New updates and improvements
V7 Go
File splitter property in Go
The File Splitter splits PDFs and Excels into collections of individual pages or sheets.
Historically such splitting was generally done as a pre-processing step with code, but this is now available within Go natively, no code required.
This unlocks a deeper level of page by page or sheet by sheet analysis. For instance, you can turn an Excel file into a collection of sheets, run models over the individual sheets, and then aggregate these answers back up into a summary of summaries.
Since PDFs are split into pages represented by JPEGs, this also unlocks the native multimodal understanding of the latest foundation models, which can power tasks like reading charts or images from pages.
Excel exports now available in V7 Go
V7 Go now supports Excel file exports. Download a complete V7 project, and preserve your structure by saving each view as a separate sheet in the .xlsx file.
Benefit from easier data analysis and authorized sharing outside the V7 Go platform, the ability to add custom charts and reports without additional data manipulation steps. As well as using formulas and Excel functionalities on your V7 Go outputs and creating comprehensive backups in a widely-supported file format.
Improved Project Templates
The template library has been redesigned with a focus on industry-specific solutions. You'll find in-depth templates for sectors such as finance, law, and logistics for data extraction and analysis tasks.
These project templates will help you explore V7 Go's capabilities and serve as great starting points for your projects. Feel free to try them out and use them in your workflows.
Explore new templates here.
AI citations for JSON properties
You can now enable AI citations for JSON properties. This feature allows you to track the source of AI-generated insights within JSON structures, adding an extra layer of transparency to your data processing.
OpenAI's o1 and o1 mini models available in V7 Go
We've integrated OpenAI's latest model series, o1 and o1 mini, into V7 Go behind a feature flag. These models are pre-trained for chain-of-thought reasoning, making them ideal for complex tasks in data analysis, coding, and mathematical problem-solving.
These models prioritize accuracy over speed, taking more time to "think" before responding. While o1 outperforms GPT-4o in reasoning, it may not be suitable for all tasks. Please note the current rate limits of 100 requests per minute may cause errors, and they have higher token costs compared to GPT models.
Project-level permissions and User roles
V7 Go customers now have better control over project access and editing rights. Set projects as private or public, and assign specific view or edit permissions to members with the User role to prevent accidental edits.
Keep your most sensitive projects hidden from the rest of your team
Add colleagues or external users as project viewers, removing the risk of accidental edits
Invite new workspace users directly to a project within V7 Go
Admins and Owners still have full project visibility. Check out our documentation for more details.
Filters now live in V7 Go
You can now filter your data natively in Go, which was one of our top feature requests. Click the filter icon in the lower left corner to add filters and combine them using all/any/none logic for Text or Select properties.
AI reasoning in Select properties
For classification tasks in Select properties, the AI now provides explanations when it can't find a matching option. This improvement enhances transparency in AI workflows and helps you spot potential data taxonomy issues at a glance, as well as creating a feedback loop to iterate on your prompts.
Soon, we’ll add more granularity so you can define actions when the AI can’t find a match and show reasoning for successful matches too.
Long documents (100+ pages and beyond)
We've solved the "content too long" error for documents exceeding model input token limits. Our new chunking mechanism allows V7 Go to process extensive, multi hundred page documents like SEC Form S-1 filings, lengthy technical documentation, or court hearing transcripts.
This alpha feature is available behind a feature flag. Contact us with your use case, and we can enable it for your V7 Go account.
V7 Go Summer Update
We have some great news! Our V7 Go Summer Update is now live, packed with exciting new features to level-up your document processing, data extraction, and AI automation workflows.
Watch the video below to learn how to enable trustworthy AI in your company and automate even the most challenging processes:
Explore our latest features:
Ask Go. Set up projects in seconds using natural language
AI Citations. Verify AI outputs at a glance with PDF highlights
Collections. Organize unstructured data into custom tables
Web Properties. Extract data from URLs and perform web searches
Graphs (Beta). Interpret charts and convert them to tables with multimodal AI
Audio Analysis. Process audio files in batches for summaries and transcriptions
Supervised Fine-Tuning & RLHF. Teach AI to solve specialized tasks
Plus, we've added:
New AI models: GPT-4o Mini, Claude 3.5 Sonnet, and more
Python Code Tool for custom operations using NumPy, Pandas, and more
Improved CSV import with granular column and row mapping
Bring your own API key option for enterprise users
All of these features are designed to make your AI workflows more efficient, controllable, and secure.
