mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
Fixed source key name for docugami loader (#8598)
The Docugami loader was not returning the source metadata key. This was triggering this exception when used with retrievers, per https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/schema/prompt_template.py#L193C1-L195C41 The fix is simple and just updates the metadata key name for the document each chunk is sourced from, from "name" to "source" as expected. I tested by running the python notebook that has an end to end scenario in it. Tagging DataLoader maintainers @rlancemartin @eyurtsev
This commit is contained in:
Bagatur
GitHub
commit
e2e582f1f6
@ -15,14 +15,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# You need the lxml package to use the DocugamiLoader\n",
|
||||
"!pip install lxml"
|
||||
"# You need the lxml package to use the DocugamiLoader (run pip install directly without \"poetry run\" if you are not using poetry)\n",
|
||||
"!poetry run pip install lxml --quiet"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -75,25 +75,25 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='MUTUAL NON-DISCLOSURE AGREEMENT This Mutual Non-Disclosure Agreement (this “ Agreement ”) is entered into and made effective as of April 4 , 2018 between Docugami Inc. , a Delaware corporation , whose address is 150 Lake Street South , Suite 221 , Kirkland , Washington 98033 , and Caleb Divine , an individual, whose address is 1201 Rt 300 , Newburgh NY 12550 .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:ThisMutualNon-disclosureAgreement', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'ThisMutualNon-disclosureAgreement'}),\n",
|
||||
" Document(page_content='The above named parties desire to engage in discussions regarding a potential agreement or other transaction between the parties (the “Purpose”). In connection with such discussions, it may be necessary for the parties to disclose to each other certain confidential information or materials to enable them to evaluate whether to enter into such agreement or transaction.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Discussions', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Discussions'}),\n",
|
||||
" Document(page_content='In consideration of the foregoing, the parties agree as follows:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Consideration', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Consideration'}),\n",
|
||||
" Document(page_content='1. Confidential Information . For purposes of this Agreement , “ Confidential Information ” means any information or materials disclosed by one party to the other party that: (i) if disclosed in writing or in the form of tangible materials, is marked “confidential” or “proprietary” at the time of such disclosure; (ii) if disclosed orally or by visual presentation, is identified as “confidential” or “proprietary” at the time of such disclosure, and is summarized in a writing sent by the disclosing party to the receiving party within thirty ( 30 ) days after any such disclosure; or (iii) due to its nature or the circumstances of its disclosure, a person exercising reasonable business judgment would understand to be confidential or proprietary.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Purposes/docset:ConfidentialInformation-section/docset:ConfidentialInformation[2]', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ConfidentialInformation'}),\n",
|
||||
" Document(page_content=\"2. Obligations and Restrictions . Each party agrees: (i) to maintain the other party's Confidential Information in strict confidence; (ii) not to disclose such Confidential Information to any third party; and (iii) not to use such Confidential Information for any purpose except for the Purpose. Each party may disclose the other party’s Confidential Information to its employees and consultants who have a bona fide need to know such Confidential Information for the Purpose, but solely to the extent necessary to pursue the Purpose and for no other purpose; provided, that each such employee and consultant first executes a written agreement (or is otherwise already bound by a written agreement) that contains use and nondisclosure restrictions at least as protective of the other party’s Confidential Information as those set forth in this Agreement .\", metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Obligations/docset:ObligationsAndRestrictions-section/docset:ObligationsAndRestrictions', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ObligationsAndRestrictions'}),\n",
|
||||
" Document(page_content='3. Exceptions. The obligations and restrictions in Section 2 will not apply to any information or materials that:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Exceptions/docset:Exceptions-section/docset:Exceptions[2]', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Exceptions'}),\n",
|
||||
" Document(page_content='(i) were, at the date of disclosure, or have subsequently become, generally known or available to the public through no act or failure to act by the receiving party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheDate/docset:TheDate', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheDate'}),\n",
|
||||
" Document(page_content='(ii) were rightfully known by the receiving party prior to receiving such information or materials from the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:SuchInformation/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
|
||||
" Document(page_content='(iii) are rightfully acquired by the receiving party from a third party who has the right to disclose such information or materials without breach of any confidentiality obligation to the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheReceivingParty/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
