Instructions to use pemix09/paperstack_document_data_retrieval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use pemix09/paperstack_document_data_retrieval with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("pemix09/paperstack_document_data_retrieval") - Notebooks
- Google Colab
- Kaggle
| <project version="4"> | |
| <component name="AutoImportSettings"> | |
| <option name="autoReloadType" value="SELECTIVE" /> | |
| </component> | |
| <component name="ChangeListManager"> | |
| <list default="true" id="5426c4e8-35e3-4a2b-8bc4-8ee661ab7192" name="Changes" comment="document data retrieval v.1 - automatic using ollama, without checking the data (and verifying them), with instructions to use the language of the document (not flexible, cannot"> | |
| <change afterPath="$PROJECT_DIR$/semantic_simillarity/convert_to_tflite_download_vocab.ipynb" afterDir="false" /> | |
| </list> | |
| <option name="SHOW_DIALOG" value="false" /> | |
| <option name="HIGHLIGHT_CONFLICTS" value="true" /> | |
| <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" /> | |
| <option name="LAST_RESOLUTION" value="IGNORE" /> | |
| </component> | |
| <component name="FileTemplateManagerImpl"> | |
| <option name="RECENT_TEMPLATES"> | |
| <list> | |
| <option value="Python Script" /> | |
| </list> | |
| </option> | |
| </component> | |
| <component name="Git.Settings"> | |
| <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" /> | |
| </component> | |
| <component name="GitHubPullRequestSearchHistory">{ | |
| "lastFilter": { | |
| "state": "OPEN", | |
| "assignee": "pemix09" | |
| } | |
| }</component> | |
| <component name="GithubPullRequestsUISettings">{ | |
| "selectedUrlAndAccountId": { | |
| "url": "https://github.com/pemix09/document-data-retrieval.git", | |
| "accountId": "8a222931-697e-4756-a51a-e6060944a565" | |
| } | |
| }</component> | |
| <component name="ProjectColorInfo">{ | |
| "associatedIndex": 7 | |
| }</component> | |
| <component name="ProjectId" id="37kAHtnvfEdwNcAdSBtJj0kacny" /> | |
| <component name="ProjectViewState"> | |
| <option name="hideEmptyMiddlePackages" value="true" /> | |
| <option name="showLibraryContents" value="true" /> | |
| </component> | |
| <component name="PropertiesComponent">{ | |
| "keyToString": { | |
| "ModuleVcsDetector.initialDetectionPerformed": "true", | |
| "Python.clean_scans.executor": "Run", | |
| "Python.compare_model_before_after_conversion_to_tflite.executor": "Run", | |
| "Python.convert_to_tflite.executor": "Run", | |
| "Python.document_type_classifierlearn.executor": "Run", | |
| "Python.map_scans_to_less_types.executor": "Run", | |
| "Python.process_syntethic_content.executor": "Run", | |
| "Python.retrieve_multilang.executor": "Run", | |
| "Python.summarizer_learn.executor": "Run", | |
| "Python.verify_converted_to_tflite.executor": "Run", | |
| "Python.verify_summarizer.executor": "Run", | |
| "RunOnceActivity.ShowReadmeOnStart": "true", | |
| "RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager": "true", | |
| "RunOnceActivity.git.unshallow": "true", | |
| "git-widget-placeholder": "main", | |
| "last_opened_file_path": "/Users/przemo/Coding/document data retrieval" | |
| } | |
| }</component> | |
| <component name="RecentsManager"> | |
| <key name="MoveFile.RECENT_KEYS"> | |
| <recent name="$PROJECT_DIR$/scans/courtDocument" /> | |
| <recent name="$PROJECT_DIR$/scans/birthCertificate" /> | |
| <recent name="$PROJECT_DIR$/scans/officialCertificate" /> | |
| <recent name="$PROJECT_DIR$/scans/rentalAgreement" /> | |
| <recent name="$PROJECT_DIR$/scans/educationDocument" /> | |
| </key> | |
| </component> | |
| <component name="SharedIndexes"> | |
| <attachedChunks> | |
| <set> | |
| <option value="bundled-python-sdk-53e2683a6804-9cdd278e9d02-com.jetbrains.pycharm.community.sharedIndexes.bundled-PC-251.26094.141" /> | |
| </set> | |
| </attachedChunks> | |
| </component> | |
| <component name="TaskManager"> | |
| <task active="true" id="Default" summary="Default task"> | |
| <changelist id="5426c4e8-35e3-4a2b-8bc4-8ee661ab7192" name="Changes" comment="" /> | |
| <created>1767436610679</created> | |
| <option name="number" value="Default" /> | |
| <option name="presentableId" value="Default" /> | |
| <updated>1767436610679</updated> | |
| </task> | |
| <task id="LOCAL-00001" summary="document data retrieval v.1 - automatic using ollama, without checking the data (and verifying them), with instructions to use the language of the document (not flexible, cannot"> | |
| <option name="closed" value="true" /> | |
| <created>1767695912197</created> | |
| <option name="number" value="00001" /> | |
| <option name="presentableId" value="LOCAL-00001" /> | |
| <option name="project" value="LOCAL" /> | |
| <updated>1767695912197</updated> | |
| </task> | |
| <option name="localTasksCounter" value="2" /> | |
| <servers /> | |
| </component> | |
| <component name="Vcs.Log.Tabs.Properties"> | |
| <option name="TAB_STATES"> | |
| <map> | |
| <entry key="MAIN"> | |
| <value> | |
| <State /> | |
| </value> | |
| </entry> | |
| </map> | |
| </option> | |
| </component> | |
| <component name="VcsManagerConfiguration"> | |
| <MESSAGE value="document data retrieval v.1 - automatic using ollama, without checking the data (and verifying them), with instructions to use the language of the document (not flexible, cannot" /> | |
| <option name="LAST_COMMIT_MESSAGE" value="document data retrieval v.1 - automatic using ollama, without checking the data (and verifying them), with instructions to use the language of the document (not flexible, cannot" /> | |
| </component> | |
| <component name="XDebuggerManager"> | |
| <breakpoint-manager> | |
| <breakpoints> | |
| <line-breakpoint enabled="true" suspend="THREAD" type="python-line"> | |
| <url>file://$PROJECT_DIR$/process_syntethic_content.py</url> | |
| <line>53</line> | |
| <option name="timeStamp" value="1" /> | |
| </line-breakpoint> | |
| <line-breakpoint enabled="true" suspend="THREAD" type="python-line"> | |
| <url>file://$PROJECT_DIR$/process_syntethic_content.py</url> | |
| <line>55</line> | |
| <option name="timeStamp" value="2" /> | |
| </line-breakpoint> | |
| <line-breakpoint enabled="true" suspend="THREAD" type="python-line"> | |
| <url>file://$PROJECT_DIR$/process_syntethic_content.py</url> | |
| <line>110</line> | |
| <option name="timeStamp" value="3" /> | |
| </line-breakpoint> | |
| <line-breakpoint enabled="true" suspend="THREAD" type="python-line"> | |
| <url>file://$PROJECT_DIR$/process_syntethic_content.py</url> | |
| <line>48</line> | |
| <option name="timeStamp" value="4" /> | |
| </line-breakpoint> | |
| </breakpoints> | |
| </breakpoint-manager> | |
| </component> | |
| </project> |