v0.0.8
版本发布时间: 2023-07-14 22:37:25
TransformerOptimus/SuperAGI最新发布版本:v0.0.14(2024-01-16 22:21:23)
✨SuperAGI v0.0.8✨
Announcing the launch of 🌴 Google PaLM2 Integration 🛠 (APM) Agent Performance Monitoring, ⏱️ Schedule Agent Run & more
Improvements to the Core ⚙
-
🤖 Introduced Agent Performance Monitoring (APM) to SuperAGI. The APM dashboard provides critical telemetry into the working of agent systems including: -- Organization level metrics such # of Agents, # of Tokens, # of Runs etc. -- Users can also get Agents-LLM specific insights such as Runs made by an agent using a particular LLM, LLM’s Token consumption etc. -- Agent level Analytics like tokens consumed by an agent, Total # of runs, avg tokens per run, total calls & run time.
-
🦬 Added Google's PaLM 2 Bison LLM: Users can configure PaLM2 Bison model in account settings and select from the model dropdown at the time of agent provisioning. Due to PaLM2's smaller size, users can use PaLM2 model for specific goals that do not require as much thinking ability. We have also implemented a new model factory class, enhancing SuperAGI's capability to incorporate future advancements in large language models (LLMs).
-
🧠 Added Qdrant DB as LTM: SuperAGI now supports Qdrant DB as a Long-Term Memory (LTM). Qdrant DB provides efficient indexing and searching capabilities for large-scale memory storage, enhancing the performance and scalability of SuperAGI agents' long-term memory.
-
⏱️ Schedule Agent Run: Added the option to schedule a one-time agent run for the future. Users can also set recurring agent runs after specific time intervals and set optional expiry for recurring runs, based on a time deadline or the total number of runs. For more flexibility, users can also stop, edit and save a new schedule.
-
🗂️ Resource Manager Per Run Output Directory: The Resource Manager now supports a revamped UI and backend structure that enables easier “per-run“ directory management. Outputs of each run can now be downloaded as a zip file. This update provides a more organized and efficient way to manage and access the output files generated by agents.
New ToolKits Added
🌐 DuckDuckGo Tool: Agents can use DuckDuckGo Tool to perform searches without the need for an API key, allowing for easy access to a privacy-focused search experience.
What’s Changed
- Added Agent Performance Monitoring by @jedan2506 #707
- Added Agent Scheduling by @anisha1607, @namansleeps and @Vibhusha22 in #733 & #562
- Fixed Resource manager backend structure along with per run directory frontend by @luciferlinx101 and @jedan2506 in #727 & #735
- Added Google’s PaLM 2 Bison support in LLm model by @TransformerOptimus in #695
- Added Qdrant DB as LTM by @CaptainLevi0007 in #742
- Added DuckDuckGo Tool by @Maverick-F35 in #171
- Added support for Fixed Task queue by @TransformerOptimus in #695
- Refactored Google calender code for compatibilty with SuperAGI cloud by @Tarraann in #663
- Improved JSON Parser Schema by @TransformerOptimus in #763
- Fixed the Goal update issue for new runs by @luciferlinx101 in #640
- Added Logos for all the Toolkits by @namansleeps #632
- Improved data persistency on tab switch by @nborthy in #731
- Fixed Max iterations issue by @luciferlinx101 in #754
New Contributors
- @Maverick-F35 made their first contribution by adding DuckDuckGo tool in #170
- @Arkajit-Datta made their first contribution by fixing a runtime bug in #674