2023-10-26
Enhancements
VertexAI Integration for Prompt Playground
Users can now iterate on prompts in the Prompt Playground with Google’s models built on PaLM 2. This integration allows users to iterate on prompt templates, parameters, and variables in the platform and compare responses. Additionally, users can now compare LLM providers by comparing prompt runs between OpenAI and VertexAI.Learn more ->
Monitor Downtime
Users can now schedule monitor downtime - a recurring time period in which monitors should not be evaluated. Monitor downtime aims to reduce noise in monitors due to periods of unstable or low traffic.Learn more ->
Monitors Widget in Dashboards
“Alert Graph” is a new type of dashboard widget, enabling users to view historical alerting data alongside other key metrics in their dashboard. Simply select “Alert Graph” from the widgets menu.
Text Widgets In Dashboards
Text Widgets are now included in dashboards. Users can create text widgets to share notes and observations.
spaceId + modelName to create a monitor in lieu of using modelID, allowing users to streamline monitor creation. To use, simply replace the modelId field with spaceId (from url) and the modelName (the same field used for create a file import job).Python SDK v7.6.1
- Added validation on embedding raw data for batch and record-at-a-time loggers.
- Raised the validation string limits for string fields allowing users to send much larger strings.
- Added truncation warnings if strings reach size limit.
🎓 New Educational Content
- PII Anonymization with Microsoft Presidio: How To
- The Definitive Guide to LLM Evaluation
- LLM Leaderboard
📚 New Paper Readings
Catch up on the latest in AI research papers with these new community readings:- RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models
- Decomposing Language Models Into Understandable Components