GPT-4o mini now available in V7 Go
The new GPT-4o mini model from OpenAI is now available to all V7 Go users. This compact version offers performance similar to the standard GPT-4o, but at a fraction of the cost.
60% cheaper than GPT-3.5 Turbo and 96% cheaper than GPT-4o.
128K token context window with up to 16K output tokens per request.
Handles both text and vision inputs, with audio support coming soon.
GPT-4o mini is ideal for automation tasks that require multiple model calls and for processing large volumes of documents.
AI Citations powered by visual grounding
Struggling with unreliable AI outputs? Our new V7 Go feature ensures your AI responses are accurate by linking them to specific citations in your source files, such as PDF documents.
Visual grounding shows exactly where your AI found its information. This allows for instant verification of AI-generated responses, removes errors, and reduces hallucinations. Highlighted AI citations make your document processing workflows more transparent and trustworthy. They also slash QA time from hours to minutes.
To use the feature:
Toggle Grounding in your AI property setup
Inspect a selected entity and click the lightbulb icon
Click on sentences to navigate to the relevant citation
The feature is now available to all V7 Go users. Find out more about visual grounding in our documentation.
2x more free tokens in V7 Go
Based on valuable feedback from our early users like you, we've decided to double the number of Tokens available in the free plan. Now, new users receive 2x as many Go Tokens to power their tasks in V7 Go.
If you already have an existing account and want to redeem your extra Tokens, simply contact us, and our team will assist you.
To fully unlock the potential of Go for automating tasks at scale, you can also switch to one of our pro plans.
Run Python code directly in V7 Go
You can now execute Python code as part of your V7 Go workflows. Instead of using AI models for all tasks, add the Python Tool and write custom code snippets.
Access Python libraries. You can use the Python Tool for specialized tasks, such as parsing web-scraped content with BeautifulSoup4 or performing data manipulation with Pandas.
Get predictable and deterministic results. Generate consistent and controllable outputs to make your workflows more reliable in a production environment.
Reduce token consumption. Traditional code can sometimes provide a more efficient solution and will help you reduce the unnecessary expense of AI models.
How to use the Python Tool
Add a new property. Choose the correct type. The Python Tool supports Text, JSON, Single Select, and Multi Select properties.
Select Python Tool. From the list of tools, select Python Tool.
Add variables. Use @ to select and add variables based on other properties.
For a detailed guide, visit our documentation.
Add reference files to improve AI outputs
The new Library lets you add documents and images as guidelines for your AI models.
Use these files as additional inputs to improve the performance of LLMs when specialist, context-dependent knowledge is required.
Add your company-specific context and knowledge to foundation models
Use images, photos, or scans as reference for quality control or defect detection
Cross-reference your input data with custom policies, guidelines, or dictionaries
How to use the Library
Drag and drop PDFs, CSVs, or images into the Library section of the UI. These files will become selectable as inputs for all properties in your V7 Go projects.
Additionally, you can combine these files with the new Python Code Tool to use them as variables.
For more details, visit our documentation.
Claude 3.5 Sonnet is now available in V7 Go
You can now use the latest AI model from Anthropic in V7 Go for document processing, visual captioning, and much more.
Claude 3.5 Sonnet
Beats GPT4o on many reasoning benchmarks
2x faster than Claude 3.5 Opus
1/5th the cost of Opus, and cheaper than GPT4o
To set up a V7 Go project powered by Claude 3.5 Sonnet, edit an AI property and select the model from the Tool list.
If you want to find out more about the model and its performance, visit the official release post. You can also set up your own benchmarking tests directly in V7 Go.
Load More