|
||||
" Document(page_content='4. Compelled Disclosure . Nothing in this Agreement will be deemed to restrict a party from disclosing the other party’s Confidential Information to the extent required by any order, subpoena, law, statute or regulation; provided, that the party required to make such a disclosure uses reasonable efforts to give the other party reasonable advance notice of such required disclosure in order to enable the other party to prevent or limit such disclosure.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Disclosure/docset:CompelledDisclosure-section/docset:CompelledDisclosure', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'CompelledDisclosure'}),\n",
|
||||
" Document(page_content='5. Return of Confidential Information . Upon the completion or abandonment of the Purpose, and in any event upon the disclosing party’s request, the receiving party will promptly return to the disclosing party all tangible items and embodiments containing or consisting of the disclosing party’s Confidential Information and all copies thereof (including electronic copies), and any notes, analyses, compilations, studies, interpretations, memoranda or other documents (regardless of the form thereof) prepared by or on behalf of the receiving party that contain or are based upon the disclosing party’s Confidential Information .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheCompletion/docset:ReturnofConfidentialInformation-section/docset:ReturnofConfidentialInformation', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ReturnofConfidentialInformation'}),\n",
|
||||
" Document(page_content='6. No Obligations . Each party retains the right to determine whether to disclose any Confidential Information to the other party.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoObligations/docset:NoObligations-section/docset:NoObligations[2]', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoObligations'}),\n",
|
||||
" Document(page_content='7. No Warranty. ALL CONFIDENTIAL INFORMATION IS PROVIDED BY THE DISCLOSING PARTY “AS IS ”.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoWarranty/docset:NoWarranty-section/docset:NoWarranty[2]', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoWarranty'}),\n",
|
||||
" Document(page_content='8. Term. This Agreement will remain in effect for a period of seven ( 7 ) years from the date of last disclosure of Confidential Information by either party, at which time it will terminate.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:ThisAgreement/docset:Term-section/docset:Term', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Term'}),\n",
|
||||
" Document(page_content='9. Equitable Relief . Each party acknowledges that the unauthorized use or disclosure of the disclosing party’s Confidential Information may cause the disclosing party to incur irreparable harm and significant damages, the degree of which may be difficult to ascertain. Accordingly, each party agrees that the disclosing party will have the right to seek immediate equitable relief to enjoin any unauthorized use or disclosure of its Confidential Information , in addition to any other rights and remedies that it may have at law or otherwise.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:EquitableRelief/docset:EquitableRelief-section/docset:EquitableRelief[2]', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'EquitableRelief'}),\n",
|
||||
" Document(page_content='10. Non-compete. To the maximum extent permitted by applicable law, during the Term of this Agreement and for a period of one ( 1 ) year thereafter, Caleb Divine may not market software products or do business that directly or indirectly competes with Docugami software products .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheMaximumExtent/docset:Non-compete-section/docset:Non-compete', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Non-compete'}),\n",
|
||||
" Document(page_content='11. Miscellaneous. This Agreement will be governed and construed in accordance with the laws of the State of Washington , excluding its body of law controlling conflict of laws. This Agreement is the complete and exclusive understanding and agreement between the parties regarding the subject matter of this Agreement and supersedes all prior agreements, understandings and communications, oral or written, between the parties regarding the subject matter of this Agreement . If any provision of this Agreement is held invalid or unenforceable by a court of competent jurisdiction, that provision of this Agreement will be enforced to the maximum extent permissible and the other provisions of this Agreement will remain in full force and effect. Neither party may assign this Agreement , in whole or in part, by operation of law or otherwise, without the other party’s prior written consent, and any attempted assignment without such consent will be void. This Agreement may be executed in counterparts, each of which will be deemed an original, but all of which together will constitute one and the same instrument.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Accordance/docset:Miscellaneous-section/docset:Miscellaneous', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Miscellaneous'}),\n",
|
||||
" Document(page_content='[SIGNATURE PAGE FOLLOWS] IN WITNESS WHEREOF, the parties hereto have executed this Mutual Non-Disclosure Agreement by their duly authorized officers or representatives as of the date first set forth above.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:TheParties', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheParties'}),\n",
