Changelog
Follow up on the latest improvements and updates.
RSS
🤖
New AI Models Integration
What's New:
- Added Claude's latest models: 3.5 Haiku and 3.7 Sonnet
- Integrated four powerful open source models: DeepSeek, Mistral, Meta Llama, and Gemma
- Available in both standalone prompts and workflow environments
- Seamless model switching in existing workflows
- Mix and match different model types within the same workflow
Benefits:
- More options to balance performance, cost, and capabilities
- Access to cutting-edge Claude models with similar pricing to predecessors
- Leverage open source alternatives for specific use cases
- Build more flexible and cost-effective AI solutions
- Test different models against the same prompts to compare outputs
🖼️ OpenAI Image Generation Integration
What's New
: Integrated OpenAI's latest image generation model just two days after release.- Powerful image creation capabilities directly in Fetch Hive workflows
- Fully configurable generation parameters including quality, size, and format options
- Background settings (transparent, opaque, or auto)
- Adjustable image compression and quality levels
- Multiple image generation in a single request
- Complete image library for managing all generated assets
Benefits
:- Lightning-fast access to OpenAI's most cost-effective image model
- Easy integration with existing AI workflow steps
- Powerful visual content creation for marketing, design, and product teams
🧠 Improve with AI
What's New:
Create better prompts with AI assistance in both Prompts and Workflows.- AI-generated system prompts to guide LLM behavior
- AI-generated user prompts with clear instructions, steps, and output formats
- Ability to iterate on prompts with additional AI improvement requests
- Available in both standalone prompts and workflow prompts
Benefits:
- Quickly create 90% optimized prompts without prompt engineering expertise
- Clear prompt structure with instructions, steps, and formatting
- Reduced hallucinations with proper prompt construction
- Streamlined prompt creation for beginners and experts alike
🧩 Maximum Character Control for Website Scraping
What's New:
Set character limits on website scrape operations in workflows.- Control exactly how much content is scraped from websites
- Default conservative 7,500 character limit
- Customizable limits to fit your workflow needs
- Helps manage token consumption in complex workflows
Benefits:
- Prevents hitting LLM token limits in multi-step workflows
- Better control over input context size
- Improved reliability for workflows with multiple data sources
- More predictable workflow execution
📊 Advanced Dataset Configurations
What's New:
Enhanced control and transparency for vector database storage.- Choose between default (speed-optimized) or advanced chunking strategies
- Configure custom chunk length and overlap settings
- Remove sensitive data like emails and phone numbers
- Run custom prompts to clean or format data before storage
- Detailed metrics on chunks, paragraphs, sentences, tokens, and costs
Benefits:
- Complete transparency in how data is stored and chunked
- Better control over vector database storage
- Clear visibility into storage costs and token usage
- Improved data privacy with sensitive information removal
🔍 Test Dataset Searches
What's New:
Search your datasets directly in the dashboard without using agent credits.- Three search options: Hybrid, Vector, and Full Text
- Configurable chunk limits (1-20 results per search)
- Adjustable similarity thresholds for result quality control
- Real-time testing of your datasets before using in agents
Benefits:
- Verify dataset content before using in production
- Save credits by testing without agent invocation
- Fine-tune search parameters for optimal results
- Better understanding of how vector and text search differ
🌍 Search Localization
What's New:
Google Search, Google News, and Bing Search now support location and language customization.- Set specific country locations for search results
- Choose preferred language for search queries
- Available in all search-related workflow steps
Benefits:
- More accurate regional search results
- Better language-specific content discovery
- Enhanced international research capabilities
🔄 Fallback Search
What's New:
Implemented backup search services for improved reliability.- Two backup services available when primary service is down
- Automatic failover system
- Works with Google Search, Google News, and Bing Search
Benefits:
- Increased workflow reliability
- Reduced downtime
- Seamless service continuity
💬 Discussions and Commenting
What's New:
Team collaboration features for workflow results.- Comment on workflow steps
- @mention team members
- Discussion threads on activity logs
- Available across prompts, workflow steps, datasets, and agents
Benefits:
- Enhanced team collaboration
- Better knowledge sharing
- Streamlined feedback process
- Real-time notifications for mentions
🔗 Deep Linking
What's New:
Shareable links for activity logs and results.- Copy and share direct links to specific activities
- Compatible with external platforms (Discord, Slack)
- Instant access to relevant content
Benefits:
- Easy external sharing
- Improved team communication
- Seamless workflow referencing
You can now add
JSON Schema
steps to your Workflows
. Simply add the step to your workflow, then customize the object to fit your specific needs.
Now you will have ultimate control on how data is presented from completed Workflows, ready to integrate into your application flow!
Stay tuned for more updates!
You can now create your own custom Brand Kit inside the dashboard. Simply enter your business/brand domain and Fetch Hive will automatically generate the following content for you:
👉🏼
Brand Name
👉🏼
Brand Description
👉🏼
Brand Customer (Ideal Customer Profile)
👉🏼
List of competitors
From here you can easily integrate the Brand Kit data inside your workflows to customize your prompts even further with a few clicks!
Stay tuned for more updates!