AI HelpAdded the modern AI help function on the Enter-Viewer display. Now you can use it to generate annotations in your inputs mechanicallyAPIAdded inference parameters customization and versatile API key choice Bug FixesPython SDKAdded inference parameters customization and versatile API key choiceBuilt-in YAML workflow interfaces with proto endpointsEnhanced the SDK’s foundational constructionNew Printed FashionsPrinted a number of new, ground-breaking fashionsLlamaIndexFashionsAdded potential to fine-tune text-to-text fashions[Enterprise Preview] Mounted a difficulty with the Leaderboard, which organizes fashions primarily based on their analysis outcomesBug FixesModulesEliminated collaborative purposes from the apps drop-down checklist inside the Set up Module modal when an org consumer is chosenEnhanced the default app choice within the Set up Module modalImproved the search performance for modulesLaunched a useful addition to the module’s viewer web page—an easy-to-use copy iconEnter-SupervisorAdded potential to view and tag textual content inputs inside the Enter-ViewerBug FixesInvitesGroup Settings and AdministrationBug FixesAppsEnhanced App Settings web page to show particulars of collaboratorsBug FixesLogin/Logout and Signup MoveLaunched modal pop-ups for login and signup, and for numerous eventualities the place redirects had been beforehand employedBug FixesLabeling DutiesBug FixesWorkflowsBug FixesMarkdown SearchAdded potential to carry out text-based searches inside the markdown notes of apps, fashions, workflows, modules, and datasetsCowl PictureAdded cowl picture help for numerous kinds of assets, together with apps, datasets, fashions, workflows, and modules
AI Help
Added the modern AI help function on the Enter-Viewer display. Now you can use it to generate annotations in your inputs mechanically
- In contrast with current Good Search and Bulk Labeling options that can be utilized inside the Enter-Supervisor display to speed up labeling, our latest AI-Help options might be employed whereas working with particular person Inputs inside the Enter-Viewer display.
- To begin, merely choose an current Mannequin or Workflow (both owned by you or from Clarifai’s Neighborhood) inside the Annotate Mode settings within the right-hand sidebar.
- For the complete story try our weblog!
API
Added inference parameters customization and versatile API key choice
- Now you can configure inference parameters akin to temperature, max tokens, and extra, relying on the particular mannequin you’re utilizing, for each text-to-text and text-to-image generative duties. This empowers you to customise and fine-tune your mannequin interactions to raised fit your particular person wants.
Bug Fixes
- Mounted a difficulty the place the ListWorkflows endpoint fetched workflows from deleted apps. Beforehand, workflows from deleted purposes had been fetched within the response of the ListWorkflows endpoint. We fastened the problem.
Python SDK
Added inference parameters customization and versatile API key choice
- The SDK helps the next textual content information codecs: plain textual content, CSV, and TSV (in roadmap).
- It helps the next picture information codecs: JPEG, PNG, TIFF, BMP, WEBP, and GIF.
- You could have the pliability to add information from both URLs or native storage, whether or not it is inside a single folder or unfold throughout a number of sub-folders.
- You’ll be able to add textual content information enriched with metadata and textual content classification annotations.
- You too can add picture information enriched with annotations, geoinformation, and metadata data.
- You’ll be able to effectively create apps designed for textual content mode and picture mode use circumstances.
- The SDK ensures clear progress monitoring throughout every add and promptly experiences any encountered errors.
Built-in YAML workflow interfaces with proto endpoints
- Within the SDK, the workflow interfaces are actually represented in YAML format, however they’re seamlessly built-in with proto endpoints for environment friendly communication and interplay.
Enhanced the SDK’s foundational construction
- The SDK now helps authentication solely utilizing Private Entry Tokens (PAT) and UserIDs.
- We plan to supply helper utilities for wealthy textual content formatting and printing to facilitate a user-friendly interplay.
- We’re working to continually add a strong error-handling system that covers numerous eventualities.