|
||||
" Document(page_content='DOCUGAMI INC . : \\n\\n Caleb Divine : \\n\\n Signature: Signature: Name: \\n\\n Jean Paoli Name: Title: \\n\\n CEO Title:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:DocugamiInc/docset:DocugamiInc/xhtml:table', 'id': '43rj0ds7s0ur', 'name': 'NDA simple layout.docx', 'structure': '', 'tag': 'table'})]"
|
||||
"[Document(page_content='MUTUAL NON-DISCLOSURE AGREEMENT This Mutual Non-Disclosure Agreement (this “ Agreement ”) is entered into and made effective as of April 4 , 2018 between Docugami Inc. , a Delaware corporation , whose address is 150 Lake Street South , Suite 221 , Kirkland , Washington 98033 , and Caleb Divine , an individual, whose address is 1201 Rt 300 , Newburgh NY 12550 .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:ThisMutualNon-disclosureAgreement', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'ThisMutualNon-disclosureAgreement'}),\n",
|
||||
" Document(page_content='The above named parties desire to engage in discussions regarding a potential agreement or other transaction between the parties (the “Purpose”). In connection with such discussions, it may be necessary for the parties to disclose to each other certain confidential information or materials to enable them to evaluate whether to enter into such agreement or transaction.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Discussions', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Discussions'}),\n",
|
||||
" Document(page_content='In consideration of the foregoing, the parties agree as follows:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Consideration', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Consideration'}),\n",
|
||||
" Document(page_content='1. Confidential Information . For purposes of this Agreement , “ Confidential Information ” means any information or materials disclosed by one party to the other party that: (i) if disclosed in writing or in the form of tangible materials, is marked “confidential” or “proprietary” at the time of such disclosure; (ii) if disclosed orally or by visual presentation, is identified as “confidential” or “proprietary” at the time of such disclosure, and is summarized in a writing sent by the disclosing party to the receiving party within thirty ( 30 ) days after any such disclosure; or (iii) due to its nature or the circumstances of its disclosure, a person exercising reasonable business judgment would understand to be confidential or proprietary.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Purposes/docset:ConfidentialInformation-section/docset:ConfidentialInformation[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ConfidentialInformation'}),\n",
|
||||
" Document(page_content=\"2. Obligations and Restrictions . Each party agrees: (i) to maintain the other party's Confidential Information in strict confidence; (ii) not to disclose such Confidential Information to any third party; and (iii) not to use such Confidential Information for any purpose except for the Purpose. Each party may disclose the other party’s Confidential Information to its employees and consultants who have a bona fide need to know such Confidential Information for the Purpose, but solely to the extent necessary to pursue the Purpose and for no other purpose; provided, that each such employee and consultant first executes a written agreement (or is otherwise already bound by a written agreement) that contains use and nondisclosure restrictions at least as protective of the other party’s Confidential Information as those set forth in this Agreement .\", metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Obligations/docset:ObligationsAndRestrictions-section/docset:ObligationsAndRestrictions', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ObligationsAndRestrictions'}),\n",
|
||||
" Document(page_content='3. Exceptions. The obligations and restrictions in Section 2 will not apply to any information or materials that:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Exceptions/docset:Exceptions-section/docset:Exceptions[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Exceptions'}),\n",
|
||||
" Document(page_content='(i) were, at the date of disclosure, or have subsequently become, generally known or available to the public through no act or failure to act by the receiving party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheDate/docset:TheDate', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheDate'}),\n",
|
||||
" Document(page_content='(ii) were rightfully known by the receiving party prior to receiving such information or materials from the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:SuchInformation/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
|
||||
" Document(page_content='(iii) are rightfully acquired by the receiving party from a third party who has the right to disclose such information or materials without breach of any confidentiality obligation to the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheReceivingParty/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
|
||||
" Document(page_content='4. Compelled Disclosure . Nothing in this Agreement will be deemed to restrict a party from disclosing the other party’s Confidential Information to the extent required by any order, subpoena, law, statute or regulation; provided, that the party required to make such a disclosure uses reasonable efforts to give the other party reasonable advance notice of such required disclosure in order to enable the other party to prevent or limit such disclosure.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Disclosure/docset:CompelledDisclosure-section/docset:CompelledDisclosure', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'CompelledDisclosure'}),\n",
