llama-cloud 0.1.19__py3-none-any.whl → 0.1.21__py3-none-any.whl

{llama_cloud-0.1.19.dist-info → llama_cloud-0.1.21.dist-info}/RECORD

@@ -1,4 +1,4 @@
-llama_cloud/__init__.py,sha256=ek0T4C2t2jQzRaagVuKndSzFXXwuS_AY6J6pvsiay_s,23165
+llama_cloud/__init__.py,sha256=LY7rGZhiQwpQG72OHDir1GGwPpY18UKTow2wVENeRxs,24071
 llama_cloud/client.py,sha256=L8gEXB8nVlGVgfncfdLaS1j4b-1wExV4TqElUwayvtQ,5759
 llama_cloud/core/__init__.py,sha256=QJS3CJ2TYP2E1Tge0CS6Z7r8LTNzJHQVX1hD3558eP0,519
 llama_cloud/core/api_error.py,sha256=RE8LELok2QCjABadECTvtDp7qejA1VmINCh6TbqPwSE,426
@@ -32,7 +32,7 @@ llama_cloud/resources/embedding_model_configs/types/embedding_model_config_creat
 llama_cloud/resources/evals/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/evals/client.py,sha256=v2AyeQV0hVgC6xoP2gJNgneJMaeXALV1hIeirYGxlPw,3242
 llama_cloud/resources/files/__init__.py,sha256=3B0SNM8EE6PddD5LpxYllci9vflEXy1xjPzhEEd-OUk,293
-llama_cloud/resources/files/client.py,sha256=7VmhrE5fbftB6p6QUQUkGM5FO48obF73keq86vGFyhE,49676
+llama_cloud/resources/files/client.py,sha256=oPwDQAkf0zN1mxP_vT6Songp4scOq5k0jcfHo-zfCtY,50560
 llama_cloud/resources/files/types/__init__.py,sha256=EPYENAwkjBWv1MLf8s7R5-RO-cxZ_8NPrqfR4ZoR7jY,418
 llama_cloud/resources/files/types/file_create_from_url_resource_info_value.py,sha256=Wc8wFgujOO5pZvbbh2TMMzpa37GKZd14GYNJ9bdq7BE,214
 llama_cloud/resources/files/types/file_create_permission_info_value.py,sha256=KPCFuEaa8NiB85A5MfdXRAQ0poAUTl7Feg6BTfmdWas,209
@@ -53,9 +53,9 @@ llama_cloud/resources/llama_extract/types/extract_schema_validate_request_data_s
 llama_cloud/resources/organizations/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/organizations/client.py,sha256=OGSVpkfY5wu8-22IFWVmtbYSDiy0-KqA3Lc1E_jNHvg,55889
 llama_cloud/resources/parsing/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
-llama_cloud/resources/parsing/client.py,sha256=M3w5xLx8SZdvfh0Op7TI0CDwdF0YNcjk6E9qEfbZTf0,76377
+llama_cloud/resources/parsing/client.py,sha256=QoRN6Zie7jSY3qAhRa6OnCdYg4e62SkunFQ3NJWLWcs,76711
 llama_cloud/resources/pipelines/__init__.py,sha256=Mx7p3jDZRLMltsfywSufam_4AnHvmAfsxtMHVI72e-8,1083
-llama_cloud/resources/pipelines/client.py,sha256=x6MjLVwA6bQfDZmelc364tXmSoJeMUj6xPadjermpGQ,129010
+llama_cloud/resources/pipelines/client.py,sha256=3sBLSIR5iY-rH5usZUM6dTWjbIEiL62Up15wbsWAzn4,129436
 llama_cloud/resources/pipelines/types/__init__.py,sha256=jjaMc0V3K1HZLMYZ6WT4ydMtBCVy-oF5koqTCovbDws,1202
 llama_cloud/resources/pipelines/types/pipeline_file_update_custom_metadata_value.py,sha256=trI48WLxPcAqV9207Q6-3cj1nl4EGlZpw7En56ZsPgg,217
 llama_cloud/resources/pipelines/types/pipeline_update_embedding_config.py,sha256=c8FF64fDrBMX_2RX4uY3CjbNc0Ss_AUJ4Eqs-KeV4Wc,2874
@@ -68,7 +68,7 @@ llama_cloud/resources/reports/types/__init__.py,sha256=LfwDYrI4RcQu-o42iAe7HkcwH