New Printed Fashions
Printed a number of new, ground-breaking fashions
- Wrapped Falcon-40B-Instruct, a causal decoder-only Massive Language Mannequin (LLM) constructed by TII primarily based on Falcon-40B and fine-tuned on a mix of Baize.
- Wrapped WizardLM-70B, a mannequin fine-tuned on the Llama2-70B mannequin utilizing Evol+ strategies; it delivers excellent efficiency.
- Wrapped CodeLlama-13B-Instruct-GPTQ, CodeLlama-34B-Instruct-GPTQ, and CodeLlama-7B-GPTQ. Code Llama is a household of code-focused LLMs, constructed upon Llama 2. These fashions excel at filling in code, dealing with in depth enter contexts, and following programming directions with out prior coaching for numerous programming duties.
- Wrapped WizardLM-13B, an LLM fine-tuned on the Llama-2-13b mannequin utilizing the Evol+ strategy; it delivers excellent efficiency.
- Wrapped WizardCoder-15B, a code-based LLM that has been fine-tuned on Llama 2 utilizing the Evol-Instruct technique and has demonstrated superior efficiency in comparison with different open-source and closed-source LLMs on distinguished code technology benchmarks.
- Wrapped WizardCoder-Python-34B, a code-based LLM that has been fine-tuned on Llama 2. It excels in Python code technology duties and has demonstrated superior efficiency in comparison with different open-source and closed-source LLMs on distinguished code technology benchmarks.
- Wrapped Phi-1, a high-performing 1.3 billion-parameter text-to-code language mannequin, excelling in Python code technology duties whereas prioritizing high-quality coaching information.
- Wrapped Phi-1.5, a 1.3 billion parameter LLM that excels at advanced reasoning duties and was skilled on a high-quality artificial dataset.
- Wrapped OpenAI’s GPT-3.5-Turbo-Instruct, an LLM designed to excel in understanding and executing particular directions effectively. It excels at finishing duties and offering direct solutions to questions.
- Wrapped Mistral-7B-Instruct, a state-of-the-art 7.3 billion parameter language mannequin, outperforming Llama2-13B in a number of NLP benchmarks, together with code-related challenges.
LlamaIndex
We now help integrating with the LlamaIndex information framework for numerous use circumstances, together with:
- Ingesting, structuring, and accessing exterior information for the LLMs you fine-tune on our platform. This lets you enhance the accuracy of your LLM purposes with personal or domain-specific information.
- Storing and indexing your information for numerous functions, together with integrating with our downstream vector search and database companies.
- Constructing an embeddings question interface that accepts any enter immediate and leverages your information to supply knowledge-augmented responses.
Fashions
Added potential to fine-tune text-to-text fashions
- Superior mannequin builders can now additional customise the habits and output of the text-to-text fashions for particular textual content technology duties. They will practice the fashions on particular datasets to adapt their habits for specific duties or domains.
[Enterprise Preview] Mounted a difficulty with the Leaderboard, which organizes fashions primarily based on their analysis outcomes
- Beforehand, for visible detection fashions, the displayed metrics included classification metrics like ROC, as a substitute of the anticipated metric, which is Imply Common Precision (MAP). The Leaderboard now appropriately shows MAP, similar to within the mannequin viewer’s model desk.
Bug Fixes
- Launched multi-label textual content classification with Hugging Face textual content classification pipeline. Beforehand, there was a difficulty with multi-label textual content classification utilizing the Hugging Face textual content classification pipeline. Whereas it labored properly for multi-class classification, it didn’t carry out appropriately for multi-label classification. We fastened the problem.
- Mounted points with the mannequin model particulars web page.
- Mounted a difficulty that prevented the mannequin model particulars web page from displaying any output fields.
- Mounted a difficulty that brought on the mannequin model particulars desk web page to crash unexpectedly.
- Mounted a difficulty the place the mannequin model particulars web page displayed incorrect parameter values when switching between totally different mannequin variations.
- Mounted a difficulty the place the mannequin model particulars web page displayed fields irrelevant to the particular mannequin kind. Pointless fields unrelated to the chosen mannequin kind are actually not seen.
