Skip to content

Releases: alipay/agentUniverse

v0.0.11

11 Jul 12:23
5ba4db5
Compare
Choose a tag to compare

[0.0.11] - 2024-07-11

Added

  • DataAgent Autonomous Data Agent MVP Version Released
    • Minimum Viable Product version, DataAgent aims to empower your agent with the capability of self-assessment and evolution through intelligent agent abilities. For detailed information, please refer to the user documentation.
  • Added intermediate information streaming output capabilities in PEER and ReAct modes

Note

  • Latest PEER research findings released
    • This paper provides a detailed introduction to the mechanisms and principles of the PEER multi-agent framework. Experimental validation proves the advancement of the PEER model. For detailed information, please refer to the user documentation.
  • Added use cases
    • Andrew Ng's Reflexive Workflow Translation Agent Replication
  • Some code optimizations and documentation updates.

More Details

What's Changed

New Contributors

Full Changelog: v0.0.10...v0.0.11

v0.0.10

28 Jun 15:03
a4eb490
Compare
Choose a tag to compare

[0.0.10] - 2024-06-28

Added

  • Added standard integration for the DeepSeek model in the LLM module.
  • Added a new OpenAI general protocol wrapper class, OpenAIStyleLLM.
    • Models using the OpenAI protocol can be configured directly.
  • Added a new LangChain tool wrapper class, LangChainTool, with several example tools for search and execution.
    • LangChain tools can be configured directly.
  • Added Agent information collection capability in the monitor module.

Note

  • Added use cases.
    • Supplemented documentation with a financial event analysis case study using PEER collaborative mode.
  • Added several new documents for LLM components, tool components, and the Monitor module.
  • Updated the new README.
  • Some code optimizations and documentation updates.

More Details

What's Changed

Full Changelog: v0.0.9...v0.0.10

v0.0.9

14 Jun 10:36
Compare
Choose a tag to compare

[0.0.9] - 2024-06-14

Added

  • Added standard integration for Claude and Ollama LLM components
  • Added new Qwen embedding module
  • Added default agents for ReAct-Type and NL2API-Type

Note

  • Added new use cases

    • RAG-Type Agent Examples: Legal Consultation Agent
    • ReAct-Type Agent Examples: Python Code Generation and Execution Agent
    • Multi-Agent: Discussion Group Based on Multi-Turn Multi-Agent Mode

    For more details, please refer to the use case section in the user documentation.

  • Some code optimizations and documentation updates.


More Details

What's Changed

New Contributors

Full Changelog: v0.0.8...v0.0.9

v0.0.8

06 Jun 15:07
343c179
Compare
Choose a tag to compare

[0.0.8] - 2024-06-06

Added

  • Introduced a new monitor module
    • Data running in any agentUniverse can be collected and observed
  • Added webserver post_fork functionality
    • Provides multi-node process intervention capabilities after starting the webserver in agentUniverse
  • Introduced SQLDB_WRAPPER wrapper class, offering typical database connection methods
    • Through the SQLDB_WRAPPER wrapper class, you can conveniently connect to various databases and storage technologies including SQLServer, MySQL, Oracle, PostgreSQL, SQLite and others
  • Added connection support for Milvus vector database component

For more usage of the above features, please pay attention to the agentUniverse guidebook.

Changed

  • Flask is set as the default webserver startup method across all platforms, with gunicorn and gRPC capabilities disabled by default
    • In the previous version, we found slight compatibility differences with gunicorn and gRPC across different operating systems. Thus, we have made Flask the primary startup method for all platforms. You can enable gunicorn and gRPC in the configuration as needed.

Security

  • Some aU dependencies were identified to have security vulnerabilities in third-party packages. For security reasons, we have upgraded their versions, with the main changes including:
    • requests (^2.31.0 -> ^2.32.0)
    • flask (^2.2 -> ^2.3.2)
    • werkzeug (^2.2.2 -> ^3.0.3)
    • langchain (0.0.352 -> 0.1.20)
    • langchain-core (0.1.3 -> 0.1.52)
    • langchain-community (no version lock -> 0.0.38)
    • gunicorn (21.2.0 -> ^22.0.0)
    • Jinja2 (no version lock -> ^3.1.4)
    • tqdm (no version lock -> ^4.66.3)
      If your system has external access, we strongly recommend installing version v0.0.8 of agentUniverse to mitigate the security risks posed by these third-party packages. For more detailed information, you can visit https://security.snyk.io.

Note

  • Some code optimizations and documentation updates.