|
||||
" Document(page_content='5. Return of Confidential Information . Upon the completion or abandonment of the Purpose, and in any event upon the disclosing party’s request, the receiving party will promptly return to the disclosing party all tangible items and embodiments containing or consisting of the disclosing party’s Confidential Information and all copies thereof (including electronic copies), and any notes, analyses, compilations, studies, interpretations, memoranda or other documents (regardless of the form thereof) prepared by or on behalf of the receiving party that contain or are based upon the disclosing party’s Confidential Information .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheCompletion/docset:ReturnofConfidentialInformation-section/docset:ReturnofConfidentialInformation', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ReturnofConfidentialInformation'}),\n",
|
||||
" Document(page_content='6. No Obligations . Each party retains the right to determine whether to disclose any Confidential Information to the other party.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoObligations/docset:NoObligations-section/docset:NoObligations[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoObligations'}),\n",
|
||||
" Document(page_content='7. No Warranty. ALL CONFIDENTIAL INFORMATION IS PROVIDED BY THE DISCLOSING PARTY “AS IS ”.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoWarranty/docset:NoWarranty-section/docset:NoWarranty[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoWarranty'}),\n",
|
||||
" Document(page_content='8. Term. This Agreement will remain in effect for a period of seven ( 7 ) years from the date of last disclosure of Confidential Information by either party, at which time it will terminate.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:ThisAgreement/docset:Term-section/docset:Term', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Term'}),\n",
|
||||
" Document(page_content='9. Equitable Relief . Each party acknowledges that the unauthorized use or disclosure of the disclosing party’s Confidential Information may cause the disclosing party to incur irreparable harm and significant damages, the degree of which may be difficult to ascertain. Accordingly, each party agrees that the disclosing party will have the right to seek immediate equitable relief to enjoin any unauthorized use or disclosure of its Confidential Information , in addition to any other rights and remedies that it may have at law or otherwise.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:EquitableRelief/docset:EquitableRelief-section/docset:EquitableRelief[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'EquitableRelief'}),\n",
|
||||
" Document(page_content='10. Non-compete. To the maximum extent permitted by applicable law, during the Term of this Agreement and for a period of one ( 1 ) year thereafter, Caleb Divine may not market software products or do business that directly or indirectly competes with Docugami software products .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheMaximumExtent/docset:Non-compete-section/docset:Non-compete', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Non-compete'}),\n",
|
||||
" Document(page_content='11. Miscellaneous. This Agreement will be governed and construed in accordance with the laws of the State of Washington , excluding its body of law controlling conflict of laws. This Agreement is the complete and exclusive understanding and agreement between the parties regarding the subject matter of this Agreement and supersedes all prior agreements, understandings and communications, oral or written, between the parties regarding the subject matter of this Agreement . If any provision of this Agreement is held invalid or unenforceable by a court of competent jurisdiction, that provision of this Agreement will be enforced to the maximum extent permissible and the other provisions of this Agreement will remain in full force and effect. Neither party may assign this Agreement , in whole or in part, by operation of law or otherwise, without the other party’s prior written consent, and any attempted assignment without such consent will be void. This Agreement may be executed in counterparts, each of which will be deemed an original, but all of which together will constitute one and the same instrument.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Accordance/docset:Miscellaneous-section/docset:Miscellaneous', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Miscellaneous'}),\n",
|
||||
" Document(page_content='[SIGNATURE PAGE FOLLOWS] IN WITNESS WHEREOF, the parties hereto have executed this Mutual Non-Disclosure Agreement by their duly authorized officers or representatives as of the date first set forth above.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:TheParties', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheParties'}),\n",
|
||||
" Document(page_content='DOCUGAMI INC . : \\n\\n Caleb Divine : \\n\\n Signature: Signature: Name: \\n\\n Jean Paoli Name: Title: \\n\\n CEO Title:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:DocugamiInc/docset:DocugamiInc/xhtml:table', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': '', 'tag': 'table'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
@ -116,7 +116,7 @@
|
||||
"source": [
|
||||
"The `metadata` for each `Document` (really, a chunk of an actual PDF, DOC or DOCX) contains some useful additional information:\n",