- Mounted a difficulty the place the Mannequin Viewer web page incorrectly rotated photographs in particular group apps. Beforehand, when photographs with a portrait orientation (peak higher than width) had been submitted to some apps, the expected detection bins appeared misaligned or incorrect. The Mannequin Viewer web page now appropriately rotates photographs with portrait orientation, aligning detection bins precisely for improved consumer expertise and detection accuracy.
- Mounted a difficulty the place the mannequin ID disappeared after deciding on the Base embed_model within the mannequin creation course of. Beforehand, customers encountered a difficulty the place their beforehand entered mannequin ID would disappear upon deciding on a base embed mannequin when creating a brand new mannequin. We fastened the problem.
Modules
Eliminated collaborative purposes from the apps drop-down checklist inside the Set up Module modal when an org consumer is chosen
- Since group customers don’t have collaborative apps or interact in collaborations, we’ve optimized the interface by eradicating collaborated apps within the Set up Module modal particularly for this consumer group. This additionally fastened the app failure bug.
Enhanced the default app choice within the Set up Module modal
- The Set up Module modal now mechanically selects your present app because the default vacation spot to put in your chosen module.
Improved the search performance for modules
- This refinement within the search function affords a extra streamlined and productive expertise when in search of particular modules or associated content material.
Launched a useful addition to the module’s viewer web page—an easy-to-use copy icon
- Now you can click on the copy icon positioned within the Newest Model ID part to swiftly acquire the entire newest model URL for a module. This URL lets you expedite the module set up course of in your software.
Enter-Supervisor
Added potential to view and tag textual content inputs inside the Enter-Viewer
- Now we have designed a complete UI that lets you interactively create and handle annotations for textual content inputs.
Bug Fixes
- Improved keyboard shortcut performance in Enter-Viewer. Within the Enter-Viewer, you need to use keyboard shortcuts (hotkeys), akin to H, V, P, and B, to modify between annotation instruments.
- Beforehand, when opening the mannequin selector or every other component with a popover whereas within the Enter-Viewer, typing any of the hotkeys would unintentionally change instruments within the background. We fastened the problem, and the hotkeys don’t now set off occasions that have an effect on instruments within the background.
- Enabled error-free transition to annotation mode in Enter-Viewer. Beforehand, there was an error instantly after switching to annotation mode within the Enter-Viewer. We fastened the problem.
- Mounted situation stopping collaborators from creating annotations in Enter-Viewer. Collaborators can now actively take part within the annotation course of, contributing to a extra collaborative and environment friendly workflow.
- Improved the Enter-Viewer’s URL dealing with to make sure a extra seamless navigation expertise. Beforehand, there was a difficulty the place the enter ID a part of the route parameters was not utilized successfully for rendering, resulting in undesired redirects. We fastened the problem.
Invites
- Now you can seamlessly overview and settle for pending Group invites instantly inside the Portal, eliminating the necessity to rely solely on e mail for this goal. That is beneficial for each our SaaS providing and our on-premise deployments, because it caters to eventualities the place e mail help could also be restricted or unavailable.
Group Settings and Administration
Bug Fixes
- Mounted a difficulty with displaying incorrect menu gadgets within the cellular view. Beforehand, while you switched out of your private consumer account to a company account by clicking your profile icon on the top-right nook of the navigation menu bar, the drop-down checklist displayed your private particulars as a substitute of the group’s data. We fastened the problem.
- Mounted a difficulty the place a company contributor couldn’t entry public workflows. Group contributors (group members) can now fetch a whole checklist of all public workflows with none hindrances.
- Enabled group contributors to view accessible vacation spot apps in Set up Module Modal. We fastened a difficulty that beforehand hindered group contributors from viewing the checklist of accessible vacation spot apps inside the Set up Module modal when making an attempt to put in a module.
- Mounted a difficulty with looking for group members. Beforehand, while you used a number of parameters, akin to each first title and final title collectively, to seek for members whose first title or final title matched the question textual content, it may lead to an error inside the response. We fastened the problem.
