Versions v41.1.x and v41.2.x are available to SaaS customers only.
41.2.3 (17 Jul 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.2.2 (9 Jul 2025)
Versions 41.2.0 and 41.2.1 were not released and are not supported.
Layout Editor
New
Improved Field List view for Structured layouts — You can now horizontally resize the right-hand panel in the Layout Editor, making it easier to view and edit long field names. This enhancement helps reduce errors when working with fields that have similar or lengthy names.
Updated
Full Layout Variation name now visible in the Structured Layout Editor — We’ve updated the Structured Layout Editor to display the full layout variation name for longer entries. The full name of a layout variation is now visible directly in the header. This update makes it easier to differentiate between variations, especially when they have similar names. It helps users quickly identify which variation they’re working with, reducing confusion and saving time.
ORCA (Optical Reasoning and Cognition Agent) Vision Language Model (VLM) Blocks
New
Thresholding, Supervision, and Quality Assurance support for ORCA — To maximize the benefits of leveraging our VLM models in data extraction, we've added thresholding support for these models. Thresholding determines which transcriptions should be sent to Supervision and which can be automatically included in the output. Any transcriptions sent to Supervision are presented to keyers the same way as Flexible Extraction tasks are.
In addition to Supervision, we're also adding support for Quality Assurance tasks for the output of VLM models. The interface for these tasks is similar to the one used for Full-Page Transcription Quality Assurance tasks, which require keyers only to indicate whether the transcription is correct or incorrect. The data from these tasks is then used to calculate the accuracy of the models' output, and the system includes the data in the Manual Accuracy vs Machine Accuracy Report (Reporting > Accuracy). To learn more about QA tasks for VLMs, see Vision Language Model Quality Assurance.
More information about VLMs can be found in ORCA (Optical Reasoning and Cognition Agent) VLMs. To include VLM models in your workflows, contact your Hyperscience representative.
Fine-tuning support for ORCA VLM Blocks — Machine learning provides many benefits, including the ability to fine-tune model performance on customer-specific use cases and data. In v41.2, we're extending those capabilities to our in-house VLM (ORCA) installed in the application in a Hyperscience-managed process.
To take advantage of fine-tuning, you will be asked to provide the team with a representative set of documents, which they will then use to create layouts on your behalf. Next, they will annotate the documents and compute fine-tuning weights for each layout version. Those weights are then ingested into our ORCA VLM Block, helping it to provide more accurate transcriptions than it would have on its own.
For more information about this process, see ORCA (Optical Reasoning and Cognition Agent) VLMs. To implement it for your use case, contact your Hyperscience representative.
Training Data Management (TDM) for Classification Models
Updated
Handling Excluded Pages in Training Requirements — We’ve updated how Excluded pages are handled and displayed in TDM for Classification. These changes improve clarity and ensure the interface accurately reflects the requirements for training a Classification model for Semi-structured layouts.
Excluded pages are required only when a release contains a single Semi-structured or Additional layout.
Excluded pages are not required if the release contains two or more Semi-structured or Additional layouts.
The Run Training button is only enabled when all required data is present.
Fixed
Display logic for Excluded pages in TDM for Classification — We’ve updated how Excluded pages are shown in the Summary card of TDM for Classification.
The Excluded Pages card now displays a required page count only when the release contains a single Semi-structured or Additional layout.
When the release contains two or more such layouts, the Summary card displays only the number of uploaded pages, as Excluded pages are not required.
The required value is fixed and consistent with how requirements are shown for other layouts.
TDM for Identification Models
New
Search by Text Segment — We’ve added Search by Text Segment to Training Data Management for Table Identification models. This feature was previously available only during Field Identification Supervision tasks.
You can now search for text using specific text segments directly in the Training Data Management for Table ID models interface.
When Performance Optimization (
) is enabled, the search works only within the currently focused page.
