12/11/2024

๐Ÿ”ง Improved Test UX and Bug Fixes

  • ๐Ÿš€ Itโ€™s much easier to switch between prompt editing (Playground) and Tests now using tab navigation
  • ๐Ÿ“Š New users now get limited free usage for Anthropic & Google without providing their own API keys
  • ๐Ÿงช Added Gemini experimental model 1206
  • ๐Ÿ› Fixed index & id in response for multiple tool calls from Anthropic
  • ๐Ÿ› Fixed variables list rendering in prompt detail view
  • ๐Ÿ› Fixed missing user message in assistant playground
  • ๐Ÿ› Fixed copy-pasting prompts from playground to include new lines correctly
  • ๐Ÿ› Fixed dev console error when viewing non-JSON test results
12/04/2024

๐ŸŽจ Test design updates and new onboarding experience

  • ๐ŸŽจ Redesigned test interface to match playground styling and UX
  • ๐Ÿ“š Introduced new user onboarding flow for better getting started experience
  • โœจ Magic prompt enhancer with diff view and accept functionality
  • ๐Ÿž Fixed assistant deployment snippet generation
  • ๐Ÿž Added support for video URLs without file extensions
11/20/2024

๐Ÿ”— Improved test response UX and other fixes

  • ๐Ÿ“ You can now enable test response text wrapping to easily see longer responses
  • ๐Ÿ“ Added support for markdown in the test response drawer
  • ๐Ÿ”ง Fixed selection of content in the test response drawer
  • ๐ŸŽจ Fixed test variable icon color on theme switch without reload
  • ๐Ÿ”ง Adjusted LLM assertion to allow shorter Yes/No descriptions
  • ๐Ÿ”„ Fixed thread messages not saving with assistant API in Anthropic/Google
  • ๐Ÿ› Fixed a rare bug where a second main test config could be created
11/12/2024

๐Ÿ”— Shareable Prompts and Assistants, and UX Enhancements

  • ๐Ÿ”— Added OG tags to shareable prompt assistants for better visibility and discoverability.
  • ๐Ÿž When copy-pasting multiple rows into Tests, the order is now fixed.
  • โŒจ๏ธ Enhanced tab navigation in the messages drawer for better accessibility.
  • ๐Ÿ”„ Implemented proper handling of multiple test runs.
  • ๐Ÿ“‹ Formatted the test output preview and added a copy button for improved readability.
  • ๐Ÿž Resolved issues with Gemini tool calls in tests and Anthropic model behavior.
  • ๐Ÿ“ Added undo/redo functionality to the test table for easier editing.
  • ๐Ÿค– Introduced a prototype for LLM assertion generation.
  • ๐Ÿค– Added support for the xAI grok-beta model.
  • โœจ Implemented magic to generate descriptions and titles for assistants.
11/05/2024

๐Ÿค– New Model Support, Magic buttons, Testing Improvements, and Onboarding

  • ๐Ÿค– Added support for the Claude 3.5 Haiku model from Anthropic.
  • โœจ Introduced several โ€œmagicโ€ buttons throughout the app to improve your experience with LLMs. These include prompts for enhancing prompts, generating test cases, and more! Let us know which ones you find and how useful they are - itโ€™s like an Easter egg hunt!
  • ๐Ÿž Fixed an issue where the test data grid couldnโ€™t delete repeated test cases.
  • โš™๏ธ Introduced a โ€œnoneโ€ option for tool choice.
  • ๐Ÿ” Added a history viewer for better visibility into past events.
  • ๐Ÿ“ฑ Improved onboarding experience for mobile devices.
10/29/2024

๐Ÿž Post 1.0 Fixes and UI Improvements

  • ๐ŸŽจ Implemented various small UI fixes and improvements.
  • ๐Ÿ”ข Fixed an issue with ordering items in the testing table when they have the same creation date.
  • ๐Ÿ“ Improved test generation by passing test_inputs to the magic function for better test data.
  • ๐Ÿ“š Added templates and documentation links to the sidebar for easier access.
10/24/2024

๐Ÿš€ Langtail 1.0: Brand New Testing Interface, Assistants, and More!

