n 5. Citizenship at the commencement of the Constitution. \\n6. Rights of citizenship of certain persons who have migrated to \\nIndia from Pakistan. \\n 7. Rights of citizenship of certain migrants to Pakistan. \\n8. Rights of citizenship of certain persons of Indian origin residing \\noutside India. \\n9. Persons voluntarily acquiring citizenship of a foreign State not to \\nbe citizens. \\n10. Continuance of the rights of citizenship. \\n11. Parliament to regulate the right of citizenship by law. '" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][3]" ] }, { "cell_type": "code", "execution_count": null, "id": "dd1c8671-d49c-4b0f-8227-7e464f632baf", "metadata": { "scrolled": true }, "outputs": [], "source": [ "res" ] }, { "cell_type": "code", "execution_count": 11, "id": "2b991749-1219-447b-94eb-0dce9ceb9ce4", "metadata": {}, "outputs": [], "source": [ "import pickle\n", "\n", "with open(\"embeddings.pkl\", \"rb\") as p:\n", " embeddings = pickle.load(p)" ] }, { "cell_type": "code", "execution_count": 12, "id": "79cdf6e5-e226-425e-b436-f724a62e5116", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([-2.57174131e-02, -4.15116362e-03, 1.00257555e-02, 7.95926899e-02,\n", " -5.00002429e-02, -3.94614115e-02, 1.33040652e-03, 2.53507891e-03,\n", " 3.81039083e-02, 6.45715967e-02, -3.22419666e-02, 2.89166835e-03,\n", " -4.41535637e-02, 6.61504979e-04, -5.27535751e-02, 3.93252261e-02,\n", " 2.10104175e-02, 7.21139321e-03, -1.50410482e-03, 1.66766183e-03,\n", " -2.18644273e-02, 1.02400398e-02, -3.55437882e-02, -2.15868000e-03,\n", " 2.28184578e-03, 1.63813438e-02, 1.12895691e-03, 7.70135522e-02,\n", " 3.45573463e-02, 2.44991146e-02, -2.00111717e-02, 6.72883913e-03,\n", " -2.55250596e-02, -5.63424500e-03, -7.87753426e-03, -3.85418697e-03,\n", " -2.48634145e-02, -7.07174744e-03, 3.84833887e-02, 3.21004912e-02,\n", " -2.16781627e-04, -2.28117988e-03, 1.99199300e-02, 4.85927574e-02,\n", " -4.08204794e-02, 2.73830462e-02, -1.26146292e-02, -7.49849342e-03,\n", " -4.45639668e-03, 1.89360857e-04, -2.24946439e-03, -3.31600965e-03,\n", " -1.60166472e-02, -4.04273309e-02, -1.43064400e-02, 7.14589376e-03,\n", " 5.04611582e-02, 2.84321122e-02, -3.95181105e-02, -8.68732517e-04,\n", " -2.38176603e-02, 2.31797881e-02, 3.92579325e-02, 4.16808613e-02,\n", " 3.38643230e-02, 1.28792981e-02, 9.27819684e-03, -7.97275975e-02,\n", " -3.62305865e-02, 2.44509690e-02, 2.51307455e-03, 4.34498712e-02,\n", " 1.60570405e-02, -1.33092497e-02, -9.81435552e-03, 5.10461740e-02,\n", " -3.22855450e-02, -1.40512027e-02, -7.44149759e-02, -1.59587599e-02,\n", " 2.51831021e-02, 1.58212669e-02, 4.97941598e-02, -3.26568261e-02,\n", " -2.20435690e-02, 2.86261998e-02, -2.31538024e-02, -1.90641768e-02,\n", " 4.00074311e-02, -1.61560122e-02, -3.14329937e-02, 6.27738088e-02,\n", " -2.24409103e-02, 3.14719267e-02, 2.86239833e-02, 2.29620934e-02,\n", " 1.44532863e-02, -5.51838502e-02, -2.88846418e-02, -4.62175580e-03,\n", " 1.42100332e-02, 5.03641441e-02, -1.44368866e-02, 1.35967033e-02,\n", " -1.18015390e-02, 2.06576474e-03, 1.52302766e-02, -2.91087516e-02,\n", " -1.70847271e-02, 5.28466376e-03, -4.24599834e-02, -5.27886814e-03,\n", " 3.86601617e-03, -4.36887257e-02, -1.96105447e-02, -3.98451649e-02,\n", " -8.91261175e-03, -1.73474178e-02, 9.97464289e-04, 2.16768160e-02,\n", " -3.74223106e-02, 4.30773124e-02, 1.28850238e-02, -9.29087326e-02,\n", " 1.92922913e-02, 4.35058624e-02, 1.49308136e-02, 1.14250602e-03,\n", " -2.46660896e-02, -5.55287255e-03, 3.18912715e-02, -2.60299258e-02,\n", " 8.21265057e-02, -3.20272557e-02, -4.86789122e-02, 1.06412657e-02,\n", " 3.98511738e-02, 1.11424178e-02, -9.69936256e-04, 6.70285448e-02,\n", " -2.38062274e-02, -6.55766157e-03, 1.78289581e-02, -4.01245579e-02,\n", " 2.62775505e-03, 3.77939045e-02, -4.85070348e-02, -2.35254504e-02,\n", " -3.50936875e-02, 1.93835108e-03, 3.82161736e-02, -8.27286094e-02,\n", " -2.75273547e-02, 3.61397304e-02, -2.14401968e-02, -4.95456764e-03,\n", " -4.97811707e-04, -2.23175157e-03, 1.15858512e-02, 2.71322229e-03,\n", " -2.63919011e-02, -1.70119721e-02, -2.30862983e-02, -4.39894572e-02,\n", " 8.27744696e-03, 8.56813118e-02, 5.17081209e-02, 1.51095930e-02,\n", " 1.18505927e-02, -6.92560226e-02, 2.08177138e-02, -2.48438437e-02,\n", " -5.57903796e-02, 1.35288127e-02, 9.48630273e-03, 3.01143415e-02,\n", " -2.14476660e-02, 6.19690605e-02, -6.08530045e-02, 3.01848315e-02,\n", " -3.79563421e-02, 8.09773356e-02, 2.98364609e-02, 3.11936922e-02,\n", " 8.36985186e-02, -1.94082968e-02, 3.28132696e-02, -1.39129777e-02,\n", " 3.52161825e-02, 1.45578096e-02, -8.08469858e-03, -4.15643305e-02,\n", " -6.27987692e-03, 3.87079939e-02, 4.05535921e-02, 2.17505591e-03,\n", " 4.16704677e-02, -1.85360219e-02, -6.13073297e-02, 4.11122628e-02,\n", " -2.94521283e-02, 2.53554173e-02, -4.13463509e-04, 1.24392090e-02,\n", " 5.10037597e-03, -8.75441432e-02, -3.35522071e-02, -3.55749391e-02,\n", " -3.74199525e-02, 3.92984822e-02, -1.36980480e-02, 3.84706073e-02,\n", " -4.34904322e-02, 3.40716764e-02, -4.10234183e-02, -1.77299529e-02,\n", " 1.07169664e-02, 7.71508552e-03, -1.33038471e-02, 4.69463877e-02,\n", " 1.00914231e-02, -1.03330135e-01, -4.46362644e-02, -1.52932955e-02,\n", " -6.22913288e-03, -3.76083292e-02, 9.37229581e-03, -1.44105330e-02,\n", " 1.81969441e-02, 5.68255000e-02, -3.81160788e-02, 4.99916263e-02,\n", " 3.55331115e-02, -5.53132333e-02, 4.30908613e-02, -8.75021890e-03,\n", " 3.62314880e-02, -5.99500723e-02, -2.00973544e-02, -4.23832871e-02,\n", " 1.48631181e-04, -3.31453537e-03, 4.87194513e-04, 6.86692726e-03,\n", " -4.33841534e-02, -4.10430506e-02, 5.04185893e-02, -4.39018644e-02,\n", " 4.79511991e-02, 7.12994207e-03, -1.65666137e-02, -1.23005453e-03,\n", " -3.21396142e-02, -1.26902126e-02, 6.85491562e-02, 1.83431469e-02,\n", " -4.26707454e-02, 4.98602390e-02, 8.39052871e-02, -9.85294953e-03,\n", " 8.00013989e-02, -4.78869081e-02, 1.33880717e-03, -2.08081026e-03,\n", " 1.29001196e-02, -5.54729849e-02, -2.85176355e-02, 2.61613596e-02,\n", " -4.12822664e-02, 1.80716123e-02, 1.55945877e-02, -1.89834833e-02,\n", " -3.57164219e-02, -1.74036268e-02, -3.76872998e-03, 2.76176017e-02,\n", " -1.64445620e-02, 4.80964892e-02, 5.67719936e-02, 2.63716877e-02,\n", " -3.05653866e-02, -7.99957588e-02, 2.77207308e-02, 8.93560424e-03,\n", " -2.45386343e-02, 4.97584045e-02, -8.40527117e-02, -3.09794471e-02,\n", " -5.38634509e-03, 7.81132886e-03, -8.46644025e-03, -3.17460448e-02,\n", " 8.91395062e-02, -8.24773312e-03, 2.08232916e-04, -3.84259224e-02,\n", " -2.60309372e-02, -2.58680284e-02, -9.59970336e-03, 2.90000089e-03,\n", " 4.20159735e-02, -4.92865033e-03, -9.60522983e-03, -3.23424898e-02,\n", " 3.46885994e-02, 4.42737192e-02, -9.42309201e-03, 6.07546279e-03,\n", " -2.04809848e-03, -1.51178017e-02, 2.23173369e-02, -3.20781916e-02,\n", " 1.50055997e-02, -2.52247248e-02, 1.61739476e-02, -4.06084396e-02,\n", " -2.92415190e-02, 3.84871215e-02, -1.96853466e-02, -1.38590904e-02,\n", " 6.11174777e-02, 4.71853018e-02, 1.21613629e-02, 3.03259287e-02,\n", " 8.15545693e-02, -2.39564423e-02, 2.26027034e-02, -7.38728466e-03,\n", " 2.18835250e-02, -3.52734514e-02, -6.87112138e-02, -5.37812039e-02,\n", " 4.49983263e-03, -5.48941791e-02, 2.35720444e-02, 2.43920870e-02,\n", " 2.60311761e-03, -3.54177244e-02, 2.39417087e-02, -3.02902274e-02,\n", " 7.50474110e-02, 2.58429758e-02, 2.00601593e-02, 3.20557528e-03,\n", " -3.02898772e-02, 1.30107952e-02, -5.12817642e-03, -3.27567197e-03,\n", " -1.83725245e-02, 8.14397857e-02, -1.26546798e-02, 2.06452329e-02,\n", " 4.48793452e-03, 5.35670370e-02, 1.71370078e-02, -1.42205236e-02,\n", " 9.90118086e-03, 3.87974083e-02, -1.12237856e-02, -9.28443745e-02,\n", " -1.61213917e-03, 5.09403422e-02, -4.10091691e-02, -2.40587331e-02,\n", " -1.67168677e-02, -8.25436227e-03, 3.00410315e-02, -3.02776904e-03,\n", " -6.56920895e-02, 1.08523667e-02, -6.01664782e-02, 3.51346321e-02,\n", " 8.31364654e-03, -2.93967668e-02, -1.29347006e-02, -3.68301757e-02,\n", " 1.74103808e-02, 8.80057830e-03, -1.67999063e-02, -1.05452416e-02,\n", " -5.53115830e-02, 1.77454613e-02, -3.31044979e-02, -1.02671804e-02,\n", " 9.23486054e-03, 4.48897704e-02, -1.33571625e-02, -4.63784002e-02,\n", " 1.67843532e-02, 4.34448905e-02, -1.48189804e-02, -3.10456082e-02,\n", " 1.77916475e-02, -4.07658145e-02, -9.48902499e-03, 5.06357923e-02,\n", " -6.29982799e-02, -2.20906939e-02, -5.56349345e-02, -5.76249603e-03,\n", " 3.26409154e-02, 1.10303722e-02, 6.41335547e-02, 4.63621244e-02,\n", " -1.44787664e-02, 2.85407621e-02, 3.85229960e-02, -1.58771165e-02,\n", " 5.23128211e-02, 3.16371135e-02, -1.93770379e-02, -8.31151009e-02,\n", " 5.96538857e-02, 1.69710200e-02, -4.47052941e-02, 2.95169409e-02,\n", " 9.96101741e-03, -7.08143264e-02, -6.08333163e-02, 5.24643855e-03,\n", " -8.67547188e-03, -1.98073518e-02, -7.10181892e-03, -4.82533732e-03,\n", " -3.42210606e-02, -6.62091821e-02, 6.86643529e-04, -3.11605888e-03,\n", " -1.88093930e-02, -4.54276763e-02, 1.66178774e-02, -9.24200937e-03,\n", " 5.04363403e-02, -2.69100834e-02, 1.21640610e-02, -3.79910320e-02,\n", " 4.61157598e-02, 4.98860776e-02, 5.40914945e-02, -9.12549496e-02,\n", " -4.24579270e-02, 1.80577394e-02, 6.82970416e-03, -4.85470816e-02,\n", " -1.51658859e-02, 1.06326202e-02, 4.70561199e-02, 3.62257920e-02,\n", " 6.07605278e-02, 5.40268002e-03, 5.89498058e-02, -6.06387146e-02,\n", " 6.58009201e-02, -4.02346766e-03, -5.90549521e-02, 4.66582738e-02,\n", " -2.19727624e-02, 7.63568701e-03, 3.38551775e-02, 2.51118299e-02,\n", " 1.67633239e-02, -7.57379690e-03, -4.53396402e-02, -4.55261953e-02,\n", " -1.29767805e-02, -1.11939721e-02, 4.74229865e-02, -7.96682760e-03,\n", " 3.46547738e-02, -1.56249227e-02, 1.14434976e-02, -4.08555977e-02,\n", " -3.93327847e-02, 8.71347077e-03, 3.25198402e-03, 7.20789796e-03,\n", " -7.07184970e-02, 3.26750567e-03, -5.97659089e-02, 1.86769310e-02,\n", " 3.20646800e-02, 4.63991277e-02, 1.44933881e-02, 2.05616876e-02,\n", " -1.46729602e-02, 1.35006113e-02, 8.28524530e-02, 9.23626348e-02,\n", " -3.67087424e-02, 2.18051486e-02, -4.95869573e-03, -4.41479124e-02,\n", " 4.56103496e-03, 2.42516212e-02, 3.94829694e-05, -3.40070799e-02,\n", " -5.38958097e-03, -1.73496694e-04, -2.03436632e-02, -3.21606882e-02,\n", " 1.34499352e-02, 8.02154373e-03, -4.59527895e-02, -7.22823888e-02,\n", " -5.73416986e-03, -2.32819538e-03, 4.25096639e-02, 2.81084422e-02,\n", " 1.47780245e-02, -1.10051595e-03, -4.70580086e-02, 3.06684598e-02,\n", " 8.43891781e-03, -2.89724376e-02, 1.08889192e-02, 7.62799010e-02,\n", " 2.24546399e-02, -3.25210132e-02, 3.03014088e-02, -3.91665846e-03,\n", " -6.56410307e-02, 1.23865018e-02, 1.15141831e-02, 2.53073722e-02,\n", " -2.65552849e-03, -6.67901114e-02, 2.30800137e-02, -8.01113620e-03,\n", " 1.19577367e-02, 2.12651268e-02, 1.04740600e-03, -1.57829765e-02,\n", " -2.08491273e-03, -5.95473126e-02, -3.47732790e-02, 1.22981109e-02,\n", " 1.06721595e-02, 5.90330996e-02, -3.01389974e-02, 1.69376973e-02,\n", " -7.87201058e-03, 3.82638760e-02, 5.33554703e-03, 3.59303206e-02,\n", " 1.50646353e-02, 8.82404968e-02, -4.65183333e-02, 3.05422116e-02,\n", " 4.39457074e-02, -5.40589988e-02, -1.60491653e-02, -2.80300882e-02,\n", " 2.44697258e-02, -6.21494614e-02, 2.62990221e-02, 8.80372524e-03,\n", " 9.02920403e-03, 3.54958400e-02, -4.17020507e-02, -4.02663983e-02,\n", " 6.77801222e-02, -9.44017246e-03, -3.44885662e-02, 2.63255667e-02,\n", " 5.52932220e-03, -5.72426198e-03, 7.46076088e-03, -1.47854602e-02,\n", " 5.22899702e-02, 7.51394406e-02, 2.11022329e-03, -7.83296824e-02,\n", " -3.88271809e-02, -4.65840399e-02, -5.72163835e-02, 1.18325837e-02,\n", " -4.14816551e-02, 7.46720955e-02, 3.25940140e-02, -7.07084639e-03,\n", " 4.13522497e-02, 5.33461533e-02, -6.85378956e-03, 9.63330083e-03,\n", " 4.37391847e-02, 6.41110018e-02, 2.76977010e-02, -3.89026180e-02,\n", " 5.68633787e-02, -1.25569738e-02, 4.32890141e-03, 4.29894067e-02,\n", " 6.14441372e-03, 4.32663560e-02, 6.76224083e-02, -4.22291160e-02,\n", " -3.15231234e-02, 5.72597347e-02, -3.88096273e-02, 3.39227952e-02,\n", " -1.68800971e-03, -1.19756786e-02, -1.84470788e-02, -3.40366624e-02,\n", " -3.03276237e-02, 6.45805225e-02, -7.87456334e-03, 7.89515488e-03,\n", " -8.29922035e-03, -1.41582796e-02, 9.94283613e-03, 6.83671907e-02,\n", " -4.33024317e-02, 5.03238551e-02, -3.11147328e-03, -3.53818089e-02,\n", " 2.36095767e-02, -1.79082900e-02, 1.64668970e-02, -2.64172014e-02,\n", " -1.39206424e-02, 4.88296337e-03, 3.47088277e-02, -1.21132974e-02,\n", " -5.42478561e-02, 7.91907087e-02, -2.03914233e-02, -5.02970181e-02,\n", " -2.03962289e-02, 1.12735834e-02, -3.91431823e-02, -2.02119183e-02,\n", " -3.52542824e-03, -2.08407342e-02, 1.86249875e-02, -2.87201889e-02,\n", " -4.62423488e-02, 1.41155329e-02, -2.84677390e-02, 1.18444616e-03,\n", " 8.76411889e-03, 1.97428302e-03, 2.39373022e-03, 4.31706980e-02,\n", " 2.09482647e-02, 4.27652290e-03, 3.41798700e-02, -3.92067693e-02,\n", " 4.06869762e-02, -2.80282907e-02, -3.85007784e-02, -6.52883723e-02,\n", " 3.35024223e-02, -1.93925053e-02, -1.04146181e-02, 2.92182397e-02,\n", " 8.47155750e-02, 5.39435931e-02, -3.32224853e-02, 3.28501128e-02,\n", " -6.44694269e-02, 1.86609123e-02, -1.22591788e-02, 9.73810554e-02,\n", " -6.55089542e-02, -3.54052931e-02, 5.99990450e-02, -4.45059650e-02,\n", " -3.33516859e-02, 2.47762445e-02, -3.01544312e-02, -1.36626391e-02,\n", " 5.10358959e-02, 4.19272594e-02, 1.67654604e-02, 1.54359555e-02,\n", " 1.70950014e-02, -4.47353302e-03, -3.86933144e-03, 6.19440805e-03,\n", " 4.24543545e-02, -5.20833442e-03, 4.19983380e-02, -1.19898049e-02,\n", " 2.92801261e-02, -3.96090709e-02, -4.55748364e-02, -1.51574863e-02,\n", " -7.18237534e-02, 1.37063820e-04, -1.96622610e-02, -1.96936242e-02,\n", " 6.50710836e-02, 5.05920760e-02, -8.20037127e-02, -2.24901978e-02,\n", " -1.91803798e-02, -2.80492386e-04, 4.05936167e-02, 1.58536131e-03,\n", " 3.94752398e-02, 7.44592212e-03, -6.67359754e-02, -2.67490977e-03,\n", " 3.05636209e-02, 2.60310457e-03, 2.86192051e-03, -3.07924058e-02,\n", " -3.34362201e-02, 6.22385554e-03, 3.61801460e-02, 3.96534726e-02,\n", " -4.80900556e-02, -3.77990194e-02, -5.96706904e-02, -3.05942800e-02,\n", " 1.83355808e-02, 3.16484310e-02, 2.69839242e-02, 3.21686789e-02,\n", " 5.26536740e-02, -6.51188428e-03, 1.55735351e-02, 