Filter by multiple groups — You can now filter by multiple groups in TDM for Identification models. The Group filter supports multi-select, making reviewing and comparing documents easier across several groups. Additionally, you can filter by multiple statuses for more flexible and efficient review.
Updated
Easier navigation to Layouts from the Model Page — We’ve improved navigation from the Model page by making it easier to access the linked layout. The layout name on the model page now shows a clickable icon when hovered.
Previously, the icon was invisible until hovered over directly, which made it dificult to discover. This update improves usability and ensures users can quickly access layout details when working from the model view.
Flows
Updated
Styling of blocks in Flow Studio — We've modernized the styling of flow blocks in Flow Studio. We've also updated them to better distinguish between notification flows and other subflows and to show how many subflows are connected to the block.
Making routing more explicit in Document Processing Subflow V41 — We've visualized the routing that occurs in Document Processing Subflow V41, allowing you to see the start and end of each route. For example, after the Machine Identification Block, we've added a Routing Block with the name "Is Manual Identification needed?" that has two branches: a "Yes" branch that leads to the Manual Identification Block and "No" branch that leads to the Machine Transcription Block. This update does not change the functionality of the Document Processing Subflow.
Fixed
Recursion in nested subflows — We've fixed a recursion-related issue that caused errors when processing submissions through flows containing a large number of nested subflows.
Submission Processing
Updated
Processing of Semi-structured documents containing more than 100 pages — You can now process documents containing more than 100 pages with Document Processing Subflow V41. After Classification, the system automatically sends these documents to Manual Identification, ensuring that keyers can work on any necessary tasks. In previous versions, submitting documents with more than 100 pages would cause the documents' submissions to halt.
Tasks
Updated
Refreshed design — The Perform Tasks, Task Queue, and SLA Rules tabs have been updated with an improved visual design. The styling is now updated for a consistent look. To learn more, see Perform Tasks Tab (v41.2), Task Queue Tab (v41.2), and SLA Rules Tab (v41.2)
Manual Classification
Updated
Improved layout selection in Manual Classification — We’ve updated the Layout drop-down list in the Manual Classification task. Previously, keyers had to scroll through the full list of layouts to find a specific one. Searching for a layout by name is now available directly in the drop-down list. This change makes assigning layouts more efficient, especially when working with a large number of options.
Manual Identification
Updated
Disabling Annotation Co-pilot — We’ve disabled Annotation Co-pilot by default to optimize performance. To enable this feature, please contact your Hyperscience representative.
Normalization
Updated
Normalization of year values in dates — If the raw value for the last two digits of a year (`XY`) is less than or equal to 35, it will be normalized to 20XY (e.g., 29 will be normalized to 2029). Previously, this normalization applied to year values whose last two digits were less than or equal to 30.
More information about the normalization of Date data types can be found in Data Types.
Quality Assurance
New
Quality Assurance tasks for Full-Page Transcription (FTP) use cases — If you are using the Full-Page Transcription Block in your flows (e.g., in combination with Document Chat or LLM/VLM Blocks), your keyers can complete Quality Assurance tasks to determine the accuracy of the block's output. The resulting data is used to calculate Machine Accuracy, which can be found in the Manual Accuracy vs Machine Accuracy Report (Reporting > Accuracy).
In Full-Page Transcription QA tasks, keyers do not need to enter correct transcriptions. Instead, they only need to indicate whether the transcription is correct or incorrect, reducing the potential for errors and minimizing time spent on QA tasks.
Similar to other QA tasks, Full-Page Transcription QA tasks can be cleared in bulk from the Perform Tasks page (Tasks > Perform Tasks).
For more information, Full Page Transcription Quality Assurance.
Reporting
Updated
Metrics for flows and File Filter Blocks in Usage Report — We've added metrics for flows and File Filter Blocks to the Usage Report. These metrics include:
the number of flows in the instance,
the number of live flows in the instance,
the number of live flows containing a File Filter Block,
the number of live flows with file-size filters,
the number of live flows with image-dimension filters,
the number of live flows with file-extension filters, and
Information about the files filtered and allowed by File Filter Blocks.