Weโ€™re thrilled to announce the release of Langtail 1.0, packed with exciting new features and improvements!

๐Ÿ“Š Brand New Testing Interface

  • ๐Ÿ“ At the core of Langtail 1.0 is our new spreadsheet-like interface for testing LLM applications, designed to feel natural for anyone used to working with Excel or Google Sheets.

๐Ÿ”„ Test Configurations

  • ๐ŸŽš๏ธ Introducing test configurations, allowing you to easily create and compare tests across different models with just a few clicks.

๐Ÿ› ๏ธ Tools with Hosted Code

  • ๐Ÿ’ป Your prompts can now call tools and have the code run directly within Langtail, making prototyping and testing much easier without the need for mocking responses.
  • ๐Ÿ”’ Enjoy secure and fast code execution in a sandboxed environment powered by QuickJS.

๐Ÿง  Assistants: Memory Management for Prompts

  • ๐Ÿง  Langtail 1.0 introduces Assistants โ€“ stateful entities that automatically manage memory and conversation history, reducing the need for additional code.
  • ๐Ÿ”„ Assistants can be used across models, in tests, deployed as APIs, or integrated with tools.

๐Ÿ”’ Additional Features

  • ๐ŸŒž Light Mode: Introduced a new Light mode for the Langtail app, providing a refreshing alternative to the default Dark mode.
  • ๐Ÿ›ก๏ธ Protect your AI apps from prompt injection attacks and other security vulnerabilities with our built-in AI Firewall.
  • ๐Ÿ” Execute LLM-generated code securely in a sandboxed container, thanks to our partnership with E2B.
  • ๐Ÿ“š Explore a gallery of templates showcasing different ways Langtail can help your team.
  • ๐Ÿค– Added support for Google Gemini models, including the ability to attach videos to prompts.
  • ๐Ÿข Self-hosting: Langtail can now be self-hosted entirely on your infrastructure (contact us for more information).
09/24/2024

๐Ÿ› ๏ธ Tool Calls in Assistant Playground and Gemini Support

  • ๐Ÿ› ๏ธ Added the ability to handle tool calls in the Assistant Playground, allowing you to provide responses for tool calls not handled by Langtail function handlers.
  • ๐Ÿค– Introduced native support for Gemini models, leveraging the @google/generative-ai library under the hood, with support for tools, streaming, and various media formats as input.

๐Ÿ“‹ Other Improvements

  • ๐Ÿ” Fixed an issue with opening logs with prompts in the playground.
  • ๐Ÿ’ฐ Set Gemini model prices.
09/19/2024

๐ŸŒ Assistant Sharing Redesign, LLM Leaderboard, and Hosted Functions

๐Ÿค– Assistant Sharing Redesign

  • ๐ŸŒ Redesigned the assistant sharing feature, allowing you to make your AI assistants publicly accessible and share them as standalone apps.

๐Ÿ“Š LLM Leaderboard

  • ๐Ÿ“ˆ Introduced a new LLM leaderboard page to compare the performance of different language models.

๐Ÿ› ๏ธ Hosted Code Support

  • ๐Ÿ”Œ Added support for Hosted Code, enabling you to test your tools right inside Langtail by directly calling external APIs.

๐Ÿ”’ Security and Stability Improvements

  • ๐Ÿ”’ Ensured that only team members can edit shared assistants.
  • ๐Ÿค– Added support for new OpenAI models: o1-mini and o1-preview.
  • ๐Ÿ”ง Fixed issues with tool usage for Azure models and display names.