|
||||
"\n",
|
||||
"1. **id and name:** ID and Name of the file (PDF, DOC or DOCX) the chunk is sourced from within Docugami.\n",
|
||||
"1. **id and source:** ID and Name of the file (PDF, DOC or DOCX) the chunk is sourced from within Docugami.\n",
|
||||
"2. **xpath:** XPath inside the XML representation of the document, for the chunk. Useful for source citations directly to the actual chunk inside the document XML.\n",
|
||||
"3. **structure:** Structural attributes of the chunk, e.g. h1, h2, div, table, td, etc. Useful to filter out certain kinds of chunks if needed by the caller.\n",
|
||||
"4. **tag:** Semantic tag for the chunk, using various generative and extractive techniques. More details here: https://github.com/docugami/DFM-benchmarks"
|
||||
@ -133,7 +133,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -142,7 +142,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -170,15 +170,7 @@
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Using embedded DuckDB without persistence: data will be transient\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embedding = OpenAIEmbeddings()\n",
|
||||
"vectordb = Chroma.from_documents(documents=documents, embedding=embedding)\n",
|
||||
@ -197,11 +189,11 @@
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'query': 'What can tenants do with signage on their properties?',\n",
|
||||
" 'result': ' Tenants may place signs (digital or otherwise) or other form of identification on the premises after receiving written permission from the landlord which shall not be unreasonably withheld. The tenant is responsible for any damage caused to the premises and must conform to any applicable laws, ordinances, etc. governing the same. The tenant must also remove and clean any window or glass identification promptly upon vacating the premises.',\n",
|
||||
" 'source_documents': [Document(page_content='ARTICLE VI SIGNAGE 6.01 Signage . Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant ’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises.', metadata={'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:Article/docset:ARTICLEVISIGNAGE-section/docset:_601Signage-section/docset:_601Signage', 'id': 'v1bvgaozfkak', 'name': 'TruTone Lane 2.docx', 'structure': 'div', 'tag': '_601Signage', 'Landlord': 'BUBBA CENTER PARTNERSHIP', 'Tenant': 'Truetone Lane LLC'}),\n",
|
||||
" Document(page_content='Signage. Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant ’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises. \\n\\n ARTICLE VII UTILITIES 7.01', metadata={'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:ThisOFFICELEASEAGREEMENTThis/docset:ArticleIBasic/docset:ArticleIiiUseAndCareOf/docset:ARTICLEIIIUSEANDCAREOFPREMISES-section/docset:ARTICLEIIIUSEANDCAREOFPREMISES/docset:NoOtherPurposes/docset:TenantsResponsibility/dg:chunk', 'id': 'g2fvhekmltza', 'name': 'TruTone Lane 6.pdf', 'structure': 'lim', 'tag': 'chunk', 'Landlord': 'GLORY ROAD LLC', 'Tenant': 'Truetone Lane LLC'}),\n",
|
||||
" Document(page_content='Landlord , its agents, servants, employees, licensees, invitees, and contractors during the last year of the term of this Lease at any and all times during regular business hours, after 24 hour notice to tenant, to pass and repass on and through the Premises, or such portion thereof as may be necessary, in order that they or any of them may gain access to the Premises for the purpose of showing the Premises to potential new tenants or real estate brokers. In addition, Landlord shall be entitled to place a \"FOR RENT \" or \"FOR LEASE\" sign (not exceeding 8.5 ” x 11 ”) in the front window of the Premises during the last six months of the term of this Lease .', metadata={'xpath': '/docset:Rider/docset:RIDERTOLEASE-section/docset:RIDERTOLEASE/docset:FixedRent/docset:TermYearPeriod/docset:Lease/docset:_42FLandlordSAccess-section/docset:_42FLandlordSAccess/docset:LandlordsRights/docset:Landlord', 'id': 'omvs4mysdk6b', 'name': 'TruTone Lane 1.docx', 'structure': 'p', 'tag': 'Landlord', 'Landlord': 'BIRCH STREET , LLC', 'Tenant': 'Trutone Lane LLC'}),\n",
|
||||
" Document(page_content=\"24. SIGNS . No signage shall be placed by Tenant on any portion of the Project . However, Tenant shall be permitted to place a sign bearing its name in a location approved by Landlord near the entrance to the Premises (at Tenant's cost ) and will be furnished a single listing of its name in the Building's directory (at Landlord 's cost ), all in accordance with the criteria adopted from time to time by Landlord for the Project . Any changes or additional listings in the directory shall be furnished (subject to availability of space) for the then Building Standard charge .\", metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:TheTerms/docset:Indemnification/docset:INDEMNIFICATION-section/docset:INDEMNIFICATION/docset:Waiver/docset:Waiver/docset:Signs/docset:SIGNS-section/docset:SIGNS', 'id': 'qkn9cyqsiuch', 'name': 'Shorebucks LLC_AZ.pdf', 'structure': 'div', 'tag': 'SIGNS', 'Landlord': 'Menlo Group', 'Tenant': 'Shorebucks LLC'})]}"
|
||||
" 'result': \" Tenants can place or attach signs (digital or otherwise) to their premises with written permission from the landlord. The signs must conform to all applicable laws, ordinances, etc. governing the same. Tenants can also have their name listed in the building's directory at the landlord's cost.\",\n",
|
||||