Connections
New
Listeners for Microsoft Azure Blob Storage and Google Cloud Storage (GCS) — We've added Azure Blob Listener and GCS Listener options to Input Blocks, which allow you to ingest files and their metadata directly from Azure blobs and GCS buckets, respectively. This update provides an out-of-the-box solution for customers with submission files in these repositories, eliminating the need to create custom flows to ingest files from Azure or GCS.
These connections offer a variety of configuration options. For example, you can configure them to retrieve files with specific extensions or files that have not been modified for a certain length of time. You can also specify how often files should be retrieved.
As these Listeners retrieve submission files, they automatically move ingested files to an archive blob or bucket.
For more information, see Azure Blob Listener and GCS Listener.
Settings
New
Performance for large submissions — We’ve updated how the system handles large submissions.
Additionally, we’ve introduced a new system setting, Send documents to Training Data Management, for Identification and Classification models. This setting allows you to control whether submission data is used for model training. It is disabled by default and can be managed from the System Settings (Administration > System Settings).
This update helps reduce processing time and improve system stability when working with high volumes of data.
To learn more, see Application Settings Overview.
41.1.6 (17 Jul 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.1.5 (1 Jul 2025)
Document Reprocessing
Fixed
Reprocessing Structured documents reclassified as Semi-structured — We've fixed an issue that caused submissions to halt in the Machine Identification Block if they contained Structured documents with missing pages that were reclassified as Semi-structured documents.
41.1.4 (26 Jun 2025)
VLM Blocks
Updated
Names of available models — We've changed the names of the models available in VLM Blocks from "HSVLM" and "HSVLM-AWQ" to "ORCA" and "ORCA-AWQ," respectively.
If you used a VLM installed with the Install LLM/VLM Block in v41.1.3 or earlier, you need to change the model_name in your flow’s code from HSVLM to ORCA and the model_uuid to 14554188-cf8e-4f10-9057-d1df2f710072 after upgrading to v41.1.4 or later.
41.1.3 (4 Jun 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.1.2 (22 May 2025)
Document Renderer Block
Fixed
Processing images through the Document Renderer Block — We've fixed image-identification and -handling issues that caused submissions to halt in the Document Renderer Block in the following situations:
The Image Correction and Mobile Processing Classification settings for the flow were enabled, and:
PNG files were being processed, and the Quality Document Rendering setting for the flow was set to
80, orJPEG files were being processed, and the Quality Document Rendering setting for the flow was set to
40.
API
Updated
Filtering responses from Knowledge Store endpoints — We’ve added the following filtering options to our Knowledge Store endpoints:
You can now filter results from the Retrieving Knowledge Store Items endpoint by
external_id.You can now filter results from the Listing Knowledge Store Items endpoint by
collection.
41.1.1 (8 May 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.1.0 (7 May 2025)
Training Data Management (TDM)
New
Search by Text Segment — We’ve implemented the Search by Text Segment functionality in Training Data Management for Field Identification models.
Previously, this capability was only available during Field Identification Supervision tasks. Now, users can search for fields by specific text segments directly within the Training Data Management interface. This update makes it easier to locate, review, and annotate data during the model training process.
To learn more, see Training Data Management.
Updated
TDM for Classification Interface enhancements — We’ve improved the TDM for Classification interface as part of our ongoing efforts to streamline the user experience:
The Training Status column has been replaced with Date Deployed in the Classification Models table, providing clearer insight into the latest deployed version.
The Last Training value has been removed from the Summary card in the Overview tab of TDM for Classification.
Document Drift Management (Layout Triage)
Updated
Bounding Box Overlay — We've introduced a bounding box overlay feature in Document Drift Management (Layout Triage), making it easier to verify that the document is a variation on an existing layout.