1.61451381e-02,\n", " 1.87562760e-02, 1.43227912e-02, 4.05485146e-02, 5.85826521e-04,\n", " 1.07493647e-03, 2.27565388e-03, -4.96098772e-03, 5.04243039e-02,\n", " 5.73003665e-02, -6.26097471e-02, -4.13594954e-02, 1.29982224e-02,\n", " -1.18702397e-01, 6.81656040e-03, 3.30031961e-02, 3.82255837e-02,\n", " -5.41785173e-02, -3.18652689e-02, -5.72521761e-02, 3.55881453e-02,\n", " 1.90253754e-03, 3.53394672e-02, 1.71035007e-02, -4.14450616e-02,\n", " -4.36440995e-03, -4.24259454e-02, 5.05301841e-02, -3.15273437e-03,\n", " -4.80298959e-02, -4.68152650e-02, 2.08045412e-02, 1.52546295e-03,\n", " 1.26549099e-02, 4.36554812e-02, -3.76826711e-02, 3.91826108e-02,\n", " 1.85529906e-02, 1.80262085e-02, -2.83435956e-02, -1.07219657e-02,\n", " -2.93594263e-02, 2.86445096e-02, -1.95666999e-02, -5.39201200e-02])" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "embeddings[0]" ] }, { "cell_type": "code", "execution_count": 13, "id": "95bdfda2-1575-471e-8725-3f0900be9643", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([-1.43356454e-02, -2.16784477e-02, 3.21097896e-02, 2.72039808e-02,\n", " -4.73676957e-02, -1.18169822e-02, -2.75448826e-03, -2.73635313e-02,\n", " 2.27017626e-02, 7.22942054e-02, -3.79111543e-02, 2.92207138e-03,\n", " -2.39777602e-02, 1.10094333e-02, -2.19638925e-02, 2.56774910e-02,\n", " 1.94586087e-02, -1.32784937e-02, -4.69307834e-03, -2.03847066e-02,\n", " -3.48538011e-02, -2.24664509e-02, -6.02852693e-03, 9.74042434e-03,\n", " 8.85831658e-03, 4.31385264e-02, 2.20383871e-02, 5.08100763e-02,\n", " 5.48611768e-02, 3.38501818e-02, -2.81725992e-02, 3.53083224e-03,\n", " 7.75846944e-04, -1.82817597e-02, -1.83023009e-02, -3.09302025e-02,\n", " -7.22549707e-02, 5.76679828e-03, 7.24002123e-02, 3.40825729e-02,\n", " -4.33760975e-03, 1.72757935e-02, -5.63281029e-03, 7.27394000e-02,\n", " -4.40556072e-02, -7.95468804e-04, -4.01170459e-03, -2.62629353e-02,\n", " -2.25911066e-02, -1.19620198e-02, -9.47790034e-03, -2.43393853e-02,\n", " 1.08281998e-02, -4.20785695e-02, 1.21216569e-02, -6.19425671e-03,\n", " 4.87911515e-02, 1.80345513e-02, -3.02514657e-02, -2.77890693e-02,\n", " -3.37241367e-02, 3.61536182e-02, -1.93439461e-02, 2.84802970e-02,\n", " 1.13601284e-02, 3.97275835e-02, 6.80681987e-05, -8.40261802e-02,\n", " -4.79498170e-02, -1.61925075e-03, -1.17525617e-02, 2.64808871e-02,\n", " 1.22748120e-02, -9.20934137e-03, 6.83386670e-03, 5.15385866e-02,\n", " -2.46887524e-02, -2.95052342e-02, -6.74237385e-02, -2.01902837e-02,\n", " 5.67117780e-02, 2.98874802e-03, 4.15244102e-02, -3.93779427e-02,\n", " -1.73047222e-02, -1.57598518e-02, -5.10301366e-02, -7.92580843e-03,\n", " 4.25807275e-02, 2.39281505e-02, -3.71863209e-02, 3.48019972e-02,\n", " -7.73385214e-03, 7.72475898e-02, 3.27461213e-02, 7.30556529e-03,\n", " -1.45082911e-02, -5.52869849e-02, -3.20466384e-02, -5.49970241e-03,\n", " 2.68832892e-02, 2.03074329e-02, 4.87453863e-03, 1.80150494e-02,\n", " 2.45773625e-02, -4.11030799e-02, 2.72167623e-02, -2.47642267e-02,\n", " 9.02612321e-03, 1.76703855e-02, -2.97775995e-02, -2.27024918e-03,\n", " -6.13781717e-03, -4.55022752e-02, -4.76602837e-02, -2.83710100e-02,\n", " 9.97630693e-03, -1.23663200e-02, -1.67159121e-02, 3.27480771e-02,\n", " -2.59286966e-02, 4.96628545e-02, 4.19698209e-02, -7.26421922e-02,\n", " 1.59672238e-02, 4.21368778e-02, 1.69072244e-02, 8.72177724e-03,\n", " -1.84099749e-02, 2.12360751e-02, 1.58494115e-02, -3.99457887e-02,\n", " 9.01012868e-02, -3.52990441e-02, -5.27740084e-02, 9.24822222e-03,\n", " 2.54883599e-02, -3.33821191e-03, -2.00735647e-02, 4.36091647e-02,\n", " -2.87584141e-02, 1.76400281e-02, -2.17234120e-02, -1.43929645e-02,\n", " -1.04510412e-02, 2.99939625e-02, -4.78526168e-02, 7.80482357e-03,\n", " 1.16777271e-02, -2.99124978e-02, 3.68478112e-02, -4.97667752e-02,\n", " -3.07946280e-02, 1.47823589e-02, -6.85154274e-03, -6.66311290e-03,\n", " 2.52754590e-03, 1.49103887e-02, 7.76185421e-03, 1.66614279e-02,\n", " -2.46641729e-02, -2.75595225e-02, 2.84287729e-04, -1.30307758e-02,\n", " 1.74694210e-02, 9.60071608e-02, 2.25315895e-02, 2.16462929e-02,\n", " 2.11229902e-02, -5.51582687e-02, 1.14661148e-02, -3.58657017e-02,\n", " -4.38515842e-02, -8.70466605e-03, -1.23946965e-02, -8.24343879e-04,\n", " -5.31356223e-03, 4.21371013e-02, -4.32137400e-02, 4.81118187e-02,\n", " -2.67899502e-02, 3.10538355e-02, 3.02620362e-02, 4.64070924e-02,\n", " 6.43681586e-02, -2.03091502e-02, 3.12586389e-02, -3.14582256e-03,\n", " 3.16670127e-02, -7.15507520e-03, -1.17462473e-02, -3.93999480e-02,\n", " -1.83532648e-02, 5.91176525e-02, 3.53675485e-02, 1.51073067e-02,\n", " 1.85176414e-02, -3.89634930e-02, -6.79877549e-02, -4.66686627e-03,\n", " -3.25556397e-02, -1.43425716e-02, -1.45725086e-02, 2.59300950e-03,\n", " -1.82467129e-03, -5.82063198e-02, -4.54162844e-02, -3.97027694e-02,\n", " -2.43694261e-02, 2.81483904e-02, 5.77986706e-03, 5.01666851e-02,\n", " 4.26249579e-03, 6.20526001e-02, -2.01431997e-02, -1.14133293e-02,\n", " -2.35341955e-02, -1.98291205e-02, -6.24520238e-03, 3.05182990e-02,\n", " 3.63235623e-02, -6.86552152e-02, -5.20008765e-02, 2.21570935e-02,\n", " -2.72559002e-02, 4.67344839e-03, -3.03068329e-02, -2.93763410e-02,\n", " -8.17541219e-03, 1.18294312e-02, -3.29147018e-02, 4.59467918e-02,\n", " 1.38999932e-02, -4.40894328e-02, 1.54225696e-02, -2.64135189e-02,\n", " 3.24939527e-02, -9.18254331e-02, -1.26724700e-02, -4.01807986e-02,\n", " -2.84393411e-02, -2.08554845e-02, 3.08648106e-02, 2.75163483e-02,\n", " -9.11746547e-03, -1.82168111e-02, 4.97947484e-02, -3.73658277e-02,\n", " 1.03505170e-02, 8.32711533e-03, 1.21768573e-02, 4.65863571e-03,\n", " -2.55952775e-02, -2.17309948e-02, 4.79184426e-02, 1.81876235e-02,\n", " -4.95702401e-02, 2.97002494e-02, 4.65753078e-02, -1.96203333e-03,\n", " 6.03826232e-02, -2.12521087e-02, -7.67061068e-03, -1.00150515e-04,\n", " 2.00358685e-02, -4.53991257e-02, -4.30120453e-02, 1.71365570e-02,\n", " -4.03556302e-02, 3.33747119e-02, 3.87933594e-03, 8.95243604e-03,\n", " -1.63769536e-02, -3.35253961e-02, -1.55624859e-02, 2.98685227e-02,\n", " -1.27790188e-02, 7.16392919e-02, 4.79074344e-02, 1.17973490e-02,\n", " -4.02338728e-02, -5.64230718e-02, 1.91179868e-02, -1.59064252e-02,\n", " -3.95533368e-02, 1.74548049e-02, -1.95572395e-02, -2.42102984e-02,\n", " -4.36006999e-03, -9.87635553e-03, -2.86743417e-02, -3.05287968e-02,\n", " 3.54571417e-02, -1.82824321e-02, 1.37955286e-02, -2.10614614e-02,\n", " -2.69130641e-03, 1.11276163e-02, -1.24010555e-02, 1.21000139e-02,\n", " 6.11438183e-04, 2.18445305e-02, -2.80352728e-03, -4.72295284e-02,\n", " 2.41780821e-02, 5.12120537e-02, 1.73368491e-03, -9.49876197e-03,\n", " 1.15235127e-03, -2.46519595e-02, 9.13993455e-03, -2.35368479e-02,\n", " 7.84077216e-03, -3.09900492e-02, -1.83918432e-03, -3.89971323e-02,\n", " -2.10007392e-02, 2.85647847e-02, -1.93565004e-02, 1.82900503e-02,\n", " 5.51992990e-02, 3.07692513e-02, 8.35671090e-03, 8.42630211e-03,\n", " 7.56582916e-02, 8.34543444e-03, 3.18184383e-02, -6.17384491e-03,\n", " 3.95975113e-02, -5.76960593e-02, -3.24971490e-02, -7.34638870e-02,\n", " 3.48458299e-03, -6.58036321e-02, -4.93258890e-03, -8.00156686e-03,\n", " 1.77636128e-02, -1.19626066e-02, 2.96311900e-02, -3.68610471e-02,\n", " 3.04197185e-02, 3.41972224e-02, 1.51116475e-02, 1.50926476e-02,\n", " -2.50595133e-03, 8.46610032e-03, -1.03192646e-02, -1.24879116e-02,\n", " -3.64704728e-02, 6.70251772e-02, -2.30552815e-02, 3.32635939e-02,\n", " 3.69163342e-02, 6.18307963e-02, 5.80018647e-02, 3.14503768e-03,\n", " -9.93550755e-03, 3.29794697e-02, 6.82878727e-03, -8.85960311e-02,\n", " -1.05398204e-02, 3.91046852e-02, -4.30030152e-02, -6.79476466e-03,\n", " -6.77599618e-03, -3.99581976e-02, 4.62521836e-02, 3.22874612e-03,\n", " -5.26554808e-02, 1.18789608e-02, -6.97451755e-02, 3.71613540e-02,\n", " 1.48126408e-02, -3.18970233e-02, -2.76949760e-02, -3.14699113e-02,\n", " 2.77896840e-02, 6.64762035e-03, -6.78986870e-03, 1.00684566e-02,\n", " -1.35084391e-02, 4.00617905e-02, -4.27942835e-02, 2.15417631e-02,\n", " -7.82450847e-03, 2.10278947e-02, 4.30472791e-02, -1.75182745e-02,\n", " 7.69843860e-03, 2.49529351e-02, -1.06957583e-02, -1.72273517e-02,\n", " 2.17490103e-02, -4.46285978e-02, -1.73219312e-02, 3.80140282e-02,\n", " -5.07725589e-02, -3.16404887e-02, -6.19173385e-02, -1.16405804e-02,\n", " 1.40790930e-02, 2.30277553e-02, 2.19954625e-02, 3.79117392e-02,\n", " -2.21302340e-04, 2.20077429e-02, 2.14128159e-02, -1.88946091e-02,\n", " 5.32614700e-02, 1.13945324e-02, -2.02453090e-03, -4.07919809e-02,\n", " 1.80551484e-02, 3.14011499e-02, -1.57663785e-02, 1.57475900e-02,\n", " 7.68021774e-03, -5.41340373e-02, -2.64007263e-02, -4.56298739e-02,\n", " 3.39080230e-03, -4.95149791e-02, 1.27100460e-02, -3.50248106e-02,\n", " -9.98336589e-04, -6.38119727e-02, -3.44801806e-02, -2.87301955e-03,\n", " -3.89779285e-02, 1.03416583e-02, 2.38427166e-02, 2.25749351e-02,\n", " 7.72128627e-02, -5.37086986e-02, 3.14587951e-02, -3.51935923e-02,\n", " 3.01207229e-02, 4.15530875e-02, 1.73200294e-02, -4.14097644e-02,\n", " -4.39602584e-02, 4.54685837e-03, 1.61281810e-03, -4.10120338e-02,\n", " -6.34772182e-02, -9.71158687e-03, 1.42328069e-02, 1.48562761e-02,\n", " 1.25701465e-02, 1.54929506e-02, 8.14306214e-02, -3.25670354e-02,\n", " 8.56895000e-02, -1.12816310e-02, -4.78333086e-02, 3.89531627e-02,\n", " -2.81416792e-02, 2.40886100e-02, 1.08475313e-02, 5.59064094e-03,\n", " 3.56553379e-03, -9.31885908e-04, -4.99715805e-02, -3.07415165e-02,\n", " 1.84915271e-02, -1.08987372e-02, 3.73096168e-02, 2.27946211e-02,\n", " 3.46989557e-02, -1.72329079e-02, -6.13656500e-03, -3.82609665e-02,\n", " -1.62435696e-02, -1.75268855e-03, 1.83316856e-03, 3.31918374e-02,\n", " -3.64066996e-02, -6.18439866e-03, -3.93752456e-02, 3.00032310e-02,\n", " 2.72428449e-02, 3.88909318e-02, 5.45297340e-02, -7.42445746e-03,\n", " 2.15397030e-03, 4.34139483e-02, 6.80388212e-02, 1.08292498e-01,\n", " -1.34532712e-02, -2.40998492e-02, 1.45109359e-03, -6.32137656e-02,\n", " -6.43583899e-03, 1.18305348e-02, 4.18519275e-03, -7.55299907e-03,\n", " 4.05896455e-02, 2.10507307e-02, -1.00444211e-02, -1.44077539e-02,\n", " 2.30744965e-02, -1.66961085e-03, -2.33662166e-02, -4.45226766e-02,\n", " -9.86683276e-03, -6.08660700e-03, 2.40885708e-02, 3.08201816e-02,\n", " 1.99116091e-03, 1.15672396e-02, -3.73707749e-02, 8.76458269e-03,\n", " 1.30018257e-02, -9.70822014e-03, -7.35309767e-03, 4.23015803e-02,\n", " 1.13304285e-02, -3.17659006e-02, 2.20693252e-03, -1.51280151e-03,\n", " -3.56691331e-02, 2.18733102e-02, 1.38000110e-02, 2.83594504e-02,\n", " -2.02801432e-02, -7.58651504e-03, 4.84225601e-02, 4.07872312e-02,\n", " 3.12525034e-02, 4.98623103e-02, -2.59318184e-02, 1.06037902e-02,\n", " -1.99769307e-02, -3.70448977e-02, -3.65997739e-02, -1.28400540e-02,\n", " -2.31204871e-02, 3.12355477e-02, -3.18615772e-02, -2.66414043e-03,\n", " 8.50921869e-03, 5.69071434e-02, -1.74142160e-02, 3.01150717e-02,\n", " -5.62037015e-03, 6.25777692e-02, -3.54778245e-02, 3.51262242e-02,\n", " 5.18167876e-02, -1.85311548e-02, -4.43077870e-02, -7.78170885e-04,\n", " -5.95852453e-03, -2.20750161e-02, -1.37064734e-03, -1.84399150e-02,\n", " 1.68244578e-02, 1.68296210e-02, -3.38036977e-02, -5.51353320e-02,\n", " 6.69947937e-02, -1.65974591e-02, -1.94531567e-02, 3.75299528e-02,\n", " 2.43492443e-02, 1.47429444e-02, 2.54110666e-03, -3.37374187e-03,\n", " 3.83959636e-02, 5.41988537e-02, -1.53749324e-02, -5.23985177e-02,\n", " -1.87369306e-02, -3.57736135e-03, -3.08538303e-02, 8.57393537e-03,\n", " -3.60491723e-02, 7.14102760e-02, -2.09798254e-02, -1.43607045e-02,\n", " 1.38038006e-02, 3.09171509e-02, 5.91962715e-04, 2.74400692e-03,\n", " 2.48805992e-02, 3.70309874e-02, 4.71902303e-02, -2.15414427e-02,\n", " 8.60447958e-02, -1.17662298e-02, 1.35909701e-02, 6.13169558e-02,\n", " -2.75752191e-02, 4.96041253e-02, 4.03546989e-02, -4.98761237e-02,\n", " 3.45155224e-02, 7.37943798e-02, 7.62486132e-03, 3.54964137e-02,\n", " -7.65900873e-03, -2.44783256e-02, 3.14811477e-03, -6.01268606e-03,\n", " -4.59896289e-02, 5.05298860e-02, 8.86735320e-03, 8.68058018e-03,\n", " -2.92791463e-02, -3.10860071e-02, 6.98281452e-03, 2.56989412e-02,\n", " -3.05922031e-02, 4.07252759e-02, -1.79703105e-02, -3.80843990e-02,\n", " 2.50013713e-02, -1.45621719e-02, -6.65497361e-03, -3.38632576e-02,\n", " -1.58141274e-02, -2.88456008e-02, 1.93242673e-02, -3.63971689e-03,\n", " -3.93430404e-02, 4.50239927e-02, 8.99149291e-03, -2.13194322e-02,\n", " -1.50523365e-05, 4.87163737e-02, -3.83192790e-03, -3.31537090e-02,\n", " -2.27865279e-02, 2.66835280e-02, -3.13516334e-03, 3.38254706e-03,\n", " -3.98263857e-02, 4.44598933e-04, -1.17501970e-02, -3.26845087e-02,\n", " 1.52193720e-03, 1.74808558e-02, -1.71031076e-02, 1.74386706e-02,\n", " 2.96904780e-02, 2.46194508e-02, 5.89949228e-02, -3.35624665e-02,\n", " 2.61088405e-02, -5.50580062e-02, -5.40384762e-02, -4.65848297e-02,\n", " 4.84881215e-02, -6.58584386e-02, -3.42320688e-02, 3.50068770e-02,\n", " 2.91352943e-02, 3.93977724e-02, -2.06956677e-02, 6.16698898e-02,\n", " -6.44478872e-02, 2.48006787e-02, 9.64339881e-04, 7.72104114e-02,\n", " -5.83015606e-02, -2.44647395e-02, 2.40632612e-02, -4.77992967e-02,\n", " -3.25150900e-02, 2.54701208e-02, -1.83726717e-02, 4.42709861e-04,\n", " 6.06252290e-02, 3.01637053e-02, 6.20173709e-03, -1.76736561e-03,\n", " 1.39037138e-02, 1.14818178e-02, -1.11023383e-02, 1.54927466e-03,\n", " 2.43816245e-02, -3.69032025e-02, 1.43887503e-02, -5.68023287e-02,\n", " 9.50496923e-03, 1.90070958e-03, -5.32673746e-02, -3.12984847e-02,\n", " -5.48556000e-02, 3.69088631e-03, -1.23435631e-02, 4.68733022e-03,\n", " 4.19523641e-02, 5.11015095e-02, -4.51871119e-02, -2.72006188e-02,\n", " 6.59744674e-03, 8.66057537e-03, 1.12540713e-02, -5.09890914e-03,\n", " 5.04220165e-02, 4.54485323e-03, -6.82729930e-02, 1.95662421e-03,\n", " 3.04329898e-02, -2.34693172e-03, -1.37398043e-03, -3.53209936e-04,\n", " -4.96427082e-02, 1.34285092e-02, 2.61487197e-02, 3.21481749e-02,\n", " -4.97249775e-02, -3.57422270e-02, -2.98923347e-02, -1.42609132e-02,\n", " -1.12756649e-02, 5.08668870e-02, -2.98765954e-02, 4.66655158e-02,\n", " 4.49310951e-02, 2.53670420e-02, 9.36789718e-03, 1.36808278e-02,\n", " 8.50078370e-03, -2.44636200e-02, 3.67989205e-02, -1.96039435e-02,\n", " 