About

Agentic ADK is an Agent application development framework launched by Alibaba International AI Business, based on Google-ADK and Ali-LangEngine.

中文版说明

Agentic ADK

Agentic ADK is an Agent application development framework launched by Alibaba International AI Business, based on Google-ADK and Ali-LangEngine (launched by Alibaba, involves over 1,300 community members within the group, utilized by 767 systems). It is used for developing, constructing, evaluating, and deploying powerful, flexible, and controllable complex AI Agents. ADK aims to make Agent development simpler and more user-friendly, enabling developers to more easily build, deploy, and orchestrate various Agent applications ranging from simple tasks to complex collaborations.

Important features

• Based on the Google ADK interface, it strengthens core execution pathways such as streaming interaction and visualization debugging tools, enabling developers to efficiently develop Agent applications.
• Seamlessly integrates with Alibaba's International Multimodal Large Language Model, Ovis, to achieve deep alignment and fusion of visual and textual information. This model is characterized by high performance and lightweight design, offering the following advantages for efficient development and deployment of multimodal Agents:
  • Outstanding Logical Reasoning: By combining instruction fine-tuning and preference learning, the model's Chain-of-Thought (CoT) reasoning abilities are significantly enhanced, enabling it to better understand and execute complex instructions.
  • Precise Cross-Language Understanding and Recognition: Beyond just Chinese and English, the model has improved text recognition (OCR) capabilities in multilingual environments and optimized the accuracy of structured data extraction from complex visual elements such as tables and charts.
• Flexible multi-agent framework, supporting various execution modes such as synchronous, asynchronous, streaming, and parallel, and naturally integrating the A2A protocol.
• Offers hundreds of API tools and introduces the MCP integration gateway.
• DeepResearch/RAG, ComputerUse, BrowserUse, Sandbox, and other best practices for Agentic AI.
• Implementation of context extension for agent conversations, including Session, Memory, Artifact, and more, with built-in short and long-term memory plugins.
• Provides prompt automation tuning and security risk control-related agent examples.

Alibaba langengine

Alibaba langengine is a Java-based AI application development framework. It endows LLM with two core capabilities:

1. Data Awareness: Connecting language models with other data sources.

2. Agency Capability: Allowing language models to interact with engineering and systematic capabilities.

The main application scenarios of alibaba-langengine include personal assistants, document-based Q&A, chatbots, querying tabular data, code analysis, low-code application generation, etc.

Related Code

ali-langengine-core: The most essential AI application framework engine module.

ali-langengine-infrastructure: The infrastructure module of the AI application framework.

ali-langengine-community: Community open-source co-construction module.

alibaba-langengine-demo: Related example module.

maven

https://s01.oss.sonatype.org/#nexus-search;quick~ali-langengine

JDK version requirements

JDK 8+

Related Configuration

alibaba-langengine-openai

openai_server_url=https://api.openai.com/
openai_api_key=******
openai_api_timeout=100
# compatible
OPENAI_API_KEY=******

alibaba-langengine-dashscope

# dashscope api
dashscope_server_url=https://dashscope.aliyuncs.com/
dashscope_api_key=******
dashscope_api_timeout=100
# compatible
DASH_SCOPE_API=******

alibaba-langengine-tool

# bing api
bing_server_url=https://api.bing.microsoft.com/
bing_api_key=******

# google api
google_customsearch_server_url