Click the Toggle Field Overlay button on the Edit Metadata step in the Layout Triage experience to enable the Bounding Box Overlay feature.
When enabled, this feature displays:
Blue bounding boxes representing field locations.
Field names as tooltips when hovering over a box.
Similar Layout Variation Detection — We’ve improved support for Similar Layout Variation Detection when the Validate Classification Using LayoutID setting is enabled in the flow.
Previously, when this setting was enabled, Similar Layout Variation Detection only considered matches where the layout identifier exactly matched the one specified in the Classification settings. To learn more, see Layout Identifiers and Structured Classification and Layout Identifiers.
If the layout identifier didn’t match—even if the document was visually identical to an existing layout—no suggestions were provided. With this update, Similar Layout Variation Detection now works even when Layout ID validation is enabled.
Note that this update does not modify the existing Layout ID validation logic in Classification. It only extends support for Similar Layout Variation Detection in Document Drift Management (Layout Triage).
Page preview pane added to the Page Groups tab — We've added a Page preview pane to the Page Groups tab in Document Drift Management (Layout Triage).
You can now preview pages directly from the Pages column in the Page Groups list, similar to the preview functionality already available in the Unmatched Submissions table. This update allows you to review pages directly in the tab.
Fixed
Messaging for training jobs in SaaS deployments — We've fixed an issue that caused the following message to appear on the model details page when the Run training button was clicked: "Trainer task created, but a model will not be trained because there is no trainer that matches this version." This issue occurred even when there was a trainer available.
Flows
New
Zooming in and out in Flow Studio canvas — You can now zoom in and out to adjust your view of a flow in Flow Studio. With this enhancement, you can switch between focusing on a specific part of the flow and viewing the flow in its entirety.
To zoom in or out, you can click the buttons in the upper-left corner of the canvas, or you can use the keyboard shortcuts Command + + to zoom in, Command + - to zoom out, and Command + 0 to reset zoom to 100% on Mac OS. On Windows, you can use Control + + to zoom in, Control + - to zoom out, and Control + 0 to reset zoom to 100%. You can also use touch gestures such as pinching with two fingers, or you can use your mouse's clickwheel while holding the Command key (on MacOS) and Control key (on Windows).
This feature makes working with the canvas more manageable when viewing large or complex flows.
Automatic data deletion for flow runs — Flow runs that are not initiated from a submission are now included for deletion in automatic data deletion. Automatic data deletion makes it easier to comply with security policies and manage storage space. This change expands Hyperscience's data-deletion capabilities, as policies for data deletion in previous versions applied only to submission-based flow runs.
Note that submission-based flow runs are not affected in the deletions scheduled as part of this feature.
For more information, see PII Data Deletion.
Tables
Fixed
Assigning child rows to new parent rows in nested tables — We've resolved an issue that prevented child rows from being assigned to new parent rows in nested tables. The issue occurred when the parent table spanned across two or more pages.
Extracting single-character values — We've fixed an issue that prevented the system from detecting and transcribing single-character values in table columns.
Custom Supervision
Updated
Document Chat flow enhancements — To improve the user experience for implementing Document Chat, we've made the following updates in this version:
"Custom SV with Chat" parameter — We've introduced a new parameter that makes it easier for a flow to take a Chat flow identifier as an input and, as a result, to include a Custom Supervision task configured with Document Chat in existing flows.
New
chatrolefor flows — Flow developers can now assignchatas arolefor Document Chat subflows, allowing these subflows to be distinguished on the Flows page and included as an option for the Chat Flow setting within Custom Supervision Blocks.
.png?sv=2022-11-02&spr=https&st=2025-07-28T07%3A13%3A56Z&se=2025-07-28T07%3A47%3A56Z&sr=c&sp=r&sig=avosgJlwfSMWwuCDwnwpCTAyoCSE9oKUoQ2BvYrKcCs%3D)
For more details on Document Chat, see our Flows SDK documentation.