More Details

What's Changed

  • merge dev by @AniviaTn in #54
  • docs: update images and fix typo. by @moonfin in #60
  • Add: SQLDBWrapper class, used for manage different kinds of sql database in agentUniverse by @AniviaTn in #47
  • improvement: upgrade the langchain version to 0.1 and tweak planner/memory modules in agentUniverse. by @EdwinInAu in #62
  • feat: add trace_llm annotation to trace the llm invocation record. by @EdwinInAu in #63
  • merge dev by @AniviaTn in #64
  • Update: some dependencies which have safety bugs. by @AniviaTn in #65
  • fix: add get num tokens in openai_style_langchain_instance. by @EdwinInAu in #66
  • feat: Release version 0.0.8 by @LandJerry in #67

Full Changelog: v0.0.7...v0.0.8

v0.0.7

29 May 14:09
b38880b
Compare
Choose a tag to compare

[0.0.7] - 2024-05-29

Added

  • LLM component supports multimodal parameter invocation.
  • Added LLM integration methods for Qwen, WenXin, Kimi, Baichuan, etc.

Note

  • Added a multimodal example agent, see the invocation details in sample_standard_app.app.test.test_multimodal_agent.MultimodalAgentTest.
  • Some code optimizations and documentation updates.

More Details

What's Changed

  • feat: add chat prompt template and image url to the rag planner (multimodal) in agentUniverse. by @EdwinInAu in #35
  • refactor: the name of parameters in the parse_input method and execute method of the agent. by @EdwinInAu in #36
  • feat: multimodal agent & refactor:execute method of the agent by @LandJerry in #37
  • docs: add agent component documents by @LandJerry in #38
  • merge master by @AniviaTn in #39
  • style: change the aU code comments. by @EdwinInAu in #40
  • docs: add llm docs in guidebook by @LandJerry in #42
  • merge sync by @LandJerry in #43
  • Change: system db uri name in config file Add: docs about system db uri by @AniviaTn in #41
  • docs: add tool docs in guidebook by @LandJerry in #51
  • improvement: change the prompt path in the base package of the agentUniverse. by @EdwinInAu in #50
  • add model support by @weizjajj in #45
  • Dev remove claude by @weizjajj in #52
  • feat: Release version 0.0.7 by @LandJerry in #53

Full Changelog: v0.0.6...v0.0.7

v0.0.6

15 May 05:42
15000fb
Compare
Choose a tag to compare

[0.0.6] - 2024-05-15

Added

  • Support for the GPT-4o model, with updates to related examples.
  • Support for the RPC component gRPC, providing a standard method for service startup.

Note

  • Provide standard Docker images and K8S deployment solutions.
  • Some code optimizations and documentation updates.

More Details

What's Changed

New Contributors

Full Changelog: v0.0.5...v0.0.6

v0.0.5

08 May 16:06
bf1d0e3
Compare
Choose a tag to compare

[0.0.5] - 2024-05-08

Added

  • The LLM component supports streaming calls.
  • The Knowledge component has an added update definition.

Fixed

  • Fixed potential concurrency safety issues in the peer planner.
  • Fixed the issue in version 0.0.4 of the PyPI package where the packaging method forced users to enter an AK upon startup.

Note

  • Some code optimizations and documentation updates.

More Details

What's Changed

  • Fix: peer planner log format & prompt split texts issues by @EdwinInAu in #4
  • docs: add contact docs by @LandJerry in #6
  • Fix: the planner concurrency model assignment issue by @EdwinInAu in #5
  • Feat: Add default peer agent to the agentUniverse. by @EdwinInAu in #7
  • Improvement: modify the au sample standard app package, add more demo agents/tool sets/test examples. by @EdwinInAu in #8
  • Improvement: modify the the initialization method of the openai llm and embedding model. by @EdwinInAu in #9
  • Dev heji by @goodgood-good in #10
  • Dev by @LandJerry in #12
  • docs: add Application Engineering Structure Explanation by @LandJerry in #13
  • Refactor: the original prompt util methods & the handle_prompt method of the planner, etc by @EdwinInAu in #14
  • Improvement: add the today date to the agent prompt and example agents in sample standard app package, etc. by @EdwinInAu in #18
  • docs: update guidebook index by @LandJerry in #19
  • Add streaming support by @weizjajj in #16
  • feat: release version 0.0.5 by @LandJerry in #20

Full Changelog: v0.0.4...v0.0.5

v0.0.4

26 Apr 15:38
Compare
Choose a tag to compare

Version Update History

[0.0.4] - 2024-04-26

Added

  • Add version management capability to the prompt.

Fixed

  • Fixed compatibility issues on Windows
    • Due to compatibility issues of Gunicorn with Windows systems, automatically identify the kernel version to select the web startup method.
    • Specified YAML reading as UTF-8 encoding method.

Full Changelog: v0.0.3...v0.0.4

v0.0.3

24 Apr 10:10
Compare
Choose a tag to compare

[0.0.3] - 2024-04-24

  • Init
    The official release version of AgentUniverse has been initialized. Enjoy using it!