 llama_cloud/resources/reports/types/update_report_plan_api_v_1_reports_report_id_plan_patch_request_action.py,sha256=Qh-MSeRvDBfNb5hoLELivv1pLtrYVf52WVoP7G8V34A,807
 llama_cloud/resources/retrievers/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/retrievers/client.py,sha256=T7fu41wXAYUTGh23ZWlKPM4e8zH7mg5MDa8F1GxNYwQ,31502
-llama_cloud/types/__init__.py,sha256=eWj70ScNb8UwFMtLJTGsuhD3nqPBNssVT3qh1iEyh7s,27476
+llama_cloud/types/__init__.py,sha256=aoxpc2tZxdBkPg2NcmgJYUAuDkE98loZibDrxWSaeLg,28456
 llama_cloud/types/advanced_mode_transform_config.py,sha256=4xCXye0_cPmVS1F8aNTx81sIaEPjQH9kiCCAIoqUzlI,1502
 llama_cloud/types/advanced_mode_transform_config_chunking_config.py,sha256=wYbJnWLpeQDfhmDZz-wJfYzD1iGT5Jcxb9ga3mzUuvk,1983
 llama_cloud/types/advanced_mode_transform_config_segmentation_config.py,sha256=anNGq0F5-IlbIW3kpC8OilzLJnUq5tdIcWHnRnmlYsg,1303
@@ -81,7 +81,6 @@ llama_cloud/types/base_plan.py,sha256=5DZi20EOciTc5okLAxQDqyGylsW-DflTy14dcvQb2f
 llama_cloud/types/base_plan_metronome_plan_type.py,sha256=I3g_dVoWWztbmpWpYmseDqQSbwtlLUl2vS01tfgMjEA,499
 llama_cloud/types/base_plan_name.py,sha256=keHQaw9YV9ghsWnGfnHrLtB4qNz0v4TWX4_MoO3flRM,1926
 llama_cloud/types/base_plan_plan_frequency.py,sha256=idUZlDaSdMrMZ2lQ1ytBWM4QyduIZu6Gt2eLU0LVqH4,684
-llama_cloud/types/base_prompt_template.py,sha256=Cw3887tnytHZ5bJBSlniyU9k5ASidv9VYR86--IbNqo,1248
 llama_cloud/types/batch.py,sha256=C8320qAjzQGYHiAvUOUzYsT9Ba7OYiHfA9T9_H8_wCY,2235
 llama_cloud/types/batch_item.py,sha256=ea0efWurrduelCg3wG4bhQOLiWTH1NJfd7So3j_HEbg,1574
 llama_cloud/types/batch_paginated_list.py,sha256=p25r9oyidy-Cd2D8xt_KLiTn7eMFvAVnzmvXfvKsOsw,1262
@@ -91,7 +90,6 @@ llama_cloud/types/bedrock_embedding_config.py,sha256=32dMhoA2cLx1jeogDnCl9WPVb83
 llama_cloud/types/billing_period.py,sha256=_BvznHPiB101hKeFmP0ZIRkBnGboxNvNgJD0BhegvN4,1002
 llama_cloud/types/box_auth_mechanism.py,sha256=EwEdpWYytw_dRtSElfSMPhh5dxalYH8mGW3UAUpkUfY,502
 llama_cloud/types/character_chunking_config.py,sha256=2ooAnrlVVbKj4nDi_lR66x5E6nWOmj5YDWhSMQD0ubc,1035
-llama_cloud/types/character_splitter.py,sha256=Jm6ie7c9JmMqIqLfAN-96sYvNUaIyLzCPBjNUx29VUw,1896
 llama_cloud/types/chat_app.py,sha256=fLuzYkXLq51C_Y23hoLwfmG-OiT7jlyHt2JGe6-f1IA,1795
 llama_cloud/types/chat_app_response.py,sha256=WSKr1KI9_pGTSstr3I53kZ8qb3y87Q4ulh8fR0C7sSU,1784
 llama_cloud/types/chat_data.py,sha256=ZYqVtjXF6qPGajU4IWZu3InpU54TXJwBFiqxBepylP0,1197
@@ -114,7 +112,6 @@ llama_cloud/types/cloud_qdrant_vector_store.py,sha256=F-gjNArzwLWmqgPcC-ZxRqSrhT
 llama_cloud/types/cloud_s_3_data_source.py,sha256=LG19EMOfIfm14XLbMaUC25BKzdL5u_Mb5GwgF7cB9Kw,1376
 llama_cloud/types/cloud_sharepoint_data_source.py,sha256=iJtlgb4hsj8CP2IJ7TxdK1GOb3MdyKr7_jsOlY3kFiE,1609
 llama_cloud/types/cloud_slack_data_source.py,sha256=tlsNj-hDj1gWmM0Q2A1BeyolfaPg_wfvSlJGTETknAo,1374
-llama_cloud/types/code_splitter.py,sha256=8MJScSxk9LzByufokcWG3AHAnOjUt13VlV2w0SCXTLc,1987