User Management
Fixed
Importing permission groups and authentication groups — We've fixed an issue that prevented users from importing both permission groups and authentication groups when no data for either type of group was already present in the instance (e.g., when migrating group data from one environment to another).
As part of this update, we've added a Create missing authentication groups setting to the Upload Existing tab of the Add Permission Group dialog box. When this setting is enabled, you can upload permission groups when there are no authentication groups present in the instance.
41.0.13 (8 Jul 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.0.12 (4 Jul 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.0.11 (2 Jul 2025)
Document Reprocessing
Fixed
Reprocessing Structured documents reclassified as Semi-structured — We've fixed an issue that caused submissions to halt in the Machine Identification Block if they contained Structured documents with missing pages that were reclassified as Semi-structured documents.
41.0.10 (20 Jun 2025)
VLM Blocks
Updated
Names of available models — We've changed the names of the models available in VLM Blocks from "HSVLM" and "HSVLM-AWQ" to "ORCA" and "ORCA-AWQ," respectively.
If you used a VLM installed with the Install LLM/VLM Block in v41.0.9 or earlier, you need to change the model_name in your flow’s code from HSVLM to ORCA and the model_uuid to 14554188-cf8e-4f10-9057-d1df2f710072 after upgrading to v41.0.10+.
Infrastructure
Updated
CUDA driver requirements for trainer GPUs — Trainer GPUs in v41.0.10 and later use an updated version of CUDA (12.4), which requires a minimal CUDA driver of 550.30.02. Deployments of previous versions of Hyperscience used CUDA 12.1, which required a minimal driver version of 530.30.03.
To learn more about installing CUDA drivers, see our “Enabling Trainers with GPUs articles'“ for Docker, Podman, and Kubernetes.
41.0.9 (4 Jun 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.0.8 (22 May 2025)
Version 41.0.7 was not released and is not supported.
Document Renderer Block
Fixed
Processing images through the Document Renderer Block — We've fixed image-identification and -handling issues that caused submissions to halt in the Document Renderer Block in the following situations:
The Image Correction and Mobile Processing Classification settings for the flow were enabled, and:
PNG files were being processed, and the Quality Document Rendering setting for the flow was set to
80, orJPEG files were being processed, and the Quality Document Rendering setting for the flow was set to
40.
41.0.6 (24 Apr 2025)
VLM Blocks
Updated
Improved memory efficiency during Vision Language Model (VLM) initialization — We’ve reduced memory usage when initializing VLM Blocks. This update improves startup performance and stability by minimizing memory spikes when loading large model assets.
File Downloads
Updated
File-download behavior — We’ve updated the way files are delivered by the application. In certain cases, files may now be fetched directly from the object store using pre-signed URLs. While this change improves performance and scalability, download issues may occur in environments where object-store access is restricted at the network or browser level. To support these edge cases, you can revert to the previous file-delivery method by adding the following to your “.env” file:
REDIRECT_FILE_SERVING_TO_OBJECT_STORE=false
This setting ensures that files are downloaded and served directly by the application rather than accessed through the browser. For more information, please contact Hyperscience Support.
41.0.5 (14 Apr 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.0.4 (7 Apr 2025)
User Experience
Fixed
"Updated at" timestamps — We've fixed an issue that caused "Updated at" timestamps (e.g., in the upper-right corner of the Submissions and Flows pages) to be in the user's time zone instead of the time zone specified in the SYSTEM_TIME_ZONE ".env" variable.
Tables
Fixed
Processing submissions with nested tables — We've resolved an issue that caused submissions containing nested tables to halt in Machine Transcription. The issue occurred when all rows in a child table were deleted during Manual Identification.
41.0.3 (28 Mar 2025)
Reprocessing
Updated
"Reprocessing Enabled" setting — We've added a Reprocessing Enabled setting to the Reprocessing Block.