- Mounted a difficulty the place collaborators with the group contributor function didn’t checklist mannequin evaluations. Beforehand, collaborators making an attempt to checklist mannequin evaluations encountered an error message stating “Inadequate scopes”, regardless of the expectation that the function would grant them entry to view evaluations. We fastened the problem.
Apps
Enhanced App Settings web page to show particulars of collaborators
- Now, you’ll be able to simply entry and think about the main points of your collaborators, together with their ID, first and final title, e mail, job function, and the date they had been added to the app.
Bug Fixes
- Mounted a difficulty the place the app thumbnails weren’t cached correctly. Beforehand, there was a difficulty the place the photographs of uploaded app thumbnails on the App Overview web page and on the drop-down sidebar checklist, which supplies fast entry to your accessible apps, often appeared as clean or lacking. We fastened the problem.
Login/Logout and Signup Move
Launched modal pop-ups for login and signup, and for numerous eventualities the place redirects had been beforehand employed
- Now we have retained devoted login and signup pages whereas introducing modal home windows for these actions. Now you can entry login and signup capabilities instantly out of your lively web page, offering fast and quick access to those important options.
- For operations like “Use Mannequin,” “Use Workflow,” “Set up Modules,” and extra, we’ve changed the redirection course of with modal pop-ups. This eliminates the additional step and ensures a smoother consumer journey.
Bug Fixes
- Mounted a difficulty with the reCAPTCHA system. We improved the reCAPTCHA system to supply customers a notably smoother and extra user-friendly expertise.
Labeling Duties
Bug Fixes
- Mounted a difficulty the place it was not attainable to submit labeled inputs for some labeling duties. Beforehand, you possibly can not submit labeled inputs for sure labeled duties. When engaged on some labeling duties, if you happen to loaded the enter, chosen the related ideas, and tried to submit your labeled enter, you possibly can encounter an error. We fastened the problem.
Workflows
Bug Fixes
- Mounted a difficulty with processing movies utilizing the Common workflow. Now you can confidently course of movies with the Common workflow with out encountering any hindrances or points.
- Mounted a difficulty with modifying a workflow. Beforehand, whereas modifying any workflow, the mannequin model displayed “No outcomes discovered,” which was inconsistent with the preliminary workflow creation expertise. The mannequin model habits now matches what’s displayed when initially making a workflow.
- Mounted a difficulty the place it was not attainable to repeat a workflow with out first altering its ID. Beforehand, you possibly can efficiently copy a workflow solely after altering the copied workflow ID. Now you can copy an current workflow, even if you happen to preserve the identical workflow title through the copying course of, akin to from “(workflow title)-copy” to “(workflow title)-copy.”
- Eliminated the default/base workflow from “Use Mannequin” modal. To make use of a mannequin in a workflow, go to the mannequin’s viewer web page, click on the “Use Mannequin” button on the upper-right nook of the web page, choose the “Use in a Workflow” tab, and choose a vacation spot app and its base workflow. You’ll be redirected to the workflow editor web page.
- Beforehand, if you happen to tried to replace the workflow within the editor web page, you possibly can encounter an error. The problem arises as a result of the app’s default/base workflow can’t be edited, however this limitation is communicated to the consumer late solely after they’ve made adjustments to the workflow. We fastened the problem by graying out or excluding the bottom workflow possibility when customers try to make use of a mannequin in an current base workflow.
Markdown Search
Added potential to carry out text-based searches inside the markdown notes of apps, fashions, workflows, modules, and datasets
- For example, while you go to https://clarifai.com/discover/fashions and enter “detecting the presence” within the search area, the outcomes will embrace any related useful resource the place the phrase “detecting the presence” is discovered inside the markdown notes. This function enhances search performance and permits for extra exact and context-aware discovery of assets primarily based on the content material inside their markdown notes.
Cowl Picture
Added cowl picture help for numerous kinds of assets, together with apps, datasets, fashions, workflows, and modules
- This function provides a visually participating component to your assets, making them extra interesting and informative. You too can delete the picture if you wish to.