" 'source_documents': [Document(page_content='ARTICLE VI SIGNAGE 6.01 Signage . Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant ’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises.', metadata={'Landlord': 'BUBBA CENTER PARTNERSHIP', 'Lease Date': 'April 24 \\n\\n ,', 'Lease Parties': 'This OFFICE LEASE AGREEMENT (this \"Lease\") is made and entered into by and between BUBBA CENTER PARTNERSHIP (\" Landlord \"), and Truetone Lane LLC , a Delaware limited liability company (\" Tenant \").', 'Tenant': 'Truetone Lane LLC', 'id': 'v1bvgaozfkak', 'source': 'TruTone Lane 2.docx', 'structure': 'div', 'tag': '_601Signage', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:Article/docset:ARTICLEVISIGNAGE-section/docset:_601Signage-section/docset:_601Signage'}),\n",
|
||||
" Document(page_content='Signage. Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant ’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises. \\n\\n ARTICLE VII UTILITIES 7.01', metadata={'Landlord': 'GLORY ROAD LLC', 'Lease Date': 'April 30 , 2020', 'Lease Parties': 'This OFFICE LEASE AGREEMENT (this \"Lease\") is made and entered into by and between GLORY ROAD LLC (\" Landlord \"), and Truetone Lane LLC , a Delaware limited liability company (\" Tenant \").', 'Tenant': 'Truetone Lane LLC', 'id': 'g2fvhekmltza', 'source': 'TruTone Lane 6.pdf', 'structure': 'lim', 'tag': 'chunk', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:Article/docset:ArticleIiiUse/docset:ARTICLEIIIUSEANDCAREOFPREMISES-section/docset:ARTICLEIIIUSEANDCAREOFPREMISES/docset:AnyTime/docset:Addition/dg:chunk'}),\n",
|
||||
" Document(page_content='Landlord , its agents, servants, employees, licensees, invitees, and contractors during the last year of the term of this Lease at any and all times during regular business hours, after 24 hour notice to tenant, to pass and repass on and through the Premises, or such portion thereof as may be necessary, in order that they or any of them may gain access to the Premises for the purpose of showing the Premises to potential new tenants or real estate brokers. In addition, Landlord shall be entitled to place a \"FOR RENT \" or \"FOR LEASE\" sign (not exceeding 8.5 ” x 11 ”) in the front window of the Premises during the last six months of the term of this Lease .', metadata={'Landlord': 'BIRCH STREET , LLC', 'Lease Date': 'October 15 , 2021', 'Lease Parties': 'The provisions of this rider are hereby incorporated into and made a part of the Lease dated as of October 15 , 2021 between BIRCH STREET , LLC , having an address at c/o Birch Palace , 6 Grace Avenue Suite 200 , Great Neck , New York 11021 (\" Landlord \"), and Trutone Lane LLC , having an address at 4 Pearl Street , New York , New York 10012 (\" Tenant \") of Premises known as the ground floor space and lower level space, as per floor plan annexed hereto and made a part hereof as Exhibit A (“Premises”) at 4 Pearl Street , New York , New York 10012 in the City of New York , Borough of Manhattan , to which this rider is annexed. If there is any conflict between the provisions of this rider and the remainder of this Lease , the provisions of this rider shall govern.', 'Tenant': 'Trutone Lane LLC', 'id': 'omvs4mysdk6b', 'source': 'TruTone Lane 1.docx', 'structure': 'p', 'tag': 'Landlord', 'xpath': '/docset:Rider/docset:RIDERTOLEASE-section/docset:RIDERTOLEASE/docset:FixedRent/docset:TermYearPeriod/docset:Lease/docset:_42FLandlordSAccess-section/docset:_42FLandlordSAccess/docset:LandlordsRights/docset:Landlord'}),\n",
|
||||
" Document(page_content=\"24. SIGNS . No signage shall be placed by Tenant on any portion of the Project . However, Tenant shall be permitted to place a sign bearing its name in a location approved by Landlord near the entrance to the Premises (at Tenant's cost ) and will be furnished a single listing of its name in the Building's directory (at Landlord 's cost ), all in accordance with the criteria adopted from time to time by Landlord for the Project . Any changes or additional listings in the directory shall be furnished (subject to availability of space) for the then Building Standard charge .\", metadata={'Landlord': 'Perry & Blair LLC', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'dsyfhh4vpeyf', 'source': 'Shorebucks LLC_CO.pdf', 'structure': 'div', 'tag': 'SIGNS', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:ThisLease-section/docset:ThisLease/docset:Guaranty-section/docset:Guaranty[2]/docset:TheTransfer/docset:TheTerms/docset:Indemnification/docset:INDEMNIFICATION-section/docset:INDEMNIFICATION/docset:Waiver/docset:Waiver/docset:Signs/docset:SIGNS-section/docset:SIGNS'})]}"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
@ -233,7 +225,7 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' 9,753 square feet'"
|
||||
"' 9,753 square feet.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
@ -243,31 +235,31 @@
|
||||
],
|
||||
"source": [
|
||||
"chain_response = qa_chain(\"What is rentable area for the property owned by DHA Group?\")\n",
|
||||
"chain_response[\"result\"] # the correct answer should be 13,500"
|
||||
"chain_response[\"result\"] # correct answer should be 13,500 sq ft"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"At first glance the answer may seem reasonable, but if you review the source chunks carefully for this answer, you will see that the chunking of the document did not end up putting the Landlord name and the rentable area in the same context, since they are far apart in the document. The retriever therefore ends up finding unrelated chunks from other documents not even related to the **Menlo Group** landlord. That landlord happens to be mentioned on the first page of the file **Shorebucks LLC_NJ.pdf** file, and while one of the source chunks used by the chain is indeed from that doc that contains the correct answer (**13,500**), other source chunks from different docs are included, and the answer is therefore incorrect."