As part of this update, we've changed the logic for clicking Mark Layout Variation Incorrect during Supervision to the following:
If the Reprocessing Block is present and its Reprocessing Enabled setting is selected:
The layout will be removed from all pages of the current document, and a Manual Classification task will be created for it.
If the Reprocessing Block is not present, or if its Reprocessing Enabled setting is deselected:
Processing of the submission will end, and no data will be extracted from it.
41.0.2 (27 Mar 2025)
Updates
This version includes a number of updates that optimize our internal testing and deployment processes.
41.0.1 (18 Mar 2025)
Version 41.0.0 was not released and is not supported.
User Experience
Updated
Additional strings available for translation — We've enabled the translation of additional text in the application's user interface. This text is visible to users in the Data Keyers permission group (e.g., Supervision interfaces). For a complete list of text strings available for translation, download the en_US translation file after upgrading.
To learn more about translating the user interface, see Providing a Translated User Interface.
Layouts
Updated
Auto-splitting — Semi-structured documents now benefit from advanced layout-level grouping logic, enabling document-specific splitting rules. The Auto-splitting feature introduces enhanced document processing capabilities, allowing customers to split back-to-back documents of the same layout automatically. This update provides more flexibility and reduces manual intervention, improving efficiency for document-heavy workflows.
In v41, you can define specific rules for splitting documents within the Layout Editor. Only one rule can be applied per layout. The supported rules include:
Fixed Number of Pages — Automatically splits documents based on a set number of pages.
First Page Regex Match — Splits documents when a specific regular-expression (regex) pattern is detected on the first page.
Last Page Regex Match — Splits documents when a specific regex pattern is detected on the last page.
Page-to-Page Regex Matching — Compares regex patterns across consecutive pages to determine splitting logic.
If a splitting rule fails (e.g., regex not found or page count mismatch), documents can be automatically sent for manual review. This option is configurable at the layout level.
Auto-splitting is available for flows created in v40.2 and later.
For more information, see Auto-splitting.
Fixed
Marking of annotations as ineligible — We’ve resolved an issue where annotations were incorrectly marked as ineligible in Training Data Management when multiple live versions of the same layout existed.
Training Data Management
Updated
TDM for Classification user-interface enhancements — We’ve updated the user interface for managing Semi-structured Classification models to align with the user experience for Identification models. In particular, we’ve introduced the Model History table, which allows you to view and manage different versions of Classification models.
To learn more about TDM for Classification, see TDM for Classification Models.
Fixed
Previewing pages in Training Data Management (TDM) for Classification models — We've fixed an issue that caused delays in loading preview images of pages in TDM for Classification models.
Accuracy
Updated
Field- and column-level accuracy targets for identification in Semi-structured documents — In some submissions, identification accuracy may be more important for some fields or table columns than others (e.g., policy / account numbers, addresses). For these use cases, you can set individual accuracy targets for the identification of crucial fields and table columns. This update eliminates the need to set higher accuracy targets at the flow level, preventing your keyers from having to complete Identification Supervision tasks for lower-value fields and table columns.
You can set field- and column-level accuracy targets for identification in a flow's settings.
The accuracy achieved for each field or column you've set a specific target for can be found on the Accuracy page of the application (Reporting > Accuracy).
Note that setting accuracy targets at the field or column level has no effect on the number of QA tasks that the system creates.
To learn more about this feature, see Identification Settings.
Flows
New
Support for Python 3.12 — We now support the use of Python 3.12 in custom code, custom flows, and Python packages. In addition, we still support the use of Python 3.9 and 3.11 . This support ensures the continued security and reliability of your operations as you upgrade your code and flows to use Python 3.12.
The default flows included in Hyperscience have been updated to use Python 3.12.
While you can use any of our supported Python versions in Hyperscience v41, we recommend upgrading the entirety of your flows' code to use Python 3.12 as soon as possible.