๐Ÿ” Shared Assistant Indexes

  • ๐Ÿ” Implemented shared assistant indexes for improved discoverability and searchability.
07/24/2024

๐Ÿ“ Text Assertion Enhancements and LLaMa 3.1 Support

  • ๐Ÿ“ Grouped all text operation assertions under โ€œTextโ€ for better organization.
  • ๐Ÿ”– Added new text assertion options: not equals, does not contain, and does not icontain.
  • ๐Ÿ“ Introduced a text editor for the โ€œTextโ€ assertion modal form, with support for variables.
  • ๐Ÿค– Added support for new LLaMa 3.1 models from groq.
07/22/2024

๐Ÿ’ฐ Usage Limits, Test Improvements, and GPT-4o Mini Support

  • ๐Ÿค– Added support for GPT-4o Mini, OpenAIโ€™s cost-efficient model offering advanced text and multimodal performance
  • ๐Ÿ’ฐ Implemented a banner to notify free users when they exceed usage limits.
  • ๐Ÿž Fixed an issue with the test ID for the assertion popup in test results.
  • ๐ŸŽš๏ธ Improved the layout styles for project logs.
07/16/2024

๐ŸŒ Expanded Message Types and Provider Visibility

  • ๐Ÿ“จ Added support for other message types, tools, and images in the โ€œmessagesโ€ column, allowing you to simulate user and assistant messages, as well as mock tools and upload images for Vision testing.
  • ๐Ÿ”“ Unlocked providers are now displayed at the top for better visibility.
07/15/2024

๐ŸŽจ Layout Redesign and Test Table Improvements

๐Ÿ” Enhanced Project-Level Visibility

Weโ€™ve redesigned the layout to provide better visibility and access to key project-level components:

  • Playground
  • Tests
  • Deployments
  • Assistants

๐Ÿž Test Table Fixes and Enhancements

  • ๐ŸŽฅ Fixed an issue with the test table width when the drawer is open.
  • ๐Ÿ”˜ Added the ability to close the cell edit drawer by pressing the ESC key.
  • ๐Ÿ› Resolved issues with HTML pasting in the data table.
  • ๐Ÿ“‹ Improved the display of relevant information in the test history.

๐Ÿ”’ Security Enhancements

  • ๐Ÿ”’ Fixed issues related to system_fingerprint and model value for Anthropic models.
  • ๐Ÿ”ผ Updated to the latest SDK, resolving an OpenAI issue with images.
06/20/2024

๐Ÿค– Introducing Anthropicโ€™s Claude 3.5 Sonnet Model

  • ๐Ÿ†• Added support for Anthropicโ€™s Claude 3.5 Sonnet model, offering faster and cheaper performance compared to Claude 3 Opus, with enhanced reasoning, knowledge, and coding abilities.
06/19/2024

๐Ÿž Test Table UX Enhancements and Bug Fixes

Weโ€™ve made several improvements to the test table user experience and addressed some pesky bugs:

  • ๐Ÿ–ผ๏ธ Text table UX improvements
  • ๐ŸŽฏ Streamlined the handling of messages in the test table for a smoother workflow.
  • ๐Ÿ” Enhanced the behavior of the edit drawer, ensuring a more intuitive experience.
  • โŒจ๏ธ Improved keyboard navigation and selection within the test table.
  • ๐Ÿ› Fixed issues related to arrow key navigation and drawer behavior.
06/12/2024

๐ŸŽฏ Testing Enhancements: Keyboard-Friendly Table, Helper Variables, and Improved LLM Assertions

โŒจ๏ธ Keyboard-Friendly Testing Table โŒจ๏ธ

Weโ€™ve made our testing table more keyboard-friendly, allowing you to bulk delete rows and copy multiple values at once.

๐Ÿงฎ Helper Variables for Assertions ๐Ÿงฎ

You can now add additional columns that act as helper variables for assertions (JavaScript, LLM assertions). Place the correct answer in these helper variables and use them in assertions for more efficient and accurate testing.

๐Ÿ“š Improved LLM Assertions ๐Ÿ“š

Based on user feedback, weโ€™ve improved LLM assertions. Now, the entire conversation history is included in the context, providing a more comprehensive view for better testing.

๐Ÿ“จ Multiple Messages in the โ€œMessagesโ€ Column ๐Ÿ“จ

You can now use multiple messages in the โ€œmessagesโ€ column. Currently, itโ€™s possible to simulate user and assistant messages. Weโ€™re working on the ability to mock Tools and upload images for Vision testing.