7.59241823e-03, 2.50165574e-02, -6.03327528e-03, 4.61267866e-02,\n", " 1.35313133e-02, -3.77288796e-02, -5.14320210e-02, 1.09182186e-02,\n", " -1.05255470e-01, 4.06814693e-03, 5.25197200e-02, 4.45685256e-03,\n", " -5.17143719e-02, -4.59787715e-03, -2.57198438e-02, 3.69616076e-02,\n", " 2.12156083e-02, 2.93332636e-02, 5.23170717e-02, -1.31642222e-02,\n", " 1.40874460e-02, -4.84576896e-02, 3.18079107e-02, -1.36526749e-02,\n", " -7.40123838e-02, -1.70104075e-02, 2.65298821e-02, 1.72942714e-03,\n", " 1.32380184e-02, 5.42758889e-02, -2.61124335e-02, 4.26517315e-02,\n", " 1.73017047e-02, -3.98834702e-04, 1.36054317e-02, -6.38240203e-03,\n", " -3.33479457e-02, 1.91155151e-02, -8.56664905e-04, -3.58897559e-02])" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "embeddings[1]" ] }, { "cell_type": "code", "execution_count": null, "id": "95038468-5fdc-406d-81f7-a99cd941e64f", "metadata": {}, "outputs": [], "source": [ "d = 128 # Dimension of vectors\n", "nb = 1000 # Number of database vectors\n", "np.random.seed(42)\n", "data = np.random.random((nb, d)).astype('float32')" ] }, { "cell_type": "code", "execution_count": null, "id": "6d84ffe2-5376-455c-b28d-84a4b64cd6d9", "metadata": { "scrolled": true }, "outputs": [], "source": [ "data" ] }, { "cell_type": "code", "execution_count": 15, "id": "ca73fdd2-af22-4738-97cc-cd671e02b4b1", "metadata": {}, "outputs": [], "source": [ "import faiss\n", "d = 768\n", "index = faiss.IndexFlatL2(d)" ] }, { "cell_type": "code", "execution_count": 16, "id": "e93311d5-d5ef-4974-9d3c-eacf912403da", "metadata": {}, "outputs": [], "source": [ "index.add(embeddings)" ] }, { "cell_type": "code", "execution_count": 17, "id": "fa9059fc-773e-42c0-a414-5262089faa58", "metadata": {}, "outputs": [], "source": [ "faiss.write_index(index, \"../../volumes/indexes/law_corpus_index.bin\")" ] }, { "cell_type": "code", "execution_count": 19, "id": "3dcff12e-23b9-40f1-aa8a-8c04232053c6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\n \\n \\n \\n \\n THE CONSTITUTION OF INDIA \\n[As on May , 2022] \\n2022 \\n '" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][0]" ] }, { "cell_type": "code", "execution_count": 20, "id": "c35858d0-3211-4e3c-b0b4-1ddb8f527cd0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\n \\nPREFACE \\n \\nThis is the fifth pocket size edition of the Constitution of \\nIndia in the diglot form. In this edition, the text of the \\nConstitution of India has been brought up-to-date by \\nincorporating therein all the amendments up to the Constitution \\n(One Hundred and Fifth Amendment) Act, 2021. The foot notes \\nbelow the text indicate the Constitution Amendment Acts by \\nwhich such amendments have been made. \\nThe Constitution (One Hundredth Amendment) Act, 2015 \\ncontaining details of acquired and transferred territories \\nbetween the Governments of India and Bangladesh has been \\nprovided in APPENDIX I. \\nThe Constitution (Application to Jammu and Kashmir) \\nOrder, 2019 and the declaration under article 370(3) of the \\nConstitution have been provided respectively in Appendix II and \\nAppendix III for reference. \\n \\n \\nNew Delhi; Dr. Reeta Vasishta, \\n Secretary to the Government of India. \\n \\n '" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][1]" ] }, { "cell_type": "code", "execution_count": 22, "id": "b93d46dc-81ee-435b-82a5-1009700a12d3", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' \\nLIST OF ABBREVIATIONS USED \\n \\n \\nArt., arts. ........................................................ for Article, articles. \\nCl., cls. ........................................................ ″ Clause, clauses. \\nC.O. ........................................................ ″ Constitution Order. \\nIns. ........................................................ ″ Inserted. \\nP., pp. ........................................................ ″ Page, pages. \\nPt. ........................................................ ″ Part. \\nRep. ........................................................ ″ Repealed. \\nSs., ss. .......................................................... ″ Section, sections. \\nSch. ......................................................... ″ Schedule. \\nSubs. ........................................................ ″ Substituted. \\nw.e.f. ......................................................... ″ with effect from. \\nw.r.e.f. ...................................................... ″ with retrospective effect \\nfrom. \\n '" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][2]" ] }, { "cell_type": "code", "execution_count": 23, "id": "a8c8b023-f06a-4c12-ad4c-c4db7be95bef", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Contents \\n \\n ARTICLES (iv)\\n 40. Organisation of village panchayats. \\n 41. Right to work, to education and to public assistance in certain \\ncases. \\n 42. Provision for just and humane conditions of work and maternity \\nrelief. \\n 43. Living wage, etc., for workers. \\n43A. Participation of workers in management of Industries. \\n43B. Promotion of co-operative societies. \\n 44. Uniform civil code for the citizens. \\n 45. Provision for early childhood care and educat ion to children \\nbelow the age of six years. \\n 46. Promotion of educational and economic interests of Scheduled \\nCastes, Scheduled Tribes and other weaker sections. \\n 47. Duty of the State to raise the level of nutrition and the standard \\nof living and to improve public health. \\n 48. Organisation of agriculture and animal husbandry. \\n48A. Protection and improvement of environment and safeguarding of \\nforests and wild life. \\n 49. Protection of monuments and places and objects of national \\nimportance. \\n 50. Separation of judiciary from executive. \\n 51. Promotion of international peace and security. \\n PART IVA \\nFUNDAMENTAL DUTIES \\n51A. Fundamental duties. \\n \\n \\n \\n \\n PART V \\nTHE UNION \\nCHAPTER I.\\uf0beTHE EXECUTIVE \\nThe President and Vice-President \\n52. The President of India. \\n53. Executive power of the Union. \\n54. Election of President. '" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(pdf_text_dict.values())[0:10][6]" ] }, { "cell_type": "code", "execution_count": 23, "id": "49e5aed7-79dc-480e-a5a9-f75799eab328", "metadata": {}, "outputs": [], "source": [ "query = np.random.random((5, d)).astype('float32')" ] }, { "cell_type": "code", "execution_count": 24, "id": "a2ee4345-5a43-4ee6-9706-004d147328b2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[0.04977802, 0.48656103, 0.28263223, ..., 0.9249028 , 0.49694043,\n", " 0.6121883 ],\n", " [0.02063165, 0.32649937, 0.5049617 , ..., 0.41199866, 0.43590757,\n", " 0.20361727],\n", " [0.37153634, 0.62894505, 0.84184766, ..., 0.6600337 , 0.12406218,\n", " 0.18649617],\n", " [0.00358555, 0.36700717, 0.8201504 , ..., 0.3835851 , 0.03757534,\n", " 0.33080533],\n", " [0.41282707, 0.23166862, 0.9693633 , ..., 0.92313445, 0.02211179,\n", " 0.21810389]], dtype=float32)" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "query" ] }, { "cell_type": "code", "execution_count": 25, "id": "5fe715db-5a9c-41c5-afb6-1d6b207c3e98", "metadata": {}, "outputs": [], "source": [ "faiss.write_index(index, \"faiss_test_index.bin\")\n", "# print(\"Index saved successfully!\")" ] }, { "cell_type": "code", "execution_count": 12, "id": "fec115ed-99a7-4e64-a411-b55e8bd85f6b", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index loaded successfully!\n", "Number of vectors in the index: 10\n" ] } ], "source": [ "import faiss\n", "index = faiss.read_index(\"faiss_test_index.bin\")\n", "print(\"Index loaded successfully!\")\n", "print(\"Number of vectors in the index:\", index.ntotal)" ] }, { "cell_type": "code", "execution_count": 2, "id": "de4cebf6-cd24-499b-b79a-f7dfe98fb807", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index type: \n", "Is Trained: True\n", "Number of vectors: 10\n" ] } ], "source": [ "print(\"Index type:\", type(index))\n", "print(\"Is Trained:\", index.is_trained)\n", "print(\"Number of vectors:\", index.ntotal)\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "c02455e6-b99e-4eff-bd7a-7cf4c05566a1", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([-4.33520480e-34, 1.96945212e-39, 1.63441963e-34, 7.23149259e-29,\n", " 0.00000000e+00, 0.00000000e+00, 3.44876660e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20622715e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 1.85896145e+34, 7.77666437e+31,\n", " 1.71810666e+19, 7.14495034e+31, 1.57661930e-19, 1.94412705e+31,\n", " 1.14918035e-38, 0.00000000e+00, 9.28516057e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76294526e-27, 7.18866112e-43,\n", " 1.71810666e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 8.43042259e+11, 5.40934844e+04,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20672938e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76339824e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.75243739e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44882823e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20622715e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 4.54700658e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -9.36731029e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 7.15600499e+22, 1.38195514e+31,\n", " 3.03465913e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20701636e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 8.43042259e+11, 5.40934844e+04,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20672938e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76300997e-27, 7.18866112e-43,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44710260e-28, 7.18866112e-43,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44888986e-28, 7.18866112e-43,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20622715e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 1.24288541e-28, 7.18866112e-43,\n", " 3.03464869e+32, 8.80015436e-43, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -9.36731029e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.87729688e+03, 2.48029828e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76339824e-27, 7.18866112e-43,\n", " 1.12103877e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 8.43042259e+11, 5.40934844e+04,\n", " 8.68805048e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20672938e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76311782e-27, 7.18866112e-43,\n", " 8.68805048e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44839682e-28, 7.18866112e-43,\n", " 8.68805048e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44747238e-28, 7.18866112e-43,\n", " 8.68805048e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.22660315e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 8.68805048e-44, 0.00000000e+00, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20622715e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 1.85896145e+34, 7.77666437e+31,\n", " 1.71810666e+19, 7.14495034e+31, 1.57661930e-19, 1.10452625e+27,\n", " 1.14917755e-38, 0.00000000e+00, 9.28516057e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76300997e-27, 7.18866112e-43,\n", " 1.71810666e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 8.43042259e+11, 5.40934844e+04,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20674283e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76346295e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44882823e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44778053e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20624061e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 1.85896145e+34, 7.77666437e+31,\n", " 1.71810666e+19, 7.14495034e+31, 1.57661930e-19, 1.94412705e+31,\n", " 1.14918035e-38, 0.00000000e+00, 9.28522783e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76341981e-27, 7.18866112e-43,\n", " 1.71810666e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 8.43042259e+11, 5.40934844e+04,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20674283e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.76294526e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 2.75243739e-27, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44734912e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -4.23615889e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 3.44716688e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, 4.20624061e-38, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 4.11713748e-28, 7.18866112e-43,\n", " 1.71810193e+19, 7.14495034e+31, 5.44333404e-30, 7.18866112e-43,\n", " 2.80259693e-45, 0.00000000e+00, -9.36737755e-39, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 6.38779203e-30, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 2.80259693e-45, 0.00000000e+00,\n", " 1.19443525e-26, 7.18866112e-43, 0.00000000e+00, 0.00000000e+00,\n", " 2.15268200e-26, 7.18866112e-43, 2.15268200e-26, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 2.15267076e-26, 7.18866112e-43, 2.15267076e-26, 7.18866112e-43,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 1.40129846e-45, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 4.59065377e-41,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n", " 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00],\n", " dtype=float32)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "vector_10 = np.zeros(768, dtype='float32')\n", "index.reconstruct(10, vector_10) " ] }, { "cell_type": "code", "execution_count": 4, "id": "962695d9-9525-4ef2-9c5b-ea7c242ac5d5", "metadata": {}, "outputs": [], "source": [ "test_emb = index.reconstruct(10, vector_10) " ] }, { "cell_type": "code", "execution_count": 5, "id": "175af996-a07c-4e8e-832e-5d7410783e2a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "768" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(test_emb)" ] }, { "cell_type": "code", "execution_count": 6, "id": "2af1ba86-d178-48b7-8a6e-09399bd984bb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index Type: \n", "Index Dimension: 768\n", "Number of Vectors in Index: 10\n", "Query Shape: (768,)\n", "Is Index Trained: True\n" ] } ], "source": [ "print(\"Index Type:\", type(index))\n", "print(\"Index Dimension:\", index.d)\n", "print(\"Number of Vectors in Index:\", index.ntotal)\n", "print(\"Query Shape:\", test_emb.shape)\n", "print(\"Is Index Trained:\", index.is_trained)" ] }, { "cell_type": "code", "execution_count": 18, "id": "70f97eaf-468d-4c1b-a042-276c8f0123ef", "metadata": {}, "outputs": [], "source": [ "query = \"which pocket size is this edition?