github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-25 16:13:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

notebook cleanup

Browse Source
This commit is contained in:
Taqi Jaffri 2023-08-08 21:38:55 -07:00
parent bcdf3be530
commit 5919c0f4a2
2 changed files with 53 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
docs/extras/integrations/document_loaders/docugami.ipynb
View File

@ -15,7 +15,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 1,
"metadata": { "metadata": {
"tags": [] "tags": []
}, },
@ -58,7 +58,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -77,7 +77,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 22, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -104,7 +104,7 @@
" 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'})]" " 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": 22, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -141,7 +141,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -150,7 +150,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 24, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -176,7 +176,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 25, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -190,21 +190,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 26, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"{'query': 'What can tenants do with signage on their properties?',\n", "{'query': 'What can tenants do with signage on their properties?',\n",
" 'result': ' Tenants can place or attach signs (digital or otherwise) to their properties, after receiving written permission from their landlord. Any signs must conform to all applicable laws, ordinances, etc. governing the same.',\n", " '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='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', 'Tenant': 'Truetone Lane LLC', 'id': 'g2fvhekmltza', 'source': 'TruTone Lane 6.pdf', 'structure': 'lim', 'tag': 'chunk', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:ThisOFFICELEASEAGREEMENTThis/docset:ArticleIBasic/docset:ArticleIiiUseAndCareOf/docset:ARTICLEIIIUSEANDCAREOFPREMISES-section/docset:ARTICLEIIIUSEANDCAREOFPREMISES/docset:NoOtherPurposes/docset:TenantsResponsibility/dg:chunk'}),\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', 'Tenant': 'Truetone Lane LLC', 'id': 'g2fvhekmltza', 'source': 'TruTone Lane 6.pdf', 'structure': 'lim', 'tag': 'chunk', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:ThisOFFICELEASEAGREEMENTThis/docset:ArticleIBasic/docset:ArticleIiiUseAndCareOf/docset:ARTICLEIIIUSEANDCAREOFPREMISES-section/docset:ARTICLEIIIUSEANDCAREOFPREMISES/docset:NoOtherPurposes/docset:TenantsResponsibility/dg:chunk'}),\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='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', '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='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='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', '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'})]}" " 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": 26, "execution_count": 7,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -227,47 +227,47 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 27, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"\" I don't know.\"" "' 9,753 square feet.'"
] ]
}, },
"execution_count": 27, "execution_count": 8,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [ "source": [
"chain_response = qa_chain(\"What is rentable area for the property owned by DHA Group?\")\n", "chain_response = qa_chain(\"What is rentable area for the property owned by DHA Group?\")\n",
"chain_response[\"result\"]" "chain_response[\"result\"] # correct answer should be 13,500 sq ft"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "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", "cell_type": "code",
"execution_count": 28, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"[Document(page_content='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'Landlord': 'DHA Group', '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='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='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'Landlord': 'DHA Group', '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='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'Landlord': 'DHA Group', '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=\"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='1.1 Landlord . DHA Group , a Delaware limited liability company authorized to transact business in New Jersey .', metadata={'Landlord': 'DHA Group', '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'})]" " 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": 28, "execution_count": 13,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -287,22 +287,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 29, "execution_count": 14,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"{'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:ThisOfficeLeaseAgreement',\n", "{'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:LeaseParties',\n",
" 'id': 'v1bvgaozfkak',\n", " 'id': 'v1bvgaozfkak',\n",
" 'source': 'TruTone Lane 2.docx',\n", " 'source': 'TruTone Lane 2.docx',\n",
" 'structure': 'p',\n", " 'structure': 'p',\n",
" 'tag': 'ThisOfficeLeaseAgreement',\n", " 'tag': 'LeaseParties',\n",
" 'Lease Date': 'April 24 \\n\\n ,',\n",
" 'Landlord': 'BUBBA CENTER PARTNERSHIP',\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": 29, "execution_count": 14,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -322,7 +324,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -361,9 +363,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [ "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", "name": "stdout",
"output_type": "stream", "output_type": "stream",
@ -376,19 +386,21 @@
"text/plain": [ "text/plain": [
"{'query': 'What is rentable area for the property owned by DHA Group?',\n", "{'query': 'What is rentable area for the property owned by DHA Group?',\n",
" 'result': ' The rentable area for the property owned by DHA Group is 13,500 square feet.',\n", " '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', '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", " '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', '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='1.6 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', '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='1.6 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', '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'})]}" " 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": 31, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [ "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"
] ]
}, },
{ {

5
libs/langchain/langchain/document_loaders/docugami.py
View File

@ -19,6 +19,7 @@ TABLE_NAME = "{http://www.w3.org/1999/xhtml}table"
XPATH_KEY = "xpath" XPATH_KEY = "xpath"
DOCUMENT_ID_KEY = "id" DOCUMENT_ID_KEY = "id"
DOCUMENT_SOURCE_KEY = "source" DOCUMENT_SOURCE_KEY = "source"
DOCUMENT_NAME_KEY = "name"
STRUCTURE_KEY = "structure" STRUCTURE_KEY = "structure"
TAG_KEY = "tag" TAG_KEY = "tag"
PROJECTS_KEY = "projects" PROJECTS_KEY = "projects"
@ -146,7 +147,7 @@ class DocugamiLoader(BaseLoader, BaseModel):
metadata = { metadata = {
XPATH_KEY: _xpath_for_chunk(node), XPATH_KEY: _xpath_for_chunk(node),
DOCUMENT_ID_KEY: document[DOCUMENT_ID_KEY], DOCUMENT_ID_KEY: document[DOCUMENT_ID_KEY],
DOCUMENT_SOURCE_KEY: document[DOCUMENT_SOURCE_KEY], DOCUMENT_SOURCE_KEY: document[DOCUMENT_NAME_KEY],
STRUCTURE_KEY: node.attrib.get("structure", ""), STRUCTURE_KEY: node.attrib.get("structure", ""),
TAG_KEY: re.sub(r"\{.*\}", "", node.tag), TAG_KEY: re.sub(r"\{.*\}", "", node.tag),
} }
@ -349,7 +350,7 @@ class DocugamiLoader(BaseLoader, BaseModel):
chunks += self._parse_dgml( chunks += self._parse_dgml(
{ {
DOCUMENT_ID_KEY: path.name, DOCUMENT_ID_KEY: path.name,
DOCUMENT_SOURCE_KEY: path.name, DOCUMENT_NAME_KEY: path.name,
}, },
file.read(), file.read(),
) )