Tests are a big focus for us, and weโ€™re committed to continuously improving them. Stay tuned for more updates!

04/19/2024

โšก Major Upgrade to Langtailโ€™s Testing Table Component and Upcoming Features

โšก Langtailโ€™s Testing Table Component Upgrade โšก

Weโ€™re excited to announce significant updates to Langtailโ€™s table component aimed at improving your test-writing experience:

  • ๐Ÿš€ Lightning-fast row addition and cell content deletion for efficient test setup
  • โžก๏ธ Tab navigation between cells for seamless navigation
  • ๐Ÿ—‘๏ธ Bulk row deletion for quick test cleanup
  • ๐ŸŽฏ Selective test case execution for focused testing
  • ๐ŸŽ Test result display with LLM and assertion outcomes for comprehensive insights

๐Ÿ”œ Upcoming Feature: LLM as a Judge Assertion ๐Ÿ”œ

Stay tuned! Weโ€™re in the process of developing an โ€œLLM as a judge assertionโ€ feature, set to take our testing capabilities to the next level. More updates coming your way soon!

04/12/2024

New Dashboard View and Launch of Langtail SDK ๐Ÿš€

๐Ÿ“Š New Dashboard View ๐Ÿ“Š

Weโ€™re thrilled to introduce our new dashboard view! Now serving as the main hub for each project, the dashboard provides a snapshot of your projectโ€™s activity and performance at a glance. With recent logs and quick statistics, you can stay updated the moment you log in.

๐ŸŽฏ Langtail SDK Release ๐ŸŽฏ

The first version of the Langtail SDK is now live! ๐Ÿฅณ The SDK can function as an OpenAI proxy and is also compatible with prompts directly deployed within Langtail. Dive into the details over at our GitHub docs.

Currently, weโ€™ve rolled out the JS SDK. If youโ€™re interested in a Python SDK, weโ€™d love to hear from you.

04/05/2024

New Homepage Video, About Us Page, and Embeddable Prompts

๐ŸŽž๏ธ New Homepage Video ๐ŸŽž๏ธ

Weโ€™ve released a new video thatโ€™s now featured on our homepage. Get a quick overview of what Langtail offers by watching our latest video.

๐Ÿง‘โ€๐Ÿ’ป About Us Page ๐Ÿง‘โ€๐Ÿ’ป

Curious about the team behind Langtail? Visit our newly updated About Us page to learn more about our mission and the people who make Langtail possible. Learn more

๐Ÿ›ฃ๏ธ Roadmap, Changelog, and Feedback ๐Ÿ›ฃ๏ธ

Your feedback is crucial in helping us improve. Visit our feedback portal to see our roadmap, changelog, and to share your thoughts. Give feedback

๐Ÿ–ผ๏ธ Embeddable Prompts ๐Ÿ–ผ๏ธ

Weโ€™re happy to announce that you can now embed publicly shared prompts into iframes! Hereโ€™s a quick example:

<iframe src="https://app.langtail.com/playground?shareid=cbGLHKSIff" width="650" height="400" allow="clipboard-write"> </iframe>
03/29/2024

๐Ÿ“š Docs Expansion, ๐Ÿ–ผ๏ธ Dynamic OG Images, and ๐ŸŒ Project-Level Env Variables

๐Ÿ“š Expanded Documentation for Seamless Integration ๐Ÿ“š

Weโ€™ve significantly expanded our documentation to help you hit the ground running:

  • ๐Ÿš€ Deploying Prompts: Learn how to deploy your prompts effortlessly. Read more
  • ๐ŸŒ REST API Usage: Discover how to leverage our powerful REST API. Learn how

๐Ÿ–ผ๏ธ Dynamic OG Images for Shared Prompts ๐Ÿ–ผ๏ธ

Sharing is caring, and weโ€™ve made it even better! When you share a prompt publicly, weโ€™ll automatically generate an OG image for you.