\"\n", "query_embeddings = model.encode([query])" ] }, { "cell_type": "code", "execution_count": 19, "id": "fafd5f1c-9d42-45ec-84e6-e3dced2f9a52", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([[-3.73132437e-01, -2.49501050e-01, 5.96238971e-01,\n", " 1.60232633e-01, -7.16607630e-01, -3.35337073e-01,\n", " 2.09526420e-01, -5.55256248e-01, 6.18032277e-01,\n", " 8.19526017e-01, -6.39822304e-01, 1.57655537e-01,\n", " -2.45462924e-01, -1.64276659e-01, -2.11889967e-02,\n", " 5.78294039e-01, 3.00301939e-01, -4.89581376e-02,\n", " 5.43662719e-03, -2.26307601e-01, -6.92653283e-02,\n", " -2.94720709e-01, -5.32017469e-01, -3.34114343e-01,\n", " 2.40843698e-01, 1.39474165e+00, 8.41520846e-01,\n", " 9.00752783e-01, 3.70669335e-01, 3.69088054e-01,\n", " -2.56014347e-01, -3.89395177e-01, -4.00742084e-01,\n", " -4.74080443e-01, 5.93443394e-01, -1.70544237e-01,\n", " -7.75071025e-01, 6.44626856e-01, 7.97609329e-01,\n", " 8.33190203e-01, 1.20621324e-02, 4.71046597e-01,\n", " -3.30124229e-01, 1.22842538e+00, -7.82999873e-01,\n", " -8.05311918e-01, 2.30400667e-01, 1.82415247e-01,\n", " -2.73626685e-01, 2.95862228e-01, -2.96776861e-01,\n", " 4.01828885e-01, 5.47554195e-01, -7.41805792e-01,\n", " 6.52820528e-01, -2.80365616e-01, 5.87766767e-01,\n", " -9.25101712e-02, -1.71328247e-01, -4.88722175e-01,\n", " -6.11516654e-01, 8.54884803e-01, 6.13536574e-02,\n", " 1.03063786e+00, 1.28858745e-01, 3.10793996e-01,\n", " -9.51184779e-02, -1.10501099e+00, -6.18921220e-01,\n", " 4.59839940e-01, 4.04549509e-01, 5.46272457e-01,\n", " -4.80109006e-01, -3.37467492e-01, -2.01065853e-01,\n", " 4.94460106e-01, -5.20232677e-01, -6.38742447e-01,\n", " -6.71331465e-01, 1.15267292e-01, 8.12568665e-01,\n", " -7.69091491e-03, 1.76295757e-01, -3.87636304e-01,\n", " -2.75877208e-01, -5.07208779e-02, -9.28902864e-01,\n", " -3.06568354e-01, 4.81325299e-01, 1.30671430e-02,\n", " -2.72536874e-01, 3.41388918e-02, 3.54521304e-01,\n", " 9.06797409e-01, 2.50232577e-01, -4.86936778e-01,\n", " -4.14275318e-01, -7.26987123e-01, -6.16783917e-01,\n", " 2.70495731e-02, 3.45965385e-01, 9.04193640e-01,\n", " -2.00276956e-01, 2.49010026e-01, -2.13858709e-02,\n", " -1.21312928e+00, 1.68583840e-01, -9.86288905e-01,\n", " -3.84645879e-01, -1.94787923e-02, -5.11086226e-01,\n", " 2.62719810e-01, 3.79847251e-02, -7.36862719e-01,\n", " -5.68665743e-01, 3.88124317e-01, 1.63300022e-01,\n", " -2.86569983e-01, -3.72056500e-03, 1.50334984e-01,\n", " -4.81104314e-01, 1.73026845e-01, 5.45722723e-01,\n", " -8.67989004e-01, 5.75004995e-01, 1.82515651e-01,\n", " 9.60796356e-01, 9.23014641e-01, -8.13714638e-02,\n", " -6.45711347e-02, 5.04627109e-01, -7.77863741e-01,\n", " 1.08234835e+00, -3.77334476e-01, -1.57291222e+00,\n", " -2.56048769e-01, 1.82667434e-01, -2.18309820e-01,\n", " -4.18597072e-01, 3.87196004e-01, -1.32786959e-01,\n", " -1.56175554e-01, -7.86275685e-01, 2.34808862e-01,\n", " -1.37365952e-01, -1.35111615e-01, -4.24241722e-01,\n", " 5.96258402e-01, 8.10592413e-01, -4.84668255e-01,\n", " 4.53763366e-01, -4.93415564e-01, -2.01269567e-01,\n", " 2.73051053e-01, 3.40254188e-01, -8.09984922e-01,\n", " 5.26710093e-01, -9.40554962e-02, -1.18216380e-01,\n", " -9.88251790e-02, -4.80686188e-01, -4.20976251e-01,\n", " -2.63683915e-01, -5.48085630e-01, 2.88112044e-01,\n", " 5.15181303e-01, 5.17866492e-01, 2.55876034e-01,\n", " 1.74452350e-01, -8.66756022e-01, 1.28356129e-01,\n", " 5.93110323e-01, -2.46795833e-01, -4.72101092e-01,\n", " -9.51930806e-02, -3.32720965e-01, 2.77996790e-02,\n", " 7.48720825e-01, -8.02123785e-01, -9.64421928e-02,\n", " -2.64321007e-02, 5.29742241e-01, 5.07097185e-01,\n", " 2.51757592e-01, 5.91747046e-01, -5.11173129e-01,\n", " 2.94839919e-01, -3.23320031e-01, 1.38826823e+00,\n", " -1.81692377e-01, -8.22013058e-03, -7.93573976e-01,\n", " -6.65791273e-01, 7.07389593e-01, 6.87932596e-02,\n", " 1.39326096e-01, 4.90396291e-01, -5.17733395e-01,\n", " -1.08724594e+00, -1.31639168e-01, 2.29492158e-01,\n", " -4.92301248e-02, -3.75349402e-01, -1.11997604e-01,\n", " -5.58441617e-02, -6.61340579e-02, -1.48219085e+00,\n", " -4.10615094e-03, -3.43739361e-01, 3.03971678e-01,\n", " 9.24170196e-01, 3.64206761e-01, -3.11778784e-01,\n", " 6.69572055e-01, -6.96559727e-01, -3.94165248e-01,\n", " -6.09896004e-01, -2.76756316e-01, -7.65358359e-02,\n", " 3.11748415e-01, 1.08360314e+00, -5.18168986e-01,\n", " -9.83385503e-01, 2.48666689e-01, 2.65461743e-01,\n", " -3.07810903e-02, -1.80236802e-01, -9.18660462e-02,\n", " -1.05982646e-01, 1.97828472e-01, -2.54839603e-02,\n", " 4.36863214e-01, 6.80076063e-01, -1.05401337e+00,\n", " 1.80188343e-01, -9.56242800e-01, 5.97054809e-02,\n", " -7.74244487e-01, -3.17614317e-01, 4.34077024e-01,\n", " -7.36546636e-01, -2.82710582e-01, -2.38731354e-01,\n", " 4.33760226e-01, -5.03278792e-01, 2.40366995e-01,\n", " 4.17858779e-01, -1.14790308e+00, 3.63061996e-03,\n", " 1.98579997e-01, 4.91681933e-01, 3.63510609e-01,\n", " -1.64256126e-01, -4.82028008e-01, 1.30196822e+00,\n", " -1.67734966e-01, -1.14694767e-01, 1.03191659e-01,\n", " 3.11995834e-01, -4.81099747e-02, 6.84669852e-01,\n", " -8.66782844e-01, 3.97845149e-01, 1.05078049e-01,\n", " -1.91367771e-02, -2.31815398e-01, -4.98310983e-01,\n", " -2.50129551e-01, -3.04200739e-01, 5.40039778e-01,\n", " -3.92500944e-02, -2.26705179e-01, -5.00782847e-01,\n", " -8.49243283e-01, -1.52281150e-01, 3.02840889e-01,\n", " -8.38819087e-01, 7.79993415e-01, 6.30303144e-01,\n", " -3.37795734e-01, -4.16197717e-01, -5.30447960e-01,\n", " 3.10830384e-01, -1.88205227e-01, -5.94668686e-01,\n", " 1.59734219e-01, -1.08995959e-01, -5.41627169e-01,\n", " -2.38114670e-01, -6.63974524e-01, 2.36916468e-02,\n", " -3.53694648e-01, 9.17128250e-02, -5.80827408e-02,\n", " 1.95876032e-01, -1.01593681e-01, 1.69732177e-03,\n", " 9.79008079e-02, 2.53847957e-01, 5.74670248e-02,\n", " 3.34153295e-01, -2.72751749e-01, 6.36534452e-01,\n", " -1.16707854e-01, 5.43213308e-01, 7.07452834e-01,\n", " 3.99107561e-02, 3.24606478e-01, -6.17893934e-01,\n", " -1.00787114e-02, -4.40084338e-01, -2.32265413e-01,\n", " 2.95902163e-01, -5.53712606e-01, 4.01033670e-01,\n", " -7.52838850e-01, 1.89499423e-01, 6.55153930e-01,\n", " -2.22477034e-01, -7.49209076e-02, 3.15154910e-01,\n", " -1.48034245e-01, 5.52035034e-01, 4.73529935e-01,\n", " 8.73762369e-01, 1.08367449e-03, 5.38138390e-01,\n", " -4.17241633e-01, 3.97459447e-01, -9.75983083e-01,\n", " -5.30309439e-01, -5.86849988e-01, 1.68224990e-01,\n", " 8.97852480e-02, -3.28494668e-01, 6.88293517e-01,\n", " 6.28556967e-01, -7.58412123e-01, 4.54522401e-01,\n", " -5.63978970e-01, 1.03677034e+00, 9.27480936e-01,\n", " 7.03815997e-01, -7.34761581e-02, -6.18429720e-01,\n", " 3.67733747e-01, 3.19563188e-02, -5.64858139e-01,\n", " -7.86610365e-01, 1.15927947e+00, 2.88311422e-01,\n", " 2.27986667e-02, 1.16840279e+00, 6.96775556e-01,\n", " 4.12162632e-01, 1.42026365e-01, -7.81583369e-01,\n", " 3.59356999e-01, -3.03264558e-01, -1.23299253e+00,\n", " -2.07522169e-01, 7.18758404e-02, -8.33071828e-01,\n", " 2.67476916e-01, -3.35263610e-01, -4.65342253e-01,\n", " -4.42757085e-02, -1.95778117e-01, -4.73799497e-01,\n", " 1.64555743e-01, -1.49801087e+00, 1.52146614e+00,\n", " 1.92096204e-01, -5.09908497e-01, -2.74958666e-02,\n", " -3.37128758e-01, 4.71870899e-01, 1.35582626e-01,\n", " 1.01404175e-01, -2.10669041e-01, -4.76792127e-01,\n", " 6.74312353e-01, -5.67972898e-01, 2.08251834e-01,\n", " -1.22650824e-01, 4.15052265e-01, 2.92291105e-01,\n", " 3.84335458e-01, 3.82747501e-01, 7.96951652e-01,\n", " 2.45787919e-01, -5.12812495e-01, 5.99845231e-01,\n", " -6.05813682e-01, -2.56353378e-01, 8.67983997e-01,\n", " -6.69039071e-01, -1.16040623e+00, -8.17078352e-01,\n", " -6.14573061e-01, 9.32083800e-02, 6.49191320e-01,\n", " 6.45326793e-01, 1.19449282e+00, -3.89639467e-01,\n", " 4.40224290e-01, 8.74099731e-01, -1.36296421e-01,\n", " 9.04735982e-01, 3.27269793e-01, 9.31127742e-02,\n", " -5.14510274e-01, 7.46768236e-01, 3.84369940e-01,\n", " 1.30401716e-01, 2.02281713e-01, 9.07322466e-01,\n", " -6.44040048e-01, -7.17496872e-01, -1.07841885e+00,\n", " 3.94205689e-01, -4.85761285e-01, 1.00266829e-01,\n", " -3.77025425e-01, -1.14991017e-01, -6.03294492e-01,\n", " -5.45877039e-01, -2.83136576e-01, -5.13567448e-01,\n", " -5.82447886e-01, 2.68453449e-01, 3.32528502e-01,\n", " 1.24224198e+00, -6.67818129e-01, 9.05226171e-01,\n", " -5.66123486e-01, -1.90349564e-01, 8.19898665e-01,\n", " 1.97118804e-01, -9.68308747e-01, -3.20560634e-01,\n", " 2.53744036e-01, -7.06153274e-01, -9.31951821e-01,\n", " -1.64078271e+00, 3.15479875e-01, 1.42178342e-01,\n", " 5.88349700e-02, 5.27518749e-01, 6.56938732e-01,\n", " 2.79468894e-01, -4.10564542e-01, 9.62086380e-01,\n", " 9.48429763e-01, -7.86864221e-01, 5.47595382e-01,\n", " -7.86275983e-01, 7.61770785e-01, 5.87614894e-01,\n", " 1.48882167e-02, -4.84432578e-01, 2.60001332e-01,\n", " -1.50160336e+00, -6.95915163e-01, 5.42413652e-01,\n", " -2.24143401e-01, 3.45107228e-01, 7.04570860e-02,\n", " 5.93081042e-02, 1.59532160e-01, 1.38447762e-01,\n", " -5.61178684e-01, -9.39185560e-01, -8.43761027e-01,\n", " -4.81777310e-01, -2.88198024e-01, -9.24013674e-01,\n", " -5.58189489e-02, -5.62792122e-01, 3.82276475e-01,\n", " 1.37424067e-01, 7.60315895e-01, 5.82331598e-01,\n", " 2.34126389e-01, 4.09395903e-01, 2.04976454e-01,\n", " 1.22483075e+00, 1.28335214e+00, -8.90118599e-01,\n", " 1.99793875e-01, 1.23221315e-01, -1.26057792e+00,\n", " 2.64338050e-02, 2.98419356e-01, -1.39900632e-02,\n", " 7.02696145e-02, 2.03694075e-01, 6.90980375e-01,\n", " 2.89714545e-01, -5.54847181e-01, 8.55074942e-01,\n", " -6.81426674e-02, -5.34121580e-02, -9.28871036e-01,\n", " -1.99676026e-02, 7.34668002e-02, 1.31285846e-01,\n", " 2.54347950e-01, 1.70441449e-01, 7.08350718e-01,\n", " -6.22398257e-01, -7.84196556e-02, 5.66708684e-01,\n", " -7.40765691e-01, -2.78145909e-01, 5.26153743e-01,\n", " 4.23496008e-01, -6.95848703e-01, 1.36369213e-01,\n", " -5.10521293e-01, -1.75267711e-01, -7.64884567e-03,\n", " 9.14079428e-01, 5.20044208e-01, -2.23987743e-01,\n", " 3.53826940e-01, 8.52507830e-01, 5.36109507e-01,\n", " 4.82949048e-01, 3.01424444e-01, -4.79259759e-01,\n", " -6.10692287e-03, 6.04810655e-01, -2.61711717e-01,\n", " -5.65918505e-01, -5.64313531e-02, -5.63005209e-01,\n", " -5.22360057e-02, -9.35905874e-01, -3.12182814e-01,\n", " 1.18156619e-01, 1.01302695e+00, -1.42838508e-01,\n", " 7.82134235e-02, -8.96130681e-01, 1.70163655e+00,\n", " -1.46398842e-01, 1.10671282e+00, 8.45957100e-01,\n", " 4.63032350e-02, -1.00434208e+00, -1.14734650e-01,\n", " 2.96710730e-01, -5.72073817e-01, -2.12342575e-01,\n", " -2.37710774e-01, 3.79127055e-01, -1.49838269e-01,\n", " 1.90677255e-01, -9.28616405e-01, 7.70177543e-01,\n", " 2.35295668e-01, -7.38796234e-01, 8.12511504e-01,\n", " -4.67237413e-01, -4.24484372e-01, 1.36564776e-01,\n", " -2.15696618e-02, 9.13881302e-01, 3.11742872e-01,\n", " 7.86022991e-02, -8.72730196e-01, -7.89672911e-01,\n", " -4.01746392e-01, -2.15047896e-01, 5.05439878e-01,\n", " -1.36737025e+00, 6.40702546e-01, -6.57468557e-01,\n", " 3.03122461e-01, 2.00641811e-01, 2.77454436e-01,\n", " 4.26229477e-01, 8.42323452e-02, 4.92563128e-01,\n", " 8.77941966e-01, 5.69560945e-01, -5.02784848e-01,\n", " 1.58974600e+00, 1.30327821e-01, 2.26048499e-01,\n", " 6.67626560e-01, 5.49613871e-02, 9.43626285e-01,\n", " 1.06245506e+00, -5.50742388e-01, 5.56908190e-01,\n", " 9.31764066e-01, 3.82145762e-01, 6.55513942e-01,\n", " 2.44829385e-03, -8.68118703e-01, 2.79977143e-01,\n", " 1.21336579e-01, -3.55989635e-01, 4.50310290e-01,\n", " 1.79327637e-01, -1.72277451e-01, -3.34044784e-01,\n", " -4.58468914e-01, -2.24370077e-01, 6.02882028e-01,\n", " -9.83122110e-01, 6.39831007e-01, -5.64755946e-02,\n", " -2.68326759e-01, -3.14345598e-01, 6.05972763e-03,\n", " -6.35993928e-02, -8.61854672e-01, 3.42682093e-01,\n", " -1.87066928e-01, 7.03457654e-01, 6.24295175e-01,\n", " -6.78606808e-01, 4.04980153e-01, -1.16588630e-01,\n", " -6.46906197e-01, 2.58253694e-01, 2.56113768e-01,\n", " 7.04896092e-01, -8.82478118e-01, -3.24431896e-01,\n", " -1.49077222e-01, -2.00304121e-01, 4.80519086e-01,\n", " -8.77241135e-01, 9.28806737e-02, -2.77008176e-01,\n", " -2.52063602e-01, 3.62312973e-01, 5.23445070e-01,\n", " 6.17201477e-02, 3.06572258e-01, -2.11930275e-01,\n", " 1.78940728e-01, 3.65689784e-01, -5.40046096e-01,\n", " 2.63069421e-01, -4.92571503e-01, -1.09113395e+00,\n", " -2.64382094e-01, 1.50071561e-01, -1.21670222e+00,\n", " -1.27806652e+00, 7.23531783e-01, 1.07804430e+00,\n", " 2.99413145e-01, -3.73375475e-01, 5.63707471e-01,\n", " -3.84140350e-02, 3.85195851e-01, 7.45883882e-02,\n", " 5.53500690e-02, -1.04585457e+00, -1.97465733e-01,\n", " -8.30319058e-03, -7.37104416e-01, 4.16536480e-02,\n", " 1.17034423e+00, -1.80100635e-01, -1.88495189e-01,\n", " 5.19660592e-01, 2.14780048e-01, 3.36319059e-02,\n", " 7.73143053e-01, 3.61136287e-01, -4.28402722e-01,\n", " -8.84197876e-02, 6.89760685e-01, 4.01313961e-01,\n", " -6.98327184e-01, 2.32672039e-02, -8.21807086e-01,\n", " -3.07718366e-01, -4.05677371e-02, -8.12784433e-01,\n", " -8.40686142e-01, -5.86191237e-01, -1.52433366e-01,\n", " -3.29975456e-01, -6.76786900e-02, 1.36615014e+00,\n", " 1.39413977e+00, -5.70796877e-02, -2.52656639e-01,\n", " -4.51961011e-02, 3.77376556e-01, 3.74267623e-02,\n", " -1.00905411e-01, 5.03461361e-01, 4.47633147e-01,\n", " -8.03849757e-01, 3.12187463e-01, 7.82718778e-01,\n", " 7.99427450e-01, 8.74587893e-02, -3.69026005e-01,\n", " 4.00398403e-01, 2.46881902e-01, 4.02131408e-01,\n", " 2.96504140e-01, -2.65133023e-01, -8.00934196e-01,\n", " -1.27983302e-01, 3.69233519e-01, -3.53833318e-01,\n", " 9.58463430e-01, 8.44675601e-02, 1.76893070e-01,\n", " 9.15330946e-02, -6.18301369e-02, 7.27794826e-01,\n", " -5.30644834e-01, 5.37168384e-01, -9.10579562e-01,\n", " 9.74827886e-01, -1.29682362e-01, 8.54603410e-01,\n", " 2.43808255e-02, -5.53768694e-01, 5.91500998e-01,\n", " 5.04585087e-01, -8.32424283e-01, -1.12211466e+00,\n", " -2.83660553e-02, -1.73512232e+00, -7.24534571e-01,\n", " 7.96634674e-01, 4.31780487e-01, -1.12527800e+00,\n", " -1.56593829e-01, -2.48527288e-01, -6.10543132e-01,\n", " -3.87620851e-02, 2.72551537e-01, 7.81981230e-01,\n", " 2.83847809e-01, -5.20967424e-01, -7.18649983e-01,\n", " 2.10900754e-01, -8.37667227e-01, -5.51518202e-01,\n", " 5.75399138e-02, 2.35412762e-01, 4.11376804e-01,\n", " 1.39269143e-01, 8.81839573e-01, -1.53456211e-01,\n", " 1.32611656e+00, 5.51057339e-01, -3.10137779e-01,\n", " -3.27861547e-01, -5.78627765e-01, 2.88041979e-01,\n", " -2.95859277e-02, 5.04428446e-01, -5.79054892e-01]], dtype=float32)" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "query_embeddings" ] }, { "cell_type": "code", "execution_count": 10, "id": "1660cff8-b813-4f10-9621-408070bdb877", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index loaded successfully!