|
||||
"At first glance the answer may seem reasonable, but if you review the source chunks carefully for this answer, you will see that the chunking of the document did not end up putting the Landlord name and the rentable area in the same context, since they are far apart in the document. The retriever therefore ends up finding unrelated chunks from other documents not even related to the **DHA Group** landlord. That landlord happens to be mentioned on the first page of the file **Shorebucks LLC_NJ.pdf** file, and while one of the source chunks used by the chain is indeed from that doc that contains the correct answer (**13,500**), other source chunks from different docs are included, and the answer is therefore incorrect."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:DhaGroup/docset:Landlord-section/docset:DhaGroup', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'DhaGroup', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content='WITNESSES: LANDLORD: DHA Group , a Delaware limited liability company', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Guaranty-section/docset:Guaranty[2]/docset:SIGNATURESONNEXTPAGE-section/docset:INWITNESSWHEREOF-section/docset:INWITNESSWHEREOF/docset:Behalf/docset:Witnesses/xhtml:table/xhtml:tbody/xhtml:tr[3]/xhtml:td[2]/docset:DhaGroup', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'DhaGroup', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content=\"1.16 Landlord 's Notice Address . DHA Group , Suite 1010 , 111 Bauer Dr , Oakland , New Jersey , 07436 , with a copy to the Building Management Office at the Project , Attention: On - Site Property Manager .\", metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:NoticeAddress[2]/docset:LandlordsNoticeAddress-section/docset:LandlordsNoticeAddress[2]', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'LandlordsNoticeAddress', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content='1.6 Rentable Area of the Premises. 9,753 square feet . This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:PerryBlair/docset:PerryBlair/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises', 'id': 'dsyfhh4vpeyf', 'name': 'Shorebucks LLC_CO.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'Landlord': 'Perry & Blair LLC', 'Tenant': 'Shorebucks LLC'})]"
|
||||
"[Document(page_content='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'DhaGroup', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:DhaGroup/docset:Landlord-section/docset:DhaGroup'}),\n",
|
||||
" Document(page_content='WITNESSES: LANDLORD: DHA Group , a Delaware limited liability company', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'DhaGroup', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Guaranty-section/docset:Guaranty[2]/docset:SIGNATURESONNEXTPAGE-section/docset:INWITNESSWHEREOF-section/docset:INWITNESSWHEREOF/docset:Behalf/docset:Witnesses/xhtml:table/xhtml:tbody/xhtml:tr[3]/xhtml:td[2]/docset:DhaGroup'}),\n",
|
||||
" Document(page_content=\"1.16 Landlord 's Notice Address . DHA Group , Suite 1010 , 111 Bauer Dr , Oakland , New Jersey , 07436 , with a copy to the Building Management Office at the Project , Attention: On - Site Property Manager .\", metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'LandlordsNoticeAddress', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:NoticeAddress[2]/docset:LandlordsNoticeAddress-section/docset:LandlordsNoticeAddress[2]'}),\n",
|
||||
" Document(page_content='1.6 Rentable Area of the Premises. 9,753 square feet . This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'Perry & Blair LLC', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'dsyfhh4vpeyf', 'source': 'Shorebucks LLC_CO.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:PerryBlair/docset:PerryBlair/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -287,22 +279,24 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:ThisOfficeLeaseAgreement',\n",
|
||||
"{'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:LeaseParties',\n",
|
||||
" 'id': 'v1bvgaozfkak',\n",
|
||||
" 'name': 'TruTone Lane 2.docx',\n",
|
||||
" 'source': 'TruTone Lane 2.docx',\n",
|
||||
" 'structure': 'p',\n",
|
||||
" 'tag': 'ThisOfficeLeaseAgreement',\n",
|
||||
" 'tag': 'LeaseParties',\n",
|
||||
" 'Lease Date': 'April 24 \\n\\n ,',\n",
|
||||
" 'Landlord': 'BUBBA CENTER PARTNERSHIP',\n",
|
||||
" 'Tenant': 'Truetone Lane LLC'}"
|
||||
" 'Tenant': 'Truetone Lane LLC',\n",
|
||||
" 'Lease Parties': 'This OFFICE LEASE AGREEMENT (this \"Lease\") is made and entered into by and between BUBBA CENTER PARTNERSHIP (\" Landlord \"), and Truetone Lane LLC , a Delaware limited liability company (\" Tenant \").'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -322,17 +316,9 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Using embedded DuckDB without persistence: data will be transient\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.query_constructor.schema import AttributeInfo\n",
|
||||
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