๐ŸŒ Project-Level Environment Variables ๐ŸŒ

Tired of hardcoding API endpoints and keys directly in code? Weโ€™ve got you covered! Introducing project-level environment variables:

  • ๐Ÿ”’ Secure: Keep your sensitive information safe and separate from the code
  • ๐ŸŽ›๏ธ Centralized: Set your variables once at the project level
  • ๐ŸŒ Accessible: Use your env variables in the JavaScript editor for Test Assertions and soon in the Playground too

03/22/2024

Langtail.com updates, Proxy Integration, and Quality of Life Improvements ๐Ÿš€

โœจ Landing page updates โœจ

Our brand new website is live, showcasing the four key features that make Langtail the ultimate tool for prompt engineering:

  1. ๐Ÿ› Debug prompts effortlessly in the playground
  2. โœ… Run tests to ensure your prompts are top-notch
  3. ๐Ÿš€ Deploy prompts in a flash
  4. ๐Ÿ“Š Monitor production with comprehensive logs and metrics

๐Ÿ’ธ Pricing Preview ๐Ÿ’ธ

Weโ€™ve got a pricing plan for everyone! Choose from three tiers:

  • ๐Ÿ†“ Free Tier: Perfect for getting started
  • ๐Ÿ’ฐ Mid Tier: Unleash more power at just $99 per month
  • ๐Ÿข Enterprise Tier: Tailored solutions for your business needs

๐Ÿ“š Docs Page Expansion ๐Ÿ“š

Weโ€™ve been busy expanding our documentation to help you get the most out of Langtail. Head over to our docs page to explore the latest information and guides.

๐ŸŒ‰ Langtail Proxy: Seamless Integration ๐ŸŒ‰

Already building your application using the OpenAI SDK? No problem! With Langtail Proxy, you can experiment with Langtail without migrating your prompts. Hereโ€™s how:

  1. Create your Langtail account
  2. Generate your project API key
  3. Modify your code by updating the base URL to "https://proxy.langtail.com/v1 and passing the Langtail API key
  4. Test it out and witness the magic!

๐ŸŽจ Quality of Life Improvements ๐ŸŽจ

Weโ€™ve also released some handy enhancements to make your life easier:

  • ๐Ÿ” Log Filtering: Easily filter logs by categories like proxy
  • ๐ŸŽฏ Single Test Run: Run individual tests instead of the entire suite
  • โŒ Test Cancellation: Cancel test runs whenever you need
  • ๐Ÿ“… Current Date in System Prompt: Add the current date using handlebars
03/15/2024

๐Ÿ“† $Date Helper, ๐Ÿ” Enhanced Log Filters, and ๐Ÿ  Webpage Updates

๐Ÿ“† $Date Helper for Chatbots ๐Ÿ“†

Chatbots can now stay up-to-date with the current date! Introducing the $date helper, a new feature designed to keep your chatbots in sync with real-time.

๐Ÿ” Log Filtering ๐Ÿ”

Say hello to granular control over your logs. You can now filter logs by any column, even custom-send metadata. Find what you need, when you need it.

๐Ÿ’ฐ Pricing Page is Live ๐Ÿ’ฐ

Ever wondered about our pricing? Weโ€™ve just launched our pricing page, making it easier for you to find the perfect plan for your needs. Check it out!

03/12/2024

๐Ÿš€ Introducing Public Sharing of Prompts and Read-Only Playground!

๐ŸŽก Public Sharing of Prompts ๐ŸŽก

Good news, everyone! Weโ€™ve just launched a new feature that lets you publicly share your prompts. Previously, users needed an account to view a shared prompt, but now, anyone can view it thanks to our new read-only Playground view. ๐ŸŽ‰

๐Ÿž๏ธ Read-Only Playground ๐Ÿž๏ธ

In the read-only Playground, you can see all messages, variables, and Tools (functions). Itโ€™s an open window to the world of your prompts. Currently, only a fixed version of the prompt can be shared, but weโ€™re already working on updates that will let you share and always view the most recent version of a prompt.

03/07/2024

๐Ÿš€ Major DX Improvements for JavaScript Assertions in Tests and Upcoming Playground Enhancements ๐Ÿ› ๏ธ

๐Ÿงช Enhanced JavaScript Assertions in Tests ๐Ÿงช

Weโ€™ve made some significant improvements to our developer experience for JavaScript assertions in Tests:

  • ๐Ÿ“ Run functions with example input: Simply fill in your example input in the left column and run the function.
  • โœ… Auto Input Addition: If any input already exists, weโ€™ll automatically add it for you.
  • ๐Ÿž Debugging Support: Use console.log to debug your tests effectively.
  • ๐ŸŒ API Calls: For advanced use cases, you can now call external APIs using the Fetch API.
  • โšก๏ธ Ultra-fast API requests: Thanks to our robust infrastructure, your API requests will execute swiftly.
02/27/2024

๐Ÿš€ New Templating Engine Based on Handlebars for Enhanced Prompt Handling

๐ŸŽจ Templating Engine Support ๐ŸŽจ

Weโ€™re excited to announce that weโ€™ve released support for a templating engine, based on Handlebars! With this new feature, you can now tackle more complex use cases, including:

  • Conditional parts of prompts
  • Variations of prompts

Simply deploy a prompt with this template, send the correct variable, and watch as the final version of the prompt resolves. You can then view this in the Logs. This added flexibility opens up a world of possibilities for your prompt handling.

02/20/2024

๐Ÿš€ Project Settings, Workspace Refinement, Redesigned Logs, and OpenAI Tools Support!

๐Ÿ”ง New Project Settings ๐Ÿ”ง

Managing your projects just got easier! Weโ€™ve added a new item in the project-level sidebar that lets you perform common actions like renaming or deleting a project.

๐Ÿ› ๏ธ Enhanced Workspace Settings ๐Ÿ› ๏ธ

Your workspace is now even more flexible! Weโ€™ve refined the settings to allow you to rename your workspace and made the UI more consistent across the different sections for a smoother experience.

๐Ÿ“œ Redesigned Logs ๐Ÿ“œ

Weโ€™ve completely redesigned our Logs for a cleaner, more user-friendly interface. Plus, Logs now also display the JSON representation of whatโ€™s being sent from Langtail to end providers like OpenAI. We think youโ€™ll love this upgrade as much as we do!

๐Ÿ” OpenAI Tools Support ๐Ÿ”

Weโ€™re thrilled to announce that support for the new OpenAI Tools is here! Functions now visually resemble TypeScript functions and are even typesafe. The types are generated based on the JSON schema. Weโ€™re confident youโ€™ll find them incredibly useful.

02/08/2024

๐ŸŒŸ GPT-4 Vision is Live, Plus New Workspace Settings and Refined UX ๐Ÿ”

๐ŸŒŸ GPT-4 Vision Now Live ๐ŸŒŸ

Weโ€™re thrilled to announce that GPT-4 Vision is now live in production! You can now input images along with text, opening up a whole new realm of creative use cases. For instance, take a photo of an invoice and ask for the cost of each item โ€“ Vision has you covered.

๐ŸŽจ Experimenting with Vision in Playground ๐ŸŽจ

Want to give Vision a spin? Head over to our Playground and upload an image or insert an image URL. Please note that Vision takes a few seconds to process, so a bit of patience is required.

๐Ÿš€ Deploy Prompts with Vision ๐Ÿš€

Great news for developers โ€“ deploying prompts with Vision in Langtail is now supported!

๐Ÿ› ๏ธ Workspace Settings and UX Updates ๐Ÿ› ๏ธ

Weโ€™ve also rolled out a couple of key updates for improved user experience:

  • New Workspace Settings: Now, you can manage your provider API keys and team members all in one place.

  • Refined UX for Per API Budget: Based on your feedback, weโ€™ve refined the UX and terminology for the per API budget. You must now enable the budget before setting the total for your API key and specific user allowances.