 llama_cloud/types/cohere_embedding.py,sha256=wkv_fVCA1WEroGawzPFExwmiJ75gPfzeeemty7NBlsM,1579
 llama_cloud/types/cohere_embedding_config.py,sha256=c0Kj1wuSsBX9TQ2AondKv5ZtX5PmkivsHj6P0M7tVB4,1142
 llama_cloud/types/composite_retrieval_mode.py,sha256=PtN0vQ90xyAJL4vyGRG4lMNOpnJ__2L1xiwosI9yfms,548
@@ -125,8 +122,6 @@ llama_cloud/types/configurable_data_sink_names.py,sha256=0Yk9i8hcNXKCcSKpa5KwsCw
 llama_cloud/types/configurable_data_source_names.py,sha256=mNW71sSgcVhU3kePAOUgRxeqK1Vo7F_J1xIzmYKPRq0,1971
 llama_cloud/types/configurable_transformation_definition.py,sha256=LDOhI5IDxlLDWM_p_xwCFM7qq1y-aGA8UxN7dnplDlU,1886
 llama_cloud/types/configurable_transformation_names.py,sha256=N_YhY8IuQxsqBteCibaQwEaY0zd6Ncb6jW69d9mjrdU,1898
-llama_cloud/types/configured_transformation_item.py,sha256=9caK5ZOKgGCZc6ynJJIWwpxpScKHOHkZwHFlsBy-Fog,1826
-llama_cloud/types/configured_transformation_item_component.py,sha256=VEwtkbnImKGtzaSaIb9q46xu7ZPZliqK7oMh_-ftiq8,712
 llama_cloud/types/credit_type.py,sha256=nwSRKDWgHk_msdWitctqtyeZwj5EFd6VLto6NF2yCd4,971
 llama_cloud/types/data_sink.py,sha256=PeexYHHoD8WkVp9WsFtfC-AIWszcgeJUprG1bwC8WsQ,1498
 llama_cloud/types/data_sink_component.py,sha256=uvuxLY3MPDpv_bkT0y-tHSZVPRSHCkDBDHVff-036Dg,749
@@ -140,6 +135,9 @@ llama_cloud/types/data_source_create_component.py,sha256=-P4FGv9Xg951n-77_bb-2_C
 llama_cloud/types/data_source_create_custom_metadata_value.py,sha256=ejSsQNbszYQaUWFh9r9kQpHf88qbhuRv1SI9J_MOSC0,215
 llama_cloud/types/data_source_custom_metadata_value.py,sha256=pTZn5yjZYmuOhsLABFJOKZblZUkRqo1CqLAuP5tKji4,209
 llama_cloud/types/data_source_definition.py,sha256=HlSlTxzYcQJOSo_2OSroAE8vAr-otDvTNBSEkA54vL8,1575
+llama_cloud/types/data_source_update_dispatcher_config.py,sha256=Sh6HhXfEV2Z6PYhkYQucs2MxyKVpL3UPV-I4cbf--bA,1242
+llama_cloud/types/delete_params.py,sha256=1snPrd3WO9C1bKf0WdMslE2HQMF0yYLI3U7N53cmurM,1285
+llama_cloud/types/document_ingestion_job_params.py,sha256=33xTAl-K-m1j_Ufkj7w2GaYg9EUH5Hwsjn869X-fWMk,1524
 llama_cloud/types/edit_suggestion.py,sha256=uzXSZYJiU3FaNN-TvEd3EXdaXvjQIe7Mf4kntKkyB2I,1202
 llama_cloud/types/edit_suggestion_blocks_item.py,sha256=ojTk4lh0IHmrWP5wLPTIlsc2jAUDoHvdjJ5sm2uMut0,236
 llama_cloud/types/element_segmentation_config.py,sha256=QOBk8YFrgK0I2m3caqV5bpYaGXbk0fMSjZ4hUPZXZDI,959
@@ -150,7 +148,7 @@ llama_cloud/types/embedding_model_config_update_embedding_config.py,sha256=mrXFx
 llama_cloud/types/eval_execution_params.py,sha256=ntVaJh5SMZMPL4QLUiihVjUlg2SKbrezvbMKGlrF66Q,1369
 llama_cloud/types/extract_agent.py,sha256=T98IOueut4M52Qm7hqcUOcWFFDhZ-ye0OFdXgfFGtS4,1763
 llama_cloud/types/extract_agent_data_schema_value.py,sha256=UaDQ2KjajLDccW7F4NKdfpefeTJrr1hl0c95WRETYkM,201
-llama_cloud/types/extract_config.py,sha256=9UH8cNBvKBQX9YqVAGwG0a7B73Y4Cwrmvil5Ex-L_I0,1603
+llama_cloud/types/extract_config.py,sha256=YZgNJpH1n6N-Lx9cIeuijT9xk1F6SeKjn4526wAtljc,1745
 llama_cloud/types/extract_job.py,sha256=Yx4fDdCdylAji2LPTwqflVpz1o9slpj9tTLS93-1tzU,1431
 llama_cloud/types/extract_job_create.py,sha256=UK1mBIKyflo7e6m1MxMN95pLscj67jH_yvs8EvmBXqU,1545
 llama_cloud/types/extract_job_create_data_schema_override.py,sha256=vuiJ2lGJjbXEnvFKzVnKyvgwhMXPg1Pb5GZne2DrB60,330
@@ -191,27 +189,27 @@ llama_cloud/types/ingestion_error_response.py,sha256=8u0cyT44dnpkNeUKemTvJMUqi_W
 llama_cloud/types/input_message.py,sha256=Ym6-tX6CMWKuHfxRtyM2y16kqSS3BzHged9rFRFkX0g,1346
 llama_cloud/types/job_name_mapping.py,sha256=2dQFQlVHoeSlkyEKSEJv0M3PzJf7hMvkuABj3vMY7ys,1617
 llama_cloud/types/job_names.py,sha256=WacongwoJygg_gCyYjPsOVv3cmVtRaX633JNgFxy-d8,3915
-llama_cloud/types/job_record.py,sha256=r2WzLQXSOFogNMN2rl10rAlYI9OTCmVn06QaZXxa0rQ,2058
+llama_cloud/types/job_record.py,sha256=7hdDPZU11EG8g6_9iq6vy-zqLEryeC7i8fZ-CkUB_xQ,2084
+llama_cloud/types/job_record_parameters.py,sha256=Oqxp5y0owPfjLc_NR7AYE8P3zM2PJo36N9olbyNl7AA,3425
 llama_cloud/types/job_record_with_usage_metrics.py,sha256=iNV2do5TB_0e3PoOz_DJyAaM6Cn9G8KG-dGPGgEs5SY,1198
+llama_cloud/types/l_lama_parse_transform_config.py,sha256=YQRJZvKh1Ee2FUyW_N0nqYJoW599qBgH3JCH9SH6YLo,1249
+llama_cloud/types/legacy_parse_job_config.py,sha256=kVBdiSLraI9rKQOPf0Ci9RtbNLkco0byBJC42uE_PCI,11698
 llama_cloud/types/llama_extract_settings.py,sha256=IQFxtKa4GtHKc9w-fLwsH0LSKDWzR9_vZ_cTFJ9cGBI,2288
 llama_cloud/types/llama_index_core_base_llms_types_chat_message.py,sha256=NelHo-T-ebVMhRKsqE_xV8AJW4c7o6lS0uEQnPsmTwg,1365
 llama_cloud/types/llama_index_core_base_llms_types_chat_message_blocks_item.py,sha256=JTU5EDoZB_1vcUixiWDCEbCj3-09GhYC3RDDSc0aqBU,1216
-llama_cloud/types/llama_parse_parameters.py,sha256=zgA133oDF0QYS2E4r8CtvKPi0nOTq0K5jBRaZmXJGT4,5718
+llama_cloud/types/llama_parse_parameters.py,sha256=DNhVZm3YQ_3xZiz7WUrwH7E6jqW2fZ7YGFsdfsYalUk,5773
 llama_cloud/types/llama_parse_supported_file_extensions.py,sha256=B_0N3f8Aq59W9FbsH50mGBUiyWTIXQjHFl739uAyaQw,11207
-llama_cloud/types/llm.py,sha256=7iIItVPjURp4u5xxJDAFIefUdhUKwIuA245WXilJPXE,2234
 llama_cloud/types/llm_model_data.py,sha256=6rrycqGwlK3LZ2S-WtgmeomithdLhDCgwBBZQ5KLaso,1300
 llama_cloud/types/llm_parameters.py,sha256=RTKYt09lm9a1MlnBfYuTP2x_Ww4byUNNc1TqIel5O1Y,1377
+llama_cloud/types/load_files_job_config.py,sha256=R5sFgFmV__0mqLUuD7dkFoBJHG2ZLw5px9zRapvYcpE,1069
 llama_cloud/types/managed_ingestion_status.py,sha256=3KVlcurpEBOPAesBUS5pSYLoQVIyZUlr90Mmv-uALHE,1290
 llama_cloud/types/managed_ingestion_status_response.py,sha256=rdNpjNbQswF-6JG1e-EU374TP6Pjlxl0p7HJyNmuxTI,1373
-llama_cloud/types/markdown_element_node_parser.py,sha256=NUqdU8BmyfSFK2rV6hCrvP6U1iB6aqZCVsvHWJQ49xU,1964
-llama_cloud/types/markdown_node_parser.py,sha256=GchDnlADMRiYREFOO6o_3LoiCXwUrrhms2CQkbP8sMo,1924
 llama_cloud/types/message_annotation.py,sha256=n4F9w4LxwmGvgXDk6E8YPTMu_g0yEjZhZ_eNFXdS_bc,1017
 llama_cloud/types/message_role.py,sha256=9MpXT9drR33TyT1-NiqB3uGbuxvWwtoOdSmKQE9HmJI,1359