As part of this update, a list of installed packages for Python 3.12 can be found on the Python Packages page in the application (Flows > Python Packages). The page also contains lists of installed packages for Python 3.9 and 3.11.
While Hyperscience supports the use of Python 3.9 in v41, note that Python 3.9 will reach end-of-life in October 2025 and will not be supported in v42.
More information about Python 3.12 support can be found in Developing Flows.
Updated
File Filter Block in Document Processing flow — The Document Processing flow included in v41 contains the File Filter Block, which allows you to specify the criteria for files that will be accepted or rejected during the submission-creation process. In previous versions of Hyperscience, this block could be used only in custom flows.
To learn more about the File Filter Block, see Document Processing Subflow Settings.
Fixed
Submission processing and size of database transactions — We've fixed a database-transaction issue that delayed the advancement of submissions through flows. As part of this update, we've introduced the HYPERFLOW_ENGINE_MAX_TASKS_PER_DB_TRANSACTION ".env" file variable, which allows you to specify the maximum number of workflow-engine tasks that are included in a single database transaction.
For more information, see Tasks Per Database Transaction.
LLM Blocks
Updated
LLM Install Block — With the LLM Install Block, you can use LLM Blocks in your own custom flows. When initiated, the LLM Install Block first checks for the presence of an LLM in the instance and installs one if one is not present. In previous versions, LLM Blocks could be used only in specialized flows provided by Hyperscience, and the model-installation process required a separate flow.
For more information on using the LLM Install Block, see Flow Blocks.
Custom Supervision
Updated
Document Chat — If your Knowledge Workers need specific, hard-to-find details to complete Custom Supervision tasks, you can add a Chat Component to a Custom Supervision Block. The Chat Component enables the Knowledge Worker to send questions or other prompts about the documents in the Custom Supervision Task to an LLM or other third-party service.
For example, a Knowledge Worker can ask, "Are there test results for [condition name]?" and have the LLM respond with relevant data from the document in complete sentences.
There are no restrictions on the prompts, or questions, that Knowledge Workers can send to the LLM. Because of the free-form nature of the prompts, we recommend making this feature available only to those Knowledge Workers who have training in the relevant field (e.g., nurses for medical decisions).
Note that this chat-like interface does not require an API connection to an LLM; if it is used with an LLM installed with the LLM Install Block, you can use the Chat Component in air-gapped instances that cannot access the internet.
Document Drift Management
Updated
Similar Layout Variation Detection — Similar Layout Variation Detection introduces an enhanced workflow for managing document variations by allowing you to easily identify and add new layouts as variations of existing ones. This update simplifies the process of handling diverse document formats and reduces the manual effort required to maintain layout variations. This feature is a key component of the broader Document Drift Management (Layout Triage) experience, aimed at improving document processing accuracy and efficiency.
To enable this feature, or for more information, contact your Hyperscience representative.
User-interface enhancements — The Document Drift Management interface has been updated with improved navigation and visibility to support more effective user experience. To learn more, see Document Drift Management (Layout Triage).
Infrastructure
Updated
Supported Docker versions — Hyperscience v41 supports Docker 25.0.4 and later. It will not run on earlier versions. For more information, see Docker-Related Changes in v41.
Supported operating system versions — As part of v41, we've made the following changes to the versions of operating systems that we support:
Ubuntu — We've removed support for Ubuntu 19 and earlier.
Red Hat Enterprise Linux (RHEL) — We've removed support for RHEL 8.9 and earlier.
Supported database versions — In v41, we've made the following updates to the versions of databases that we support:
PostgreSQL — We've added support for PostgreSQL 15 and 16 and removed support for PostgreSQL 13.
Microsoft SQL Server (MSSQL) — We've added support for MSSQL 2022 and removed support for MSSQL 2016.
For information on supported container environments, operating systems, and databases, see Infrastructure Requirements.