|
||||
@ -372,22 +358,30 @@
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/root/Source/github/docugami.langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='rentable area' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='Landlord', value='DHA Group')\n"
|
||||
"query='rentable area' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='Landlord', value='DHA Group') limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'query': 'What is rentable area for the property owned by DHA Group?',\n",
|
||||
" 'result': ' 13,500 square feet.',\n",
|
||||
" 'source_documents': [Document(page_content='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:DhaGroup/docset:Landlord-section/docset:DhaGroup', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'DhaGroup', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content='WITNESSES: LANDLORD: DHA Group , a Delaware limited liability company', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Guaranty-section/docset:Guaranty[2]/docset:SIGNATURESONNEXTPAGE-section/docset:INWITNESSWHEREOF-section/docset:INWITNESSWHEREOF/docset:Behalf/docset:Witnesses/xhtml:table/xhtml:tbody/xhtml:tr[3]/xhtml:td[2]/docset:DhaGroup', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'DhaGroup', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content=\"1.16 Landlord 's Notice Address . DHA Group , Suite 1010 , 111 Bauer Dr , Oakland , New Jersey , 07436 , with a copy to the Building Management Office at the Project , Attention: On - Site Property Manager .\", metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:NoticeAddress[2]/docset:LandlordsNoticeAddress-section/docset:LandlordsNoticeAddress[2]', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'LandlordsNoticeAddress', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'}),\n",
|
||||
" Document(page_content='1.6 Rentable Area of the Premises. 13,500 square feet . This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises', 'id': 'md8rieecquyv', 'name': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'Landlord': 'DHA Group', 'Tenant': 'Shorebucks LLC'})]}"
|
||||
" 'result': ' The rentable area for the property owned by DHA Group is 13,500 square feet.',\n",
|
||||
" 'source_documents': [Document(page_content='1.6 Rentable Area of the Premises. 13,500 square feet . This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'}),\n",
|
||||
" Document(page_content='1.6 Rentable Area of the Premises. 13,500 square feet . This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'}),\n",
|
||||
" Document(page_content='1.11 Percentage Rent . (a) 55 % of Gross Revenue to Landlord until Landlord receives Percentage Rent in an amount equal to the Annual Market Rent Hurdle (as escalated); and', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'GrossRevenue', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent-section/docset:PercentageRent[2]/docset:PercentageRent/docset:GrossRevenue[1]/docset:GrossRevenue'}),\n",
|
||||
" Document(page_content='1.11 Percentage Rent . (a) 55 % of Gross Revenue to Landlord until Landlord receives Percentage Rent in an amount equal to the Annual Market Rent Hurdle (as escalated); and', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March 29th , 2019', 'Lease Parties': 'THIS OFFICE LEASE (the \"Lease\") is made and entered into as of March 29th , 2019 , by and between Landlord and Tenant . \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'GrossRevenue', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent-section/docset:PercentageRent[2]/docset:PercentageRent/docset:GrossRevenue[1]/docset:GrossRevenue'})]}"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
@ -396,7 +390,9 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"qa_chain(\"What is rentable area for the property owned by DHA Group?\")"
|
||||
"qa_chain(\n",
|
||||
" \"What is rentable area for the property owned by DHA Group?\"\n",
|
||||
") # correct answer should be 13,500 sq ft"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -423,7 +419,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.3"
|
||||
"version": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@ -16,6 +16,7 @@ TABLE_NAME = "{http://www.w3.org/1999/xhtml}table"
|
||||
|
||||
XPATH_KEY = "xpath"
|
||||
DOCUMENT_ID_KEY = "id"
|
||||
DOCUMENT_SOURCE_KEY = "source"
|
||||
DOCUMENT_NAME_KEY = "name"
|
||||
STRUCTURE_KEY = "structure"
|
||||
TAG_KEY = "tag"
|
||||
@ -143,8 +144,9 @@ class DocugamiLoader(BaseLoader, BaseModel):
|
||||
"""Create a Document from a node and text."""
|
||||
metadata = {
|
||||
XPATH_KEY: _xpath_for_chunk(node),
|
||||
DOCUMENT_ID_KEY: document["id"],
|
||||
DOCUMENT_NAME_KEY: document["name"],
|
||||
DOCUMENT_ID_KEY: document[DOCUMENT_ID_KEY],
|
||||
DOCUMENT_NAME_KEY: document[DOCUMENT_NAME_KEY],
|
||||
DOCUMENT_SOURCE_KEY: document[DOCUMENT_NAME_KEY],
|
||||
STRUCTURE_KEY: node.attrib.get("structure", ""),
|
||||
TAG_KEY: re.sub(r"\{.*\}", "", node.tag),
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user