 llama_cloud/types/metadata_filter.py,sha256=dVdXY6i0aCkvJrs7ncQt4-S8jmBF9bBSp2VuWrmAVfI,1440
 llama_cloud/types/metadata_filter_value.py,sha256=ij721gXNI7zbgsuDl9-AqBcXg2WDuVZhYS5F5YqekEs,188
 llama_cloud/types/metadata_filters.py,sha256=uSf6sB4oQu6WzMPNFG6Tc4euqEiYcj_X14Y5JWt9xVE,1315
 llama_cloud/types/metadata_filters_filters_item.py,sha256=e8KhD2q6Qc2_aK6r5CvyxC0oWVYO4F4vBIcB9eMEPPM,246
-llama_cloud/types/node_parser.py,sha256=rqZTQ_9GnCHOvSpXuAZoezxQCOgxHo-hmQv0s7pnEFc,1380
 llama_cloud/types/node_relationship.py,sha256=2e2PqWm0LOTiImvtsyiuaAPNIl0BItjSrQZTJv65GRA,1209
 llama_cloud/types/none_chunking_config.py,sha256=D062t314Vp-s4n9h8wNgsYfElI4PonPKmihvjEmaqdA,952
 llama_cloud/types/none_segmentation_config.py,sha256=j3jUA6E8uFtwDMEu4TFG3Q4ZGCGiuUfUW9AMO1NNqXU,956
@@ -224,12 +222,12 @@ llama_cloud/types/page_figure_metadata.py,sha256=iIg6_f2SwJg6UcQo9X4MoSm_ygxnIBm
 llama_cloud/types/page_screenshot_metadata.py,sha256=lobrq0AsOr8sDwMgA9ytop8lRmRFvJW2oiql3yLvbjM,1328
 llama_cloud/types/page_screenshot_node_with_score.py,sha256=EdqoXbmARCz1DV14E2saCPshIeII709uM4cLwxw_mkM,1232
 llama_cloud/types/page_segmentation_config.py,sha256=VH8uuxnubnJak1gSpS64OoMueHidhsDB-2eq2tVHbag,998
-llama_cloud/types/page_splitter_node_parser.py,sha256=rQgS1CDk18UKA0r9OPvjdtM570jzFArdLCTxYAtZny8,1424
 llama_cloud/types/paginated_extract_runs_response.py,sha256=NNeVcgBm0mYTAsumwQBO_YrxvkgUqwsvZo3xs8QjVCc,1423
 llama_cloud/types/paginated_jobs_history_with_metrics.py,sha256=Bxy6N0x0FARJhgwNKKPkNpXx8YLRHvth23G14f5Fuk4,1136
 llama_cloud/types/paginated_list_cloud_documents_response.py,sha256=MsjS0SWlT0syELDck4x2sxxR3_NC1e6QTdepgVmK9aY,1341
 llama_cloud/types/paginated_list_pipeline_files_response.py,sha256=2TKR2oHSQRyLMqWz1qQBSIvz-ZJb8U_94367lwOJ2S4,1317
 llama_cloud/types/paginated_report_response.py,sha256=o79QhQi9r0HZZrhvRlA6WGjxtyPuxN0xONhwXSwxtcs,1104
+llama_cloud/types/parse_job_config.py,sha256=KLBhRRGziH4eU2sZgab24c8-L9b8M9on1Dg0nVnObGc,6254
 llama_cloud/types/parse_plan_level.py,sha256=GBkDS19qfHseBa17EXfuTPNT4GNv5alyPrWEvWji3GY,528
 llama_cloud/types/parser_languages.py,sha256=Ps3IlaSt6tyxEI657N3-vZL96r2puk8wsf31cWnO-SI,10840
 llama_cloud/types/parsing_history_item.py,sha256=_MVzf43t84PbmjOzsMLZ_NBoyiisigLWz-fr0ZxU63g,1183
@@ -244,9 +242,9 @@ llama_cloud/types/permission.py,sha256=LjhZdo0oLvk7ZVIF1d6Qja--AKH5Ri0naUhuJvZS6
 llama_cloud/types/pg_vector_distance_method.py,sha256=U81o0ARjPR-HuFcVspHiJUrjIDJo3jLhB46vkITDu7M,1203
 llama_cloud/types/pg_vector_hnsw_settings.py,sha256=-RE59xUgHwNEyAwRYmOQ8SHeAqkSYBfCAROw7QomxUU,1758
 llama_cloud/types/pg_vector_vector_type.py,sha256=VwOohN566zw42UMlnuKTJopYJypsSnzWjCFmKRoU-bo,952
-llama_cloud/types/pipeline.py,sha256=eVNfQjfQTArB3prPeDkfDK6PtfhhBxW7-_VhH9MzlsE,2789
+llama_cloud/types/pipeline.py,sha256=4m1NIqTtG2DItvW69SWW3NjZPBL848VEW69Qbt2B7uo,2728
 llama_cloud/types/pipeline_configuration_hashes.py,sha256=7_MbOcPWV6iyMflJeXoo9vLzD04E5WM7YxYp4ls0jQs,1169
-llama_cloud/types/pipeline_create.py,sha256=pS1Lc5Ihh2OXMgRmaO_597a_6ddJEJL-m57efyRsgzw,2687
+llama_cloud/types/pipeline_create.py,sha256=kF9lOu4Kgwgg26Kj3VsAeHoi59jga6ka4oYkIzVy25M,2645
 llama_cloud/types/pipeline_create_embedding_config.py,sha256=PQqmVBFUyZXYKKBmVQF2zPsGp1L6rje6g3RtXEcdfc8,2811
 llama_cloud/types/pipeline_create_transform_config.py,sha256=HP6tzLsw_pomK1Ye2PYCS_XDZK_TMgg22mz17_zYKFg,303
 llama_cloud/types/pipeline_data_source.py,sha256=g8coq6ohp09TtqzvB3_A8Nzery3J5knIfxGWzUtozmg,2381
@@ -264,6 +262,11 @@ llama_cloud/types/pipeline_file_custom_metadata_value.py,sha256=ClFphYDNlHxeyLF5
 llama_cloud/types/pipeline_file_permission_info_value.py,sha256=a9yfg5n9po0-4ljGx8DtJoeLBwWFpaEk9ZQUN195BXg,211
 llama_cloud/types/pipeline_file_resource_info_value.py,sha256=s3uFGQNwlUEr-X4TJZkW_kMBvX3h1sXRJoYlJRvHSDc,209
 llama_cloud/types/pipeline_file_status.py,sha256=7AJOlwqZVcsk6aPF6Q-x7UzjdzdBj4FeXAZ4m35Bb5M,1003
+llama_cloud/types/pipeline_file_update_dispatcher_config.py,sha256=PiJ1brbKGyq07GmD2VouFfm_Y3KShiyhBXJkwFJsKXw,1222
+llama_cloud/types/pipeline_file_updater_config.py,sha256=KMHBYpH3fYDQaDVvxVgckosiWz0Dl3v5dC53Cgnmtb8,1761
+llama_cloud/types/pipeline_managed_ingestion_job_params.py,sha256=ahliOe6YnLI-upIq1v5HZd9p8xH6pPdkh2M_n_zM9TA,1180
+llama_cloud/types/pipeline_metadata_config.py,sha256=yMnPu6FnhagjuJ_rQ756WbIvVG5dzyXT1fmCYUAmCS0,1291
+llama_cloud/types/pipeline_status.py,sha256=aC340nhfuPSrFVZOH_DhgYHWe985J3WNHrwvUtjXTRA,481
 llama_cloud/types/pipeline_transform_config.py,sha256=zMr-ePLKGjbaScxbAHaSwYBL7rrNibVlnn0cbgElDfU,824
 llama_cloud/types/pipeline_type.py,sha256=tTqrhxHP5xd7W2dQGD0e5FOv886nwJssyaVlXpWrtRo,551
 llama_cloud/types/plan_limits.py,sha256=WAbDbRl8gsQxvhmuVB0YT8mry-0uKg6c66uivyppdQU,2056
@@ -276,8 +279,7 @@ llama_cloud/types/progress_event.py,sha256=Bk73A8geTVaq0ze5pMnbkAmx7FSOHQIixYCpC
 llama_cloud/types/progress_event_status.py,sha256=yb4RAXwOKU6Bi7iyYy-3lwhF6_mLz0ZFyGjxIdaByoE,893
 llama_cloud/types/project.py,sha256=4NNh_ZAjEkoWl5st6b1jsPVf_SYKtUTB6rS1701G4IQ,1441
 llama_cloud/types/project_create.py,sha256=GxGmsXGJM-cHrvPFLktEkj9JtNsSdFae7-HPZFB4er0,1014
-llama_cloud/types/prompt_conf.py,sha256=6vhUFOBL5MUUJ_ucyvFfmyNCaiPOWepviEawChu0enI,1550
-llama_cloud/types/pydantic_program_mode.py,sha256=QfvpqR7TqyNuOxo78Sr58VOu7KDSBrHJM4XXBB0F5z0,1202
+llama_cloud/types/prompt_conf.py,sha256=hh8I3jxk3K6e5QZoBCLqszohMYtk73PERYoL36lLmTk,1660
 llama_cloud/types/re_rank_config.py,sha256=mxRWwrC5BLg3DP1yEyRwW2lIpv5BuXZfTy8f4RbcOp0,1262
 llama_cloud/types/re_ranker_type.py,sha256=qYItMEHrf80ePBp7gNGBSL67mkTIsqco92WJaJiYweo,1123
 llama_cloud/types/recurring_credit_grant.py,sha256=19qI3p5k1mQ1Qoo-gCQU02Aa42XpEsmwxPF1F88F-Yg,1517
@@ -307,18 +309,16 @@ llama_cloud/types/role.py,sha256=SCi2TyFbc68RJuNB-OdcP8ut03Uv5zPZk84QMmf17w8,138
 llama_cloud/types/schema_relax_mode.py,sha256=v4or6dYTvWvBBNtEd2ZSaUAb1706I0Zuh-Xztm-zx_0,635
 llama_cloud/types/semantic_chunking_config.py,sha256=dFDniTVWpRc7UcmVFvljUoyL5Ztd-l-YrHII7U-yM-k,1053
 llama_cloud/types/sentence_chunking_config.py,sha256=NA9xidK5ICxJPkEMQZWNcsV0Hw9Co_bzRWeYe4uSh9I,1116
-llama_cloud/types/sentence_splitter.py,sha256=GbC3KE20Nd85uzO4bqJttjqJhQ_1co2gKnSQxzfOAiM,2140
 llama_cloud/types/status_enum.py,sha256=cUBIlys89E8PUzmVqqawu7qTDF0aRqBwiijOmRDPvx0,1018
 llama_cloud/types/struct_mode.py,sha256=ROicwjXfFmgVU8_xSVxJlnFUzRNKG5VIEF1wYg9uOPU,1020
 llama_cloud/types/struct_parse_conf.py,sha256=kKmxsfllbXlRVVDmJtL3Uto9B340row00mYXCzF5tX4,2245
-llama_cloud/types/supported_llm_model.py,sha256=0v-g01LyZB7TeN0zwAeSJejRoT95SVaXOJhNz7boJwM,1461
+llama_cloud/types/supported_llm_model.py,sha256=hubSopFICVNEegbJbtbpK6zRHwFPwUNtrw_NAw_3bfg,1380
 llama_cloud/types/supported_llm_model_names.py,sha256=xZhgu4NcxnA61vmQsxDFgPSRjWtczcXOoCKrtwOBWqc,2161
 llama_cloud/types/text_block.py,sha256=X154sQkSyposXuRcEWNp_tWcDQ-AI6q_-MfJUN5exP8,958
 llama_cloud/types/text_node.py,sha256=Tq3QmuKC5cIHvC9wAtvhsXl1g2sACs2yJwQ0Uko8GSU,2846
 llama_cloud/types/text_node_relationships_value.py,sha256=qmXURTk1Xg7ZDzRSSV1uDEel0AXRLohND5ioezibHY0,217
 llama_cloud/types/text_node_with_score.py,sha256=k-KYWO_mgJBvO6xUfOD5W6v1Ku9E586_HsvDoQbLfuQ,1229
 llama_cloud/types/token_chunking_config.py,sha256=XNvnTsNd--YOMQ_Ad8hoqhYgQftqkBHKVn6i7nJnMqs,1067
-llama_cloud/types/token_text_splitter.py,sha256=0o3dml94ub5KLy3E5MjxfK4IwVAn0-VTE4zVWG1fUZE,2048
 llama_cloud/types/transformation_category_names.py,sha256=Wb7NBB0f-tEtfEZQis-iKy71SUKmmHFcXf6XLn6g0XU,545
 llama_cloud/types/usage_and_plan.py,sha256=bclc7TE7CTBu7RLiTHG426dziyj--I8m5NVu86I2AV4,1065
 llama_cloud/types/usage_metric_response.py,sha256=ukvtNZLeLacv-5F0-GQ5wTBZOPUPEjAeurgYPc4s7nA,1047
@@ -334,7 +334,7 @@ llama_cloud/types/validation_error_loc_item.py,sha256=LAtjCHIllWRBFXvAZ5QZpp7CPX
 llama_cloud/types/vertex_ai_embedding_config.py,sha256=DvQk2xMJFmo54MEXTzoM4KSADyhGm_ygmFyx6wIcQdw,1159
 llama_cloud/types/vertex_embedding_mode.py,sha256=yY23FjuWU_DkXjBb3JoKV4SCMqel2BaIMltDqGnIowU,1217
 llama_cloud/types/vertex_text_embedding.py,sha256=-C4fNCYfFl36ATdBMGFVPpiHIKxjk0KB1ERA2Ec20aU,1932
-llama_cloud-0.1.19.dist-info/LICENSE,sha256=_iNqtPcw1Ue7dZKwOwgPtbegMUkWVy15hC7bffAdNmY,1067
-llama_cloud-0.1.19.dist-info/METADATA,sha256=1VcJf7tzF1bifeNhTbBaRxN5STLYpLydLOJJJ7Os6ck,902
-llama_cloud-0.1.19.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-llama_cloud-0.1.19.dist-info/RECORD,,
+llama_cloud-0.1.21.dist-info/LICENSE,sha256=_iNqtPcw1Ue7dZKwOwgPtbegMUkWVy15hC7bffAdNmY,1067
+llama_cloud-0.1.21.dist-info/METADATA,sha256=AyJOHUBeiTz4oFSdEaOFUWUPp_bqoiVsX-B3erArGTc,1194
+llama_cloud-0.1.21.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+llama_cloud-0.1.21.dist-info/RECORD,,

{llama_cloud-0.1.19.dist-info → llama_cloud-0.1.21.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: poetry-core 2.0.1
 Root-Is-Purelib: true
 Tag: py3-none-any

llama_cloud/types/character_splitter.py

@@ -1,46 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class CharacterSplitter(pydantic.BaseModel):
-    """
-    A splitter that splits text into characters.
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
-    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
-    paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
-    secondary_chunking_regex: typing.Optional[str]
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/code_splitter.py

@@ -1,50 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class CodeSplitter(pydantic.BaseModel):
-    """
-    Split code using a AST parser.
-
-    Thank you to Kevin Lu / SweepAI for suggesting this elegant code splitting solution.
-    https://docs.sweep.dev/blogs/chunking-2m-files
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    language: str = pydantic.Field(description="The programming language of the code being split.")
-    chunk_lines: typing.Optional[int] = pydantic.Field(description="The number of lines to include in each chunk.")
-    chunk_lines_overlap: typing.Optional[int] = pydantic.Field(
-        description="How many lines of code each chunk overlaps with."
-    )
-    max_chars: typing.Optional[int] = pydantic.Field(description="Maximum number of characters per chunk.")
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/configured_transformation_item_component.py

@@ -1,22 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-from .character_splitter import CharacterSplitter
-from .code_splitter import CodeSplitter
-from .markdown_element_node_parser import MarkdownElementNodeParser
-from .markdown_node_parser import MarkdownNodeParser
-from .page_splitter_node_parser import PageSplitterNodeParser
-from .sentence_splitter import SentenceSplitter
-from .token_text_splitter import TokenTextSplitter
-
-ConfiguredTransformationItemComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CharacterSplitter,
-    PageSplitterNodeParser,
-    CodeSplitter,
-    SentenceSplitter,
-    TokenTextSplitter,
-    MarkdownNodeParser,
-    MarkdownElementNodeParser,
-]

llama_cloud/types/llm.py

@@ -1,60 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-from .base_prompt_template import BasePromptTemplate
-from .pydantic_program_mode import PydanticProgramMode
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class Llm(pydantic.BaseModel):
-    """
-    The LLM class is the main class for interacting with language models.
-
-    Attributes:
-    system_prompt (Optional[str]):
-    System prompt for LLM calls.
-    messages_to_prompt (Callable):
-    Function to convert a list of messages to an LLM prompt.
-    completion_to_prompt (Callable):
-    Function to convert a completion to an LLM prompt.
-    output_parser (Optional[BaseOutputParser]):
-    Output parser to parse, validate, and correct errors programmatically.
-    pydantic_program_mode (PydanticProgramMode):
-    Pydantic program mode to use for structured prediction.
-    """
-
-    callback_manager: typing.Optional[typing.Any]
-    system_prompt: typing.Optional[str]
-    messages_to_prompt: typing.Optional[str] = pydantic.Field(
-        description="Function to convert a list of messages to an LLM prompt."
-    )
-    completion_to_prompt: typing.Optional[str] = pydantic.Field(
-        description="Function to convert a completion to an LLM prompt."
-    )
-    output_parser: typing.Optional[typing.Any]
-    pydantic_program_mode: typing.Optional[PydanticProgramMode]
-    query_wrapper_prompt: typing.Optional[BasePromptTemplate]
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/markdown_element_node_parser.py

@@ -1,51 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-from .llm import Llm
-from .node_parser import NodeParser
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class MarkdownElementNodeParser(pydantic.BaseModel):
-    """
-    Markdown element node parser.
-
-    Splits a markdown document into Text Nodes and Index Nodes corresponding to embedded objects
-    (e.g. tables).
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    llm: typing.Optional[Llm]
-    summary_query_str: typing.Optional[str] = pydantic.Field(description="Query string to use for summarization.")
-    num_workers: typing.Optional[int] = pydantic.Field(description="Num of workers for async jobs.")
-    show_progress: typing.Optional[bool] = pydantic.Field(description="Whether to show progress.")
-    nested_node_parser: typing.Optional[NodeParser]
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/markdown_node_parser.py

@@ -1,52 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class MarkdownNodeParser(pydantic.BaseModel):
-    """
-    Markdown node parser.
-
-    Splits a document into Nodes using Markdown header-based splitting logic.
-    Each node contains its text content and the path of headers leading to it.
-
-    Args:
-    include_metadata (bool): whether to include metadata in nodes
-    include_prev_next_rel (bool): whether to include prev/next relationships
-    header_path_separator (str): separator char used for section header path metadata
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    header_path_separator: typing.Optional[str] = pydantic.Field(
-        description="Separator char used for section header path metadata."
-    )
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/pydantic_program_mode.py

@@ -1,41 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import enum
-import typing
-
-T_Result = typing.TypeVar("T_Result")
-
-
-class PydanticProgramMode(str, enum.Enum):
-    """
-    Pydantic program mode.
-    """
-
-    DEFAULT = "default"
-    OPENAI = "openai"
-    LLM = "llm"
-    FUNCTION = "function"
-    GUIDANCE = "guidance"
-    LM_FORMAT_ENFORCER = "lm-format-enforcer"
-
-    def visit(
-        self,
-        default: typing.Callable[[], T_Result],
-        openai: typing.Callable[[], T_Result],
-        llm: typing.Callable[[], T_Result],
-        function: typing.Callable[[], T_Result],
-        guidance: typing.Callable[[], T_Result],
-        lm_format_enforcer: typing.Callable[[], T_Result],
-    ) -> T_Result:
-        if self is PydanticProgramMode.DEFAULT:
-            return default()
-        if self is PydanticProgramMode.OPENAI:
-            return openai()
-        if self is PydanticProgramMode.LLM:
-            return llm()
-        if self is PydanticProgramMode.FUNCTION:
-            return function()
-        if self is PydanticProgramMode.GUIDANCE:
-            return guidance()
-        if self is PydanticProgramMode.LM_FORMAT_ENFORCER:
-            return lm_format_enforcer()

llama_cloud/types/sentence_splitter.py

@@ -1,50 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class SentenceSplitter(pydantic.BaseModel):
-    """
-    Parse text with a preference for complete sentences.
-
-    In general, this class tries to keep sentences and paragraphs together. Therefore
-    compared to the original TokenTextSplitter, there are less likely to be
-    hanging sentences or parts of sentences at the end of the node chunk.
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
-    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
-    paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
-    secondary_chunking_regex: typing.Optional[str]
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/token_text_splitter.py

@@ -1,50 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class TokenTextSplitter(pydantic.BaseModel):
-    """
-    Implementation of splitting text that looks at word tokens.
-    """
-
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
-    callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
-    chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
-    chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
-    separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
-    backup_separators: typing.Optional[typing.List[typing.Any]] = pydantic.Field(
-        description="Additional separators for splitting."
-    )
-    keep_whitespaces: typing.Optional[bool] = pydantic.Field(
-        description="Whether to keep leading/trailing whitespaces in the chunk."
-    )
-    class_name: typing.Optional[str]
-
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
-
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}