\n", "Number of vectors in the index: 404\n" ] } ], "source": [ "from retriever import vector_db_retriever" ] }, { "cell_type": "code", "execution_count": 25, "id": "470d596e-4c67-4d14-adf8-f7c923d95f21", "metadata": {}, "outputs": [], "source": [ "query = \" explain Seventh Amendment Act\"\n", "query_embeddings = model.encode([query])" ] }, { "cell_type": "code", "execution_count": 26, "id": "5431146f-86c4-4c5b-8cda-0753940dbe12", "metadata": {}, "outputs": [], "source": [ "result = vector_db_retriever(query_embeddings, 15)" ] }, { "cell_type": "code", "execution_count": 27, "id": "255a910b-aa83-4c3f-bc27-2eaa070a6135", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "THE CONSTITUTION OF INDIA \n", "(Part VI.—The States) 101\n", "218. Application of certain provisions relating to Supreme Court to \n", "High Courts .—The provisions of clauses (4) and (5) of article 124 shall apply \n", "in relation to a High Court as they apply in relation to the Supreme Court with \n", "the substitution of references to the High Court for references to the Supreme \n", "Court. \n", "219. Oath or affirmation by Judges of High Courts. —Every person \n", "appointed to be a Judge of a High Court 1*** shall, before he enters upon his \n", "office, make and subscribe before the Governor of the State, or some person \n", "appointed in that behalf by him, an oath or affirmation according to the form \n", "set out for the purpose in the Third Schedule. \n", "2[220. Restriction on practice after being a permanent Judge .—No \n", "person who, after the commencement of this Constitution, has held office as a \n", "permanent Judge of a High Court shall plead or act in any court or before any \n", "authority in India except the Supreme Court and the other High Courts. \n", "Explanation.— In this article, the expression “High Court” does not \n", "include a High Court for a State specified in Part B of the First Schedule as it \n", "existed before the commencement3 of the Constitution (Seventh Amendment) \n", "Act, 1956.] \n", "221. Salaries, etc., of Judges. —4[(1) There shall be paid to the Judges \n", "of each High Court such salaries as may be determined by Parliament by law \n", "and, until provision in that behalf is so made, such salaries as are specified in \n", "the Second Schedule.] \n", "(2) Every Judge shall be entitled to such allowances and to such rights in \n", "respect of leave of absence and pension as may from time to time be \n", "determined by or under law made by Parliament and, until so determined, to \n", "such allowances and rights as are specified in the Second Schedule: \n", "Provided that neither the allowances of a Judge nor his rights in respect \n", "to leave of absence or pension shall be varied to his disadvantage after his \n", "appointment. \n", "______________________________________________ \n", "1. The words \"in a State\" omitted by the Constitution (Seventh Amendment) Act, 1956, \n", "s. 29 and Sch. (w.e.f. 1-11-1956). \n", "2. Subs. by s. 13, ibid. (w.e.f. 1-11-1956). \n", "3. 1st November, 1956. \n", "4. Subs. by the Constitution (Fifty-fourth Amendment) Act, 1986, s. 3, for clause (1) \n", "(w.e.f. 1-4-1986). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part XXI. —Temporary, Transitional and Special Provisions) 246\n", "(b) identification of posts or classes of posts under the State \n", "Government and in any body or organisation under the control of the \n", "State Government in the Hyderabad-Karnataka region and reservation of \n", "a proportion of such posts for persons who belong to that region by birth \n", "or by domicile and for appointment thereto by direct recruitment or by \n", "promotion or in any other manner as may be specified in the order.] \n", "372. Continuance in force of existing laws and their adaptation.— (1) \n", "Notwithstanding the repeal by this Constitution of the enactments referred to in \n", "article 395 but subject to the other provisions of this Constitution, all the law in \n", "force in the territory of India immediately before the commencement of this \n", "Constitution shall continue in force therein until altered or repealed or amended \n", "by a competent Legislature or other competent authority. \n", "(2) For the purpose of bringing the provisions of any law in force in the \n", "territory of India into accord with the provisions of this Constitution, the \n", "President may by order make such adaptations and modifications of such law, \n", "whether by way of repeal or amendment, as may be necessary or expedient, and \n", "provide that the law shall, as from such date as may be specified in the order, \n", "have effect subject to the adaptations and modifications so made, and any such \n", "adaptation or modification shall not be questioned in any court of law. \n", "(3) Nothing in clause (2) shall be deemed— \n", "(a) to empower the President to make any adaptation or \n", "modification of any law after the expiration of 1[three years] from the \n", "commencement of this Constitution; or \n", "(b) to prevent any competent Legislature or other competent \n", "authority from repealing or amending any law adapted or modified by \n", "the President under the said clause. \n", "______________________________________________ \n", " See the Adaptation of Laws Order, 1950, dated the 26th January, 1950, Gazette of \n", "India, Extraordinary, p. 449, as amended by notification No. S.R.O. 115, dated the 5th \n", "June, 1950, Gazette of India, Extraordinary, Part II, Section 3, p. 51, notification No. \n", "S.R.O. 870, dated the 4th November, 1950, Gazette of India, Extraordinary, Part II, \n", "Section 3, p. 903, notification No. S.R.O. 508, dated the 4th April, 1951, Gazette of \n", "India, Extraordinary, Part II, Section 3, p. 287, notification No. S.R.O. 1140B, dated \n", "the 2nd July, 1952, Gazette of India, Extraordinary, Part II, Section 3, p. 616/1, and the \n", "Adaptation of the Travancore-Cochin Land Acquisition Laws Order, 1952, dated the \n", "20th November, 1952, Gazette of India, Extraordinary, Part II, Section 3, p. 923. \n", "1. Subs. by the Constitution (First Amendment) Act, 1951, s. 12 for \"two years\" \n", "(w.e.f. 18-6-1951). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part III.—Fundamental Rights) 10\n", "(e) to reside and settle in any part of the territory of India; 1[and] \n", "2[(f)* * * * *] \n", "(g) to practise any profession, or to carry on any occupation, trade or \n", "business. \n", "3[(2) Nothing in sub-clause ( a) of clause (1) shall affect the operation of \n", "any existing law, or prevent the State from making any law, in so far as such \n", "law imposes reasonable restrictions on the exercise of the right conferred by the \n", "said sub-clause in the interests of 4[the sovereignty and integrity of India], the \n", "security of the State, friendly relations with foreign States, public order, \n", "decency or morality, or in relation to contempt of court, defamation or \n", "incitement to an offence.] \n", "(3) Nothing in sub-clause ( b) of the said clause shall affect the operation \n", "of any existing law in so far as it imposes, or prevent the State from making \n", "any law imposing, in the interests of 4[the sovereignty and integrity of India or] \n", "public order, reasonable restrictions on the exercise of the right conferred by \n", "the said sub-clause. \n", "(4) Nothing in sub-clause ( c) of the said clause shall affect the operation \n", "of any existing law in so far as it imposes, or prevent the State from making \n", "any law imposing, in the interests of 4[the sovereignty and integrity of India or] \n", "public order or morality, reasonable restrictions on the exercise of the right \n", "conferred by the said sub-clause. \n", "(5) Nothing in 5[sub-clauses ( d) and (e)] of the said clause shall affect \n", "the operation of any existing law in so far as it imposes, or prevent the State \n", "from making any law imposing, reasonable restrictions on the exercise of any \n", "of the rights conferred by the said sub-clauses either in the interests of the \n", "general public or for the protection of the interests of any Scheduled Tribe. \n", "______________________________________________ \n", "1. Ins. by the Constitution (Forty-fourth Amendment) Act, 1978, s. 2 (w.e.f. 20-6-1979). \n", "2. Sub-clause (f) o mitted by s.2, ibid. (w.e.f. 20-6-1979). \n", "3. Subs. by the Constitution (First Amendment) Act, 1951, s. 3, for cl. (2) (with retrospective \n", "effect). \n", "4. Ins. by the Constitution (Sixteenth Amendment) Act, 1963, s. 2 (w.e.f. 5-10-1963). \n", "5. Subs. by the Constitution (Forty-fourth Amendment) Act, 1978, s. 2, for \"sub-clauses \n", "(d), (e) and ( f)\" (w.e.f. 20-6-1979). \n", "==========================================================================\n", " 228PART XX \n", "AMENDMENT OF THE CONSTITUTION \n", "368. 1[Power of Parliament to amend the Constitution and \n", "procedure therefor].— 2[(1) Notwithstanding anything in this Constitution, \n", "Parliament may in exercise of its constituent power amend by way of addition, \n", "variation or repeal any provision of this Constitution in accordance with the \n", "procedure laid down in this article.] \n", "3[(2)] An amendment of this Constitution may be initiated only by the \n", "introduction of a Bill for the purpose in either House of Parliament, and when \n", "the Bill is passed in each House by a majority of the total membership of that \n", "House and by a majority of not less than two-thirds of the members of that \n", "House present and voting, 4[it shall be presented to the President who shall give \n", "his assent to the Bill and thereupon] the Constitution shall stand amended in \n", "accordance with the terms of the Bill: \n", "Provided that if such amendment seeks to make any change in— \n", " (a) article 54, article 55, article 73, 5[ article 162, article 241 or article \n", "279A]; or \n", " (b) Chapter IV of Part V, Chapter V of Part VI, or Chapter I of Part XI; or \n", " (c) any of the Lists in the Seventh Schedule; or \n", " (d) the representation of States in Parliament; or \n", " (e) the provisions of this article, \n", "______________________________________________ \n", "1. Marginal heading subs. by the Constitution (Twenty-fourth Amendment) Act, 1971, s. 3, \n", "for \"Procedure for amendment of the Constitution\" (w.e.f. 5-11-1971). \n", "2. Ins. by s. 3, ibid. (w.e.f. 5-11-1971). \n", "3. Art. 368 re-numbered as cl. (2) thereof by s. 3, ibid. (w.e.f. 5-11-1971). \n", "4. Subs. by s. 3, ibid., (w.e.f. 5-11-1971). \n", "5. Subs. by the Constitution (One Hundred and First Amendment) Act, 2016, s. 15, for the \n", "words and figures \"article 162 or article 241\" (w.e.f. 16-9-2016). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part XXI. —Temporary, Transitional and Special Provisions) 240\n", "(5) The Order of the Administrative Tribunal finally disposing of any \n", "case shall become effective upon its confirmation by the State Government or \n", "on the expiry of three months from the date on which the order is made, \n", "whichever is earlier: \n", "Provided that the State Government may, by special order made in \n", "writing and for reasons to be specified therein, modify or annul any order of the \n", "Administrative Tribunal before it becomes effective and in such a case, the \n", "order of the Administrative Tribunal shall have effect only in such modified \n", "form or be of no effect, as the case may be. \n", "(6) Every special order made by the State Government under the proviso \n", "to clause (5) shall be laid, as soon as may be after it is made, before both \n", "Houses of the State Legislature. \n", "(7) The High Court for the State shall not have any powers of \n", "superintendence over the Administrative Tribunal and no court (other than the \n", "Supreme Court) or tribunal shall exercise any jurisdiction, power or authority in \n", "respect of any matter subject to the jurisdiction, power or authority of, or in \n", "relation to, the Administrative Tribunal. \n", "(8) If the President is satisfied that the continued existence of the \n", "Administrative Tribunal is not necessary, the President may by order abolish \n", "the Administrative Tribunal and make such provisions in such order as he may \n", "deem fit for the transfer and disposal of cases pending before the Tribunal \n", "immediately before such abolition. \n", "(9) Notwithstanding any judgment, decree or order of any court, tribunal \n", "or other authority,— \n", "(a) no appointment, posting, promotion or transfer of any person— \n", "(i) made before the 1st day of November, 1956, to any post \n", "under the Government of, or any local authority within, the State \n", "of Hyderabad as it existed before that date; or \n", "(ii) made before the commencement of the Constitution \n", "(Thirty-second Amendment) Act, 1973, to any post under the \n", "Government of, or any local or other authority within, the State of \n", "Andhra Pradesh; and \n", "(b) no action taken or thing done by or before any person referred to \n", "in sub-clause ( a), \n", "______________________________________________ \n", " In P. Sambamurthy and Others Vs. State of Andhra Pradesh and Others (1987) \n", "1 S.C.C. 362, the Supreme Court declared cl. (5) of art. 371D along with the proviso to \n", "be unconstitutional and vo id. \n", " \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Seventh Schedule) \n", " 314\n", "64. Institutions for scientific or technical education financed by the \n", "Government of India wholly or in part and declared by Parliament by law to be \n", "institutions of national importance. \n", "65. Union agencies and institutions for— \n", "(a) professional, vocational or technical training, including the \n", "training of police officers; or \n", "(b) the promotion of special studies or research; or \n", "(c) scientific or technical assistance in the investigation or detection \n", "of crime. \n", "66. Co-ordination and determination of standards in institutions for higher \n", "education or research and scientific and technical institutions. \n", "67. Ancient and historical monuments and records, and archaeological \n", "sites and remains, 1[declared by or under law made by Parliament] to be of \n", "national importance. \n", "68. The Survey of India, the Geological, Botanical, Zoological and \n", "Anthropological Surveys of India; Meteorological organisations. \n", "69. Census. \n", "70. Union Public Service; All-India Services; Union Public Service \n", "Commission. \n", "71. Union pensions, that is to say, pensions payable by the Government of \n", "India or out of the Consolidated Fund of India. \n", "72. Elections to Parliament, to the Legislatures of States and to the offices \n", "of President and Vice-President; the Election Commission. \n", "73. Salaries and allowances of members of Parliament, the Chairman and \n", "Deputy Chairman of the Council of States and the Speaker and Deputy Speaker \n", "of the House of the People. \n", "74. Powers, privileges and immunities of each House of Parliament and of \n", "the members and the Committees of each House; enforcement of attendance of \n", "persons for giving evidence or producing documents before committees of \n", "Parliament or commissions appointed by Parliament. \n", "75. Emoluments, allowances, privileges, and rights in respect of leave of \n", "absence, of the President and Governors; salaries and allowances of the \n", "Ministers for the Union; the salaries, allowances, and rights in respect of leave \n", "of absence and other conditions of service of the Comptroller and Auditor-\n", "General of India. \n", "______________________________________________ \n", "1. Subs. by the Constitution (Seventh Amendment) Act, 1956, s. 27, for \"declared by \n", "Parliament by law\" (w.e.f. 1-11-1956). \n", "==========================================================================\n", " 276FIFTH SCHEDULE \n", "[Article 244(1)] \n", "Provisions as to the Administration and Control of Scheduled Areas and \n", "Scheduled Tribes \n", "PART A \n", "GENERAL \n", "1. Interpretation .—In this Schedule, unless the context otherwise \n", "requires, the expression “State” 1*** does not include the 2[States of Assam \n", "3[, 4[Meghalaya, Tripura and Mizoram.]]] \n", "2. Executive power of a State in Scheduled Areas.— Subject to the \n", "provisions of this Schedule, the executive power of a State extends to the \n", "Scheduled Areas therein. \n", "3. Report by the Governor 5*** to the President regarding the \n", "administration of Scheduled Areas.— The Governor 5*** of each State having \n", "Scheduled Areas therein shall annually, or whenever so required by the President, \n", "make a report to the President regarding the administration of the Scheduled \n", "Areas in that State and the executive power of the Union shall extend to the \n", "giving of directions to the State as to the administration of the said areas. \n", "PART B \n", "ADMINISTRATION AND CONTROL OF SCHEDULED AREAS AND \n", "SCHEDULED TRIBES \n", "4. Tribes Advisory Council.—( 1) There shall be established in each \n", "State having Scheduled Areas therein and, if the President so directs, also in \n", "any State having Scheduled Tribes but not Scheduled Areas therein, a Tribes \n", "Advisory Council consisting of not more than twenty members of whom, as \n", "nearly as may be, three-fourths shall be the representatives of the Scheduled \n", "Tribes in the Legislative Assembly of the State: \n", "______________________________________________ \n", "1. The words and letters \"means a State specified in Part A or Part B of the First \n", "Schedule but\" omitted by the Constitution (Seventh Amendment) Act, 1956, s. 29 and \n", "Sch. (w.e.f. 1-11-1956). \n", "2. Subs. by the North-Eastern Areas (Reorganisation) Act, 1971 (81 of 1971), s. 71, for \n", "\"State of Assam\" (w.e.f. 21-1-1972). \n", "3. Subs. by the Constitution (Forty-ninth Amendment) Act, 1984, s. 3, for \"and \n", "Meghalaya\" (w.e.f. 1-4-1985). \n", "4. Subs. by the State of Mizoram Act, 1986 (34 of 1986), s. 39, for \"Meghalaya and \n", "Tripura\" (w.e.f. 20-2-1987). \n", "5. The words \"or Rajpramukh\" omitted by the Constitution (Seventh Amendment) Act, \n", "1956, s. 29 and Sch. (w.e.f. 1-11-1956). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Fifth Schedule) 278\n", "(c) regulate the carrying on of business as money-lender by \n", "persons who lend money to members of the Scheduled Tribes in such \n", "area. \n", "(3) In making any such regulation as is referred to in sub-paragraph (2) \n", "of this paragraph, the Governor 1*** may repeal or amend any Act of \n", "Parliament or of the Legislature of the State or any existing law which is for the \n", "time being applicable to the area in question. \n", "(4) All regulations made under this paragraph shall be submitted \n", "forthwith to the President and, until assented to by him, shall have no effect. \n", "(5) No regulation shall be made under this paragraph unless the \n", "Governor 1** making the regulation has, in the case where there is a Tribes \n", "Advisory Council for the State, consulted such Council. \n", "PART C \n", "SCHEDULED AREAS \n", "6. Scheduled Areas .—(1) In this Constitution, the expression \n", "“Scheduled Areas” means such areas as the President may by order declare to \n", "be Scheduled Areas. \n", "(2) The President may at any time by order— \n", "(a) direct that the whole or any specified part of a Scheduled Area \n", "shall cease to be a Scheduled Area or a part of such an area; \n", "2[(aa) increase the area of any Scheduled Area in a State after \n", "consultation with the Governor of that State;] \n", "(b) alter, but only by way of rectification of boundaries, any \n", "Scheduled Area; \n", "______________________________________________ \n", "1. The words \"or Rajpramukh\" omitted by the Constitution (Seventh Amendment) Act, \n", "1956, s. 29 and Sch. (w.e.f. 1-11-1956). \n", " See the Scheduled Areas (Part A States) Order, 1950 (C.O. 9), the Scheduled Areas \n", "(Part B States) Order, 1950 (C.O.26), the Scheduled Areas (Himachal Pradesh) Order, \n", "1975 (C.O. 102) and the Scheduled Areas (States of Bihar, Gujarat, Madhya Pradesh \n", "and Orissa) Order, 1977 (C.O. 109). \n", " See the Madras Scheduled Areas (Cessor) Order, 1950 (C.O. 30) and the Andhra \n", "Scheduled Areas (Cessor) Order, 1955 (C.O. 50). \n", "2. Ins. by the Fifth Schedule to the Constitution (Amendment) Act, 1976 (101 of 1976), \n", "s. 2 (w.e.f. 7-9-1976). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Seventh Schedule) \n", " 316\n", "86. Taxes on the capital value of the assets, exclusive of agricultural land, \n", "of individuals and companies; taxes on the capital of companies. \n", "87. Estate duty in respect of property other than agricultural land. \n", "88. Duties in respect of succession to property other than agricultural land. \n", "89. Terminal taxes on goods or passengers, carried by railway, sea or air; \n", "taxes on railway fares and freights. \n", "90. Taxes other than stamp duties on transactions in stock exchanges and \n", "futures markets. \n", "91. Rates of stamp duty in respect of bills of exchange, cheques, \n", "promissory notes, bills of lading, letters of credit, policies of insurance, transfer \n", "of shares, debentures, proxies and receipts. \n", "1[92. * * * * * *] \n", "2[92A. Taxes on the sale or purchase of goods other than newspapers, \n", "where such sale or purchase takes place in the course of inter-State trade or \n", "commerce.] \n", "3[92B. Taxes on the consignments of goods (whether the consignment is to \n", "the person making it or to any other person), where such consignment takes \n", "place in the course of inter-State trade or commerce.] \n", "4[92C. * * * * * *] \n", "93. Offences against laws with respect to any of the matters in this List. \n", "94. Inquires, surveys and statistics for the purpose of any of the matters in \n", "this List. \n", "95. Jurisdiction and powers of all courts, except the Supreme Court, with \n", "respect to any of the matters in this List; admiralty jurisdiction. \n", "96. Fees in respect of any of the matters in this List, but not including fees \n", "taken in any court. \n", "97. Any other matter not enumerated in List II or List III including any tax \n", "not mentioned in either of those Lists. \n", "______________________________________________ \n", "1. Entry 92 omitted by the Constitution (One Hundred and First Amendment) Act, 2016, \n", "s. 17(a)(ii) (w.e.f. 16-9-2016). \n", "2. Ins. by the Constitution (Sixth Amendment) Act, 1956, s. 2 (w.e.f. 11-9-1956). \n", "3. Ins.by the Constitution (Forty-sixth Amendment) Act, 1982, s. 5 (w.e.f. 2-2-1983). \n", "4. Entry 92C was ins. by the Constitution (Eighty-eighth Amendment) Act, 2003, s. 4 \n", "(date not notified) and omitted by the Constitution (One Hundred and First \n", "Amendment) Act, 2016, s. 17( a)(ii) (w.e.f. 16-9-2016). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part III.—Fundamental Rights) 7\n", "(a) access to shops, public restaurants, hotels and places of public \n", "entertainment; or \n", "(b) the use of wells, tanks, bathing ghats, roads and places of \n", "public resort maintained wholly or partly out of State funds or dedicated \n", "to the use of the general public. \n", "(3) Nothing in this article shall prevent the State from making any \n", "special provision for women and children. \n", "1[(4) Nothing in this article or in clause (2) of article 29 shall prevent the \n", "State from making any special provision for the advancement of any socially \n", "and educationally backward classes of citizens or for the Scheduled Castes and \n", "the Scheduled Tribes.] \n", "2[(5) Nothing in this article or in sub-clause ( g) of clause (1) of article 19 \n", "shall prevent the State from making any special provision, by law, for the \n", "advancement of any socially and educationally backward classes of citizens or \n", "for the Scheduled Castes or the Scheduled Tribes in so far as such special \n", "provisions relate to their admission to educational institutions including private \n", "educational institutions, whether aided or unaided by the State, other than the \n", "minority educational institutions referred to in clause (1) of article 30.] \n", "3[(6) Nothing in this article or sub-clause ( g) of clause (1) of article 19 or \n", "clause (2) of article 29 shall prevent the State from making,— \n", "(a) any special provision for the advancement of any \n", "economically weaker sections of citizens other than the classes \n", "mentioned in clauses (4) and (5); and \n", "(b) any special provision for the advancement of any \n", "economically weaker sections of citizens other than the classes \n", "mentioned in clauses (4) and (5) in so far as such special provisions \n", "relate to their admission to educational institutions including private \n", "educational institutions, whether aided or unaided by the State, other \n", "than the minority educational institutions referred to in clause (1) of \n", "article 30, which in the case of reservation would be in addition to the \n", "existing reservations and subject to a maximum of ten per cent. of the \n", "total seats in each category. \n", "______________________________________________ \n", "1. Added by the Constitution (First Amendment) Act, 1951, s. 2 (w.e.f. 18-6-1951). \n", "2. Ins. by the Constitution (Ninety-third Amendment) Act, 2005, s. 2 (w.e.f. 20-1-2006). \n", "3. Ins. by the Constitution (One Hundred and Third Amendment) Act, 2019, s. 2 \n", "(w.e.f. 14-1-2019). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Appendix I) \n", " 369\n", " \n", "1 2 3 4 5 6 \n", "48. (i) Paschim \n", "Masaldanga Dinhata Bhurungamari 4 29.49 \n", " (ii) Paschim \n", "Masaldanga (Fragment) Dinhata Bhurungamari 4 \n", "49. (i) Purba Chhit \n", "Masaldanga Dinhata Bhurungamari 10 35.01 \n", " (ii) Purba Chhit \n", "Masaldanga (Fragment) Dinhata Bhurungamari 10 \n", "50. (i) Purba Masaldanga Dinhata Bhurungamari 11 153.89 \n", " (ii) Purba Masaldanga \n", "(Fragment) Dinhata Bhurungamari 11 \n", "51. (i) Uttar Dhaldanga Tufanganj Bhurungamari 14 24.98 \n", " (ii) Uttar Dhaldanga \n", "(Fragment) Tufanganj Bhurungamari 14 \n", " (iii) Uttar Dhaldanga \n", "(Fragment) Tufanganj Bhurungamari 14 \n", " Total Area 7,110.02 \n", " \n", "The above given details of enclaves have been jointly compared and \n", "reconciled with records held by India and Bangladesh during the Indo-\n", "Bangladesh Conference held at Calcutta during 9th—12th October, 1996 as well as \n", "during joint field inspection at Jalpaiguri (West Bengal) – Panchagarh (Bangladesh) \n", "sector during 21—24 November, 1996. \n", " \n", "Brig. J.R. Peter \n", "Director Land Records & Survey ( Ex \n", "officio) West Bengal, India & Director, \n", "Eastern Circle Survey of India, \n", "Calcutta. Md. Shafi Uddin \n", "Director General, Land Records \n", "and Surveys, Bangladesh. \n", " \n", " \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Second Schedule) 266\n", "Court under clause (1) of article 374, or \n", "(b) was holding office as any other Judge of the Federal Court and \n", "has on such commencement become a Judge (other than the Chief \n", "Justice) of the Supreme Court under the said clause, \n", "during the period he holds office as such Chief Justice or other Judge, and \n", "every Judge who so becomes the Chief Justice or other Judge of the Supreme \n", "Court shall, in respect of time spent on actual service as such Chief Justice or \n", "other Judge, as the case may be, be entitled to receive in addition to the salary \n", "specified in sub-paragraph (1) of this paragraph as special pay an amount \n", "equivalent to the difference between the salary so specified and the salary \n", "which he was drawing immediately before such commencement. \n", "(4) Every Judge of the Supreme Court shall receive such reasonable \n", "allowances to reimburse him for expenses incurred in travelling on duty within \n", "the territory of India and shall be afforded such reasonable facilities in \n", "connection with travelling as the President may from time to time prescribe. \n", "(5) The rights in respect of leave of absence (including leave allowances) \n", "and pension of the Judges of the Supreme Court shall be governed by the \n", "provisions which, immediately before the commencement of this Constitution, \n", "were applicable to the Judges of the Federal Court. \n", "10. (1) 1[There shall be paid to the Judges of High Courts, in respect of time \n", "spent on actual service, salary at the following rates per mensem, that is to say,— \n", "The Chief Justice .. 2[9,000 rupees] \n", "Any other Judge .. 3[8,000 rupees]: \n", "Provided that if a Judge of a High Court at the time of his appointment is in \n", "receipt of a pension (other than a disability or wound pension) in respect of any \n", "______________________________________________ \n", "1. Subs. by the Constitution (Seventh Amendment) Act, 1956, s. 25(c)(i), for sub-\n", "paragraph (1) (w.e.f. 1-11-1956). \n", "2. Subs. by the Constitution (Fifty-fourth Amendment) Act, 1986, s. 4, for \"4,000 rupees\" \n", "(w.e.f. 1-4-1986). \n", " Now two lakh fifty thousand rupees, vide the High Court and Supreme Court Judges \n", "(Salaries and Conditions of Service) Amendment Act, 2018 (10 of 2018), s. 2 \n", "(w.e.f. 1-1-2016). \n", "3. Subs. by the Constitution (Fifty-fourth Amendment) Act, 1986, s. 4, for \"3,500 rupees\" \n", "(w.e.f. 1-4-1986). \n", " Now two lakh twenty-five thousand rupees, vide the High Court and Supreme Court \n", "Judges (Salaries and Conditions of Service) Amendment Act, 2018 (10 of 2018), s. 2 \n", "(w.e.f. 1-1-2016). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part XXI. —Temporary, Transitional and Special Provisions) 243\n", "(i) the High Court functioning as such immediately before the \n", "appointed day in the territories comprised in the State of Sikkim shall, on \n", "and from the appointed day, be deemed to be the High Court for the \n", "State of Sikkim; \n", "(j) all courts of civil, criminal and revenue jurisdiction, all authorities and \n", "all officers, judicial, executive and ministerial, throughout the territory of the \n", "State of Sikkim shall continue on and from the appointed day to exercise \n", "their respective functions subject to the provisions of this Constitution; \n", "(k) all laws in force immediately before the appointed day in the \n", "territories comprised in the State of Sikkim or any part thereof shall \n", "continue to be in force therein until amended or repealed by a competent \n", "Legislature or other competent authority; \n", "(l) for the purpose of facilitating the application of any such law as is \n", "referred to in clause ( k) in relation to the administration of the State of \n", "Sikkim and for the purpose of bringing the provisions of any such law \n", "into accord with the provisions of this Constitution, the President may, \n", "within two years from the appointed day, by order, make such \n", "adaptations and modifications of the law, whether by way of repeal or \n", "amendment, as may be necessary or expedient, and thereupon, every \n", "such law shall have effect subject to the adaptations and modifications so \n", "made, and any such adaptation or modification shall not be questioned in \n", "any court of law; \n", "(m) neither the Supreme Court nor any other court shall have \n", "jurisdiction in respect of any dispute or other matter arising out of any \n", "treaty, agreement, engagement or other similar instrument relating to \n", "Sikkim which was entered into or executed before the appointed day and \n", "to which the Government of India or any of its predecessor Governments \n", "was a party, but nothing in this clause shall be construed to derogate \n", "from the provisions of article 143; \n", "(n) the President may, by public notification, extend with such restrictions \n", "or modifications as he thinks fit to the State of Sikkim any enactment which \n", "is in force in a State in India at the date of the notification; \n", "(o) if any difficulty arises in giving effect to any of the foregoing \n", "provisions of this article, the President may, by order, do anything \n", "(including any adaptation or modification of any other article) which \n", "appears to him to be necessary for the purpose of removing that \n", "difficulty: \n", "______________________________________________ \n", " See the Constitution (Removal of Difficulties) Order No. XI (C.O. 99). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Fifth Schedule) 277\n", "Provided that if the number of representatives of the Scheduled Tribes in \n", "the Legislative Assembly of the State is less than the number of seats in the \n", "Tribes Advisory Council to be filled by such representatives, the remaining \n", "seats shall be filled by other members of those tribes. \n", "(2) It shall be the duty of the Tribes Advisory Council to advise on such \n", "matters pertaining to the welfare and advancement of the Scheduled Tribes in \n", "the State as may be referred to them by the Governor 1***. \n", "(3) The Governor 2*** may make rules prescribing or regulating, as the \n", "case may be,— \n", "(a) the number of members of the Council, the mode of their \n", "appointment and the appointment of the Chairman of the Council and of \n", "the officers and servants thereof; \n", "(b) the conduct of its meetings and its procedure in general; and \n", "(c) all other incidental matters. \n", "5. Law applicable to Scheduled Areas. —(1) Notwithstanding anything \n", "in this Constitution, the Governor 1*** may by public notification direct that \n", "any particular Act of Parliament or of the Legislature of the State shall not \n", "apply to a Scheduled Area or any part thereof in the State or shall apply to a \n", "Scheduled Area or any part thereof in the State subject to such exceptions and \n", "modifications as he may specify in the notification and any direction given \n", "under this sub-paragraph may be given so as to have retrospective effect. \n", "(2) The Governor may make regulations for the peace and good \n", "government of any area in a State which is for the time being a Scheduled Area. \n", "In particular and without prejudice to the generality of the foregoing \n", "power, such regulations may— \n", "(a) prohibit or restrict the transfer of land by or among members \n", "of the Scheduled Tribes in such area; \n", "(b) regulate the allotment of land to members of the Scheduled \n", "Tribes in such area; \n", "______________________________________________ \n", "1. The words \"or Rajpramukh, as the case may be\" omitted by the Constitution (Seventh \n", "Amendment) Act, 1956, s. 29 and Sch. (w.e.f. 1-11-1956). \n", "2. The words \"or Rajpramukh\" omitted by s. 29 and Sch., ibid. (w.e.f. 1-11-1956). \n", "==========================================================================\n", "THE CONSTITUTION OF INDIA \n", "(Part XIX.—M ISCELLANEOUS ) 227\n", "(e) a tax on the supply of goods by any unincorporated \n", "association or body of persons to a member thereof for cash, \n", "deferred payment or other valuable consideration; \n", "(f) a tax on the supply, by way of or as part of any service \n", "or in any other manner whatsoever, of goods, being food or any \n", "other article for human consumption or any drink (whether or not \n", "intoxicating), where such supply or service, is for cash, deferred \n", "payment or other valuable consideration, \n", "and such transfer, delivery or supply of any goods shall be deemed to be \n", "a sale of those goods by the person making the transfer, delivery or \n", "supply and a purchase of those goods by the person to whom such \n", "transfer, delivery or supply is made;] \n", "1[(30) \"Union territory\" means any Union territory specified in the \n", "First Schedule and includes any other territory comprised within the \n", "territory of India but not specified in that Schedule.] \n", "367. Interpretation. —(1) Unless the context otherwise requires, the \n", "General Clauses Act, 1897, shall, subject to any adaptations and modifications \n", "that may be made therein under article 372, apply for the interpretation of this \n", "Constitution as it applies for the interpretation of an Act of the Legislature of \n", "the Dominion of India. \n", "(2) Any reference in this Constitution to Acts or laws of, or made by, \n", "Parliament, or to Acts or laws of, or made by, the Legislature of a State 2***, \n", "shall be construed as including a reference to an Ordinance made by the \n", "President or, to an Ordinance made by a Governor 3***, as the case may be. \n", "(3) For the purposes of this Constitution “foreign State” means any State \n", "other than India: \n", "Provided that, subject to the provisions of any law made by Parliament, \n", "the President may by order4 declare any State not to be a foreign State for such \n", "purposes as may be specified in the order. \n", "5[(4) * * * *] \n", "______________________________________________ \n", "1. Subs. by the Constitution (Seventh Amendment) Act, 1956, s. 29 and Sch. for cl. (30) \n", "(w.e.f. 1-11-1956). \n", "2. The words and letters \"specified in Part A or Part B of the First Schedule\" omitted by \n", "s. 29 and Sch., ibid. (w.e.f. 1-11-1956). \n", "3. The words \"or Rajpramukh\" omitted by s. 29 and Sch., ibid. (w.e.f. 1-11-1956). \n", "4. See the Constitution (Declaration as to Foreign States) Order, 1950 (C.O. 2). \n", "5. Added by the Constitution (Application to Jammu and Kashmir) Order, 2019 \n", "(C.O. 272)(w.e.f.5-8-2019). For the text of this C.O., s ee Appendix II. \n", "==========================================================================\n" ] } ], "source": [ "for idx in result[0][0]:\n", " print(pdf_text_dict[idx])\n", " print(\"==========================================================================\")" ] }, { "cell_type": "code", "execution_count": null, "id": "7eae8623-0b1d-4606-ba0c-e7d9b3db51f8", "metadata": {}, "outputs": [], "source": [ "index.search(query_embeddings, 5)" ] }, { "cell_type": "code", "execution_count": 7, "id": "b7431376-2ff8-4eab-bb71-467dce2d1032", "metadata": {}, "outputs": [], "source": [ "test_emb = test_emb.reshape(1, -1) # Reshape to (1, dimension)\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "c84de25d-194a-47c2-8481-801c8c64f320", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([[ 9.24338506e-41, 0.00000000e+00, -1.97645558e+34,\n", " 1.11390840e-38, -6.25416305e-08, 7.09057023e-43,\n", " -2.18818045e-16, 7.09057023e-43, 8.30269340e-42,\n", " 0.00000000e+00, nan, nan,\n", " 8.57594660e-43, 0.00000000e+00, 1.35631564e-19,\n", " 1.35631564e-19, 1.65943575e-07, 6.86198462e-07,\n", " 1.30291750e-11, 1.45852466e-19, 6.33692210e-10,\n", " 6.40969056e-10, 5.20015877e+22, 2.50378429e-12,\n", " 4.02852196e-11, 1.69701607e-07, 4.32033157e-05,\n", " 1.66864609e-07, 2.33013520e-09, 4.12557526e-08,\n", " 1.71538787e-07, 4.03717308e-08, 1.17036854e-19,\n", " 1.35631564e-19, 2.57977081e-06, 1.68751939e-07,\n", " 6.51968313e-10, 6.30808572e-10, 1.35671579e-19,\n", " 1.68018843e-04, 6.66505962e-10, 1.30285106e-11,\n", " 1.45859084e-19, 2.53488541e-09, 4.22524463e-05,\n", " 5.34819389e+22, 2.58910536e-12, 4.16379153e-11,\n", " 6.56483280e-07, 4.14877057e-08, 4.19508019e-08,\n", " 1.35558927e-19, 1.35631564e-19, 4.05010470e-11,\n", " 4.31995759e-05, 4.28928786e-08, 1.06798007e-05,\n", " 9.32054078e-09, 4.12548431e-08, 1.76624264e-04,\n", " 1.61487023e-07, 1.35671476e-19, 4.27199520e-05,\n", " 6.44607367e-10, 1.30296269e-11, 1.45868997e-19,\n", " 1.01393027e-08, 1.08015292e-05, 5.31902588e+22,\n", " 2.50400677e-12, 1.35631280e-19, 1.35631564e-19,\n", " 6.33692210e-10, 6.40969056e-10, 5.20015877e+22,\n", " 2.50378429e-12, 4.00462996e-11, 6.40969056e-10,\n", " 6.40969056e-10, 6.40900943e-10, 5.82533799e-10,\n", " 6.40968945e-10, 6.40969056e-10, 6.23532337e-10,\n", " 1.35671476e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 8.29056182e-33, 1.35631564e-19,\n", " 1.35631564e-19, 4.17187032e-08, 1.66900264e-07,\n", " 1.30289547e-11, 1.45878884e-19, 1.01411217e-08,\n", " 4.27246123e-05, 5.37724977e+22, 2.51821762e-12,\n", " 4.00462996e-11, 6.40969056e-10, 6.40969056e-10,\n", " 6.40900943e-10, 2.33013520e-09, 2.67057794e-06,\n", " 1.70894768e-04, 1.61486980e-07, 1.17036751e-19,\n", " 1.35631564e-19, 9.32053013e-09, 6.60092041e-07,\n", " 1.07996684e-05, 4.03717486e-08, 1.35671566e-19,\n", " 2.59286659e-09, 1.07405240e-05, 1.30280647e-11,\n", " 1.45875615e-19, 6.33734842e-10, 4.34435824e-05,\n", " 5.34808175e+22, 2.51810660e-12, 4.02736733e-11,\n", " 1.65033981e-07, 6.82502446e-07, 1.05605914e-05,\n", " 1.35558927e-19, 1.35631564e-19, 4.20926627e-11,\n", " 2.63669331e-09, 1.68748372e-07, 2.62192512e-09,\n", " 5.82533799e-10, 6.40968945e-10, 6.40969056e-10,\n", " 6.23532337e-10, 1.35671476e-19, 1.05011759e-05,\n", " 2.62259658e-09, 1.30298411e-11, 1.45875576e-19,\n", " 4.05599394e-08, 2.56427413e-09, 5.43719988e+22,\n", " 2.57500553e-12, 1.35631280e-19, 1.35631564e-19,\n", " 1.62239758e-07, 1.07400574e-05, 5.43696930e+22,\n", " 2.56073873e-12, 4.02736733e-11, 1.03137161e-08,\n", " 2.68548160e-06, 6.71212831e-07, 5.82533799e-10,\n", " 6.40968945e-10, 6.40969056e-10, 6.23532337e-10,\n", " 1.35671476e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 8.29056182e-33, 1.35631564e-19,\n", " 1.35631564e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 1.45849106e-19, 2.53488253e-09,\n", " 4.39185569e-05, 5.28962953e+22, 2.60342724e-12,\n", " 4.14105417e-11, 1.75685418e-04, 1.73755718e-04,\n", " 4.27192026e-05, 2.33013520e-09, 2.56410315e-09,\n", " 1.71571429e-07, 1.61487009e-07, 1.17036816e-19,\n", " 1.35631564e-19, 1.52707566e-04, 4.28855671e-08,\n", " 2.75975367e-06, 1.61486952e-07, 9.10475948e-12,\n", " 4.34352005e-05, 2.64054370e-06, 8.14268412e-13,\n", " 1.45855749e-19, 1.01393027e-08, 1.05032668e-05,\n", " 5.31925736e+22, 2.50389575e-12, 4.05010470e-11,\n", " 1.72798304e-04, 1.07225366e-08, 1.06798007e-05,\n", " 1.35558927e-19, 1.35631564e-19, 4.05010470e-11,\n", " 1.75659326e-04, 2.62552680e-06, 1.06798007e-05,\n", " 9.32054078e-09, 4.24843092e-05, 4.39223113e-05,\n", " 4.03717344e-08, 1.35671566e-19, 6.86125759e-07,\n", " 4.22487028e-05, 1.30285132e-11, 1.45875615e-19,\n", " 1.01397575e-08, 6.62910837e-10, 5.20050555e+22,\n", " 2.58904985e-12, 1.35631280e-19, 1.35631564e-19,\n", " 2.59566445e-06, 2.62219935e-09, 5.26022868e+22,\n", " 2.53231702e-12, 4.02736733e-11, 4.12576107e-08,\n", " 2.69535527e-09, 1.68969462e-04, 9.32054078e-09,\n", " 6.60092041e-07, 4.34436115e-05, 4.03717380e-08,\n", " 1.35671566e-19, 2.57831489e-09, 2.71481827e-06,\n", " 1.30291819e-11, 8.29188058e-33, 1.35631564e-19,\n", " 1.35631564e-19, 2.59286659e-09, 2.65544509e-06,\n", " 1.30296217e-11, 1.45875615e-19, 2.53505306e-09,\n", " 2.73012688e-06, 5.43697020e+22, 2.57483900e-12,\n", " 4.07284206e-11, 2.56438781e-09, 6.86169244e-07,\n", " 4.22423655e-05, 9.32054078e-09, 6.60092041e-07,\n", " 1.72473747e-07, 4.03717415e-08, 1.17036841e-19,\n", " 1.35631564e-19, 9.32053013e-09, 1.04883338e-08,\n", " 6.86213070e-07, 1.61487009e-07, 1.35671476e-19,\n", " 2.57831489e-09, 6.56483564e-07, 1.30289590e-11,\n", " 1.45872306e-19, 1.01393027e-08, 1.71852080e-04,\n", " 5.28882204e+22, 2.61763809e-12, 4.09557943e-11,\n", " 2.62231326e-09, 2.75998696e-06, 1.05605914e-05,\n", " 1.35558927e-19, 1.35631564e-19, 4.02736733e-11,\n", " 1.68744691e-07, 1.05025701e-05, 2.66995016e-06,\n", " 2.33013520e-09, 2.56410315e-09, 1.71571429e-07,\n", " 1.61487009e-07, 1.35671540e-19, 2.57831489e-09,\n", " 1.75685462e-04, 1.30285158e-11, 1.45872306e-19,\n", " 6.33720632e-10, 4.10274907e-08, 5.46671648e+22,\n", " 2.50400677e-12, 1.35631280e-19, 1.35631564e-19,\n", " 4.05590299e-08, 2.56421906e-09, 5.43731473e+22,\n", " 2.58921638e-12, 4.02736733e-11, 2.60776001e-09,\n", " 4.32023808e-05, 6.55481280e-10, 5.82533799e-10,\n", " 6.40968945e-10, 6.40969056e-10, 6.23532337e-10,\n", " 1.35671476e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 8.29056182e-33, 1.35631564e-19,\n", " 1.35631564e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 1.45849106e-19, 6.33692210e-10,\n", " 6.40969056e-10, 5.20015877e+22, 2.50378429e-12,\n", " 4.18652890e-11, 6.62839950e-10, 4.32061024e-05,\n", " 1.64077917e-07, 1.52707740e-04, 4.19551540e-08,\n", " 6.59272803e-10, 1.61487009e-07, 1.17036764e-19,\n", " 1.35631564e-19, 5.82533133e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.35671476e-19,\n", " 4.28828493e-08, 4.14940686e-08, 1.30287387e-11,\n", " 1.45849158e-19, 2.53488253e-09, 6.73781975e-10,\n", " 5.34854202e+22, 2.60342724e-12, 4.02736733e-11,\n", " 6.67542849e-07, 1.09805751e-05, 4.27192026e-05,\n", " 1.35558927e-19, 1.35631564e-19, 4.16379153e-11,\n", " 2.62546951e-06, 4.17259969e-08, 2.64014784e-06,\n", " 3.81769350e-05, 2.67051973e-06, 6.86198291e-07,\n", " 6.30808739e-10, 1.35671527e-19, 2.60742028e-09,\n", " 2.60758992e-09, 1.30287352e-11, 1.45852466e-19,\n", " 6.33692210e-10, 6.40969056e-10, 5.20015877e+22,\n", " 2.50378429e-12, 1.35631280e-19, 1.35631564e-19,\n", " 4.05572109e-08, 1.06047535e-08, 5.20073838e+22,\n", " 2.53220643e-12, 4.09557943e-11, 6.66435074e-10,\n", " 4.39148316e-05, 6.67487541e-07, 3.72821631e-08,\n", " 1.06804491e-05, 6.59187760e-10, 3.99060731e-08,\n", " 1.35671540e-19, 6.55492605e-10, 4.41541815e-05,\n", " 1.30291784e-11, 8.29150516e-33, 1.35631564e-19,\n", " 1.35631564e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 1.45849106e-19, 6.33692210e-10,\n", " 6.40969056e-10, 5.20015877e+22, 2.50378429e-12,\n", " 4.00462996e-11, 6.40969056e-10, 6.40969056e-10,\n", " 6.40900943e-10, 9.32054078e-09, 6.60092041e-07,\n", " 4.41597949e-05, 4.03717415e-08, 1.17036841e-19,\n", " 1.35631564e-19, 2.38605571e-06, 6.73739176e-10,\n", " 2.62214117e-09, 4.03717415e-08, 1.35671579e-19,\n", " 6.55492605e-10, 4.41541815e-05, 1.30291784e-11,\n", " 1.45865701e-19, 2.53528043e-09, 1.68755719e-07,\n", " 5.25988416e+22, 2.51821762e-12, 4.14105417e-11,\n", " 4.10238563e-08, 4.10247551e-08, 1.70876810e-04,\n", " 1.35558927e-19, 1.35631564e-19, 4.07284206e-11,\n", " 1.04897007e-08, 4.21898356e-08, 6.60036960e-07,\n", " 9.32054078e-09, 6.60092041e-07, 1.72473747e-07,\n", " 4.03717415e-08, 1.35671566e-19, 2.57831489e-09,\n", " 4.20084398e-05, 1.30287317e-11, 1.45872306e-19,\n", " 6.33706421e-10, 4.27273917e-05, 5.31856741e+22,\n", " 2.58921638e-12, 1.35631280e-19, 1.35631564e-19,\n", " 1.62228844e-07, 1.69937266e-04, 5.37771229e+22,\n", " 2.57506104e-12, 4.05010470e-11, 4.31995759e-05,\n", " 4.28928786e-08, 1.06798007e-05, 9.32054078e-09,\n", " 6.62796817e-10, 2.63709121e-09, 1.61487037e-07,\n", " 1.35671476e-19, 4.27199520e-05, 6.44607367e-10,\n", " 1.30296269e-11, 8.29169250e-33, 1.35631564e-19,\n", " 1.35631564e-19, 1.06799862e-05, 4.19606216e-08,\n", " 1.30293979e-11, 1.45849158e-19, 6.33692210e-10,\n", " 6.40969056e-10, 5.20015877e+22, 2.50378429e-12,\n", " 4.00462996e-11, 6.40969056e-10, 6.40969056e-10,\n", " 6.40900943e-10, 5.82533799e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.17036751e-19,\n", " 1.35631564e-19, 5.82533133e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.35671476e-19,\n", " 4.14858690e-08, 6.63861442e-07, 1.30296260e-11,\n", " 1.45852415e-19, 1.01411217e-08, 4.27246123e-05,\n", " 5.37724977e+22, 2.51821762e-12, 4.00462996e-11,\n", " 6.40969056e-10, 6.40969056e-10, 6.40900943e-10,\n", " 1.35558927e-19, 1.35631564e-19, 4.02736733e-11,\n", " 1.08599706e-05, 1.72480924e-07, 6.55481280e-10,\n", " 9.32054078e-09, 6.60092041e-07, 1.07996684e-05,\n", " 4.03717486e-08, 1.35671566e-19, 2.59286659e-09,\n", " 4.12612273e-08, 1.30293996e-11, 1.45875615e-19,\n", " 6.33720632e-10, 4.12594048e-08, 5.20096807e+22,\n", " 2.54647280e-12, 1.35631280e-19, 1.35631564e-19,\n", " 6.33706421e-10, 1.04894724e-08, 5.40676411e+22,\n", " 2.58921638e-12, 4.02736733e-11, 1.03137161e-08,\n", " 2.68548160e-06, 6.71212831e-07, 9.32054078e-09,\n", " 6.60092041e-07, 4.41597949e-05, 4.03717415e-08,\n", " 1.35671566e-19, 2.62529329e-06, 1.72813292e-04,\n", " 1.30285158e-11, 8.29056476e-33, 1.35631564e-19,\n", " 1.35631564e-19, 4.27199520e-05, 6.44607367e-10,\n", " 1.30296269e-11, 1.45868997e-19, 4.05572109e-08,\n", " 1.69002335e-04, 5.40722437e+22, 2.50400677e-12,\n", " 4.00462996e-11, 6.40969056e-10, 6.40969056e-10,\n", " 6.40900943e-10, 5.82533799e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.17036751e-19,\n", " 1.35631564e-19, 5.82533133e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.35671476e-19,\n", " 6.40940634e-10, 6.40969056e-10, 8.14240168e-13,\n", " 1.45849106e-19, 6.48944479e-07, 4.24908612e-05,\n", " 5.20062039e+22, 2.50378429e-12, 4.20926627e-11,\n", " 4.17241566e-08, 2.62570211e-06, 2.62192512e-09,\n", " 1.35558927e-19, 1.35631564e-19, 4.00462996e-11,\n", " 6.40969056e-10, 6.40969056e-10, 6.40900943e-10,\n", " 2.33013520e-09, 2.67057794e-06, 1.70894768e-04,\n", " 1.61486980e-07, 1.35671476e-19, 2.57831489e-09,\n", " 6.56483564e-07, 1.30289590e-11, 1.45872306e-19,\n", " 1.01393027e-08, 4.36782757e-05, 5.22979111e+22,\n", " 2.61763809e-12, 1.35631280e-19, 1.35631564e-19,\n", " 1.01397575e-08, 2.59298094e-09, 5.25930680e+22,\n", " 2.53226194e-12, 4.18652890e-11, 6.62839950e-10,\n", " 4.32061024e-05, 1.64077917e-07, 1.52707740e-04,\n", " 6.60121145e-07, 6.60121316e-07, 1.61486980e-07,\n", " 1.35671489e-19, 6.40940634e-10, 6.40969056e-10,\n", " 8.14240168e-13, 8.29056182e-33, 1.35631564e-19,\n", " 1.35631564e-19, 6.71224655e-07, 6.59187371e-10,\n", " 8.14295788e-13, 1.45852415e-19, 4.05599394e-08,\n", " 2.56427413e-09, 5.43719988e+22, 2.57500553e-12,\n", " 4.09673406e-11, 4.12548644e-08, 6.56440079e-07,\n", " 6.67487541e-07, 2.33013520e-09, 2.56410315e-09,\n", " 1.71571429e-07, 1.61487009e-07, 1.17036816e-19,\n", " 1.35631564e-19, 5.82533133e-10, 6.40968945e-10,\n", " 6.40969056e-10, 6.23532337e-10, 1.35671476e-19,\n", " 6.40940634e-10, 6.40969056e-10, 8.14240168e-13,\n", " 1.45849106e-19, 6.33692210e-10, 6.40969056e-10,\n", " 5.20015877e+22, 2.50378429e-12, 4.05010470e-11,\n", " 4.31995759e-05, 4.28928786e-08, 1.06798007e-05,\n", " 1.35558927e-19, 1.35631564e-19, 4.14105417e-11,\n", " 6.44735043e-10, 1.68044920e-04, 4.27192026e-05,\n", " 2.33013520e-09, 2.56410315e-09, 1.71571429e-07,\n", " 1.61487009e-07, 1.35671540e-19, 4.22431367e-05,\n", " 1.71859559e-04, 1.30282920e-11, 1.45852466e-19,\n", " 6.48988134e-07, 1.04301296e-08, 5.28870449e+22,\n", " 2.63184895e-12, 1.35631280e-19, 1.35631564e-19,\n", " 1.01393027e-08, 4.20121687e-05, 5.34865776e+22,\n", " 2.51805109e-12, 4.05010470e-11, 1.72798304e-04,\n", " 4.19615311e-08, 1.06798007e-05, 9.32054078e-09,\n", " 4.22458907e-05, 6.63875937e-07, 4.03717380e-08,\n", " 1.35671566e-19, 6.40940689e-10, 4.39167125e-05,\n", " 1.30287335e-11, 8.29169250e-33, 1.35631564e-19,\n", " 1.35631564e-19, 6.55492605e-10, 4.41541815e-05,\n", " 1.30291784e-11, 1.45865701e-19, 2.53488253e-09,\n", " 4.39185569e-05, 5.28962953e+22, 2.60342724e-12,\n", " 4.05010470e-11, 1.69009669e-04, 4.12630357e-08,\n", " 6.55481280e-10, 3.72821631e-08, 2.74479271e-06,\n", " 1.68029917e-04, 4.03717593e-08, 1.17036828e-19,\n", " 1.35631564e-19, 2.33013253e-09, 1.65033924e-07,\n", " 6.44735376e-10, 1.61487009e-07, 1.35671476e-19,\n", " 6.40940634e-10, 6.40969056e-10, 8.14240168e-13,\n", " 1.45849106e-19, 6.33692210e-10, 6.40969056e-10,\n", " 5.20015877e+22, 2.50378429e-12, 4.00462996e-11,\n", " 6.40969056e-10, 6.40969056e-10, 6.40900943e-10,\n", " 1.35558927e-19, 1.35631564e-19, 4.00462996e-11,\n", " 6.40969056e-10, 6.40969056e-10, 6.40900943e-10,\n", " 1.52707740e-04, 6.62811028e-10, 4.10220338e-08,\n", " 6.23532836e-10, 1.35671502e-19, 1.65943575e-07,\n", " 6.86198462e-07, 1.30291750e-11, 1.45852466e-19,\n", " 6.33692210e-10, 6.40969056e-10, 5.20015877e+22,\n", " 2.50378429e-12, 1.35631280e-19, 1.35631564e-19,\n", " 4.15305840e-05, 1.06643254e-08, 5.31925691e+22,\n", " 2.50400677e-12, 4.05010470e-11, 1.72798304e-04,\n", " 6.82502105e-07, 1.06798007e-05, 2.33013520e-09,\n", " 4.12566621e-08, 2.74473700e-06, 4.03717308e-08,\n", " 1.35671579e-19, 1.69926207e-04, 6.75109959e-07,\n", " 1.30285158e-11, 8.29056256e-33, 1.35631564e-19,\n", " 1.35631564e-19, 4.26500435e-08, 4.27218256e-05]], dtype=float32)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_emb" ] }, { "cell_type": "code", "execution_count": 9, "id": "048937c2-24a7-4116-8012-35809e1a9ca2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index Type: \n", "Index Dimension: 768\n", "Number of Vectors in Index: 10\n", "Query Shape: (1, 768)\n", "Is Index Trained: True\n" ] } ], "source": [ "print(\"Index Type:\", type(index))\n", "print(\"Index Dimension:\", index.d)\n", "print(\"Number of Vectors in Index:\", index.ntotal)\n", "print(\"Query Shape:\", test_emb.shape)\n", "print(\"Is Index Trained:\", index.is_trained)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "c764fbe2-b63e-4f54-8482-2a7a4663b1fe", "metadata": {}, "outputs": [], "source": [ "import faiss\n", "import numpy as np\n", "\n", "# Set the embedding dimension\n", "dimension = 768 \n", "num_vectors = 10 \n", "\n", "# Create random embeddings\n", "np.random.seed(42)\n", "embeddings = np.random.random((num_vectors, dimension)).astype('float32')\n", "\n", "# Create a FAISS index\n", "index = faiss.IndexFlatL2(dimension)\n", "index.add(embeddings)\n", "\n", "# Create a random query vector\n", "query_vector = np.random.random((1, dimension)).astype('float32')\n", "\n", "# Search in the index\n", "distances, indices = index.search(query_vector, 5)\n", "\n", "# Print results\n", "print(\"Search successful!\")\n", "print(\"Nearest Neighbors:\", indices)\n", "print(\"Distances:\", distances)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "9ac633d0-2683-4c9c-9cf0-ed48acc3c529", "metadata": {}, "outputs": [], "source": [ "index.search(test_emb, 5)" ] }, { "cell_type": "code", "execution_count": 102, "id": "3f73cab7-8937-4b35-9f97-73f2188675d9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "tensor([0.8617])" ] }, "execution_count": 102, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import torch\n", "\n", "torch.nn.functional.cosine_similarity(torch.tensor(temp_1[0]).unsqueeze(0), torch.tensor(temp_1[1]).unsqueeze(0))" ] }, { "cell_type": "code", "execution_count": 103, "id": "fdef611d-38fc-45e7-bf91-cb7856dd9ad7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "tensor([0.8617])" ] }, "execution_count": 103, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import torch\n", "\n", "torch.nn.functional.cosine_similarity(torch.tensor(temp_2[0]).unsqueeze(0), torch.tensor(temp_2[1]).unsqueeze(0))" ] }, { "cell_type": "code", "execution_count": 77, "id": "736151bb-9546-4909-b92c-04dbcd541a02", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "13.994422" ] }, "execution_count": 77, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "\n", "np.linalg.norm(embeddings[0])" ] }, { "cell_type": "code", "execution_count": null, "id": "ec3251c7-3a81-47b7-8e56-66851784b84f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "7dd5610f-aafa-492d-9300-8eb8db72092d", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "8f89f401-f7c3-4e23-87e2-424d661a7fc5", "metadata": {}, "outputs": [], "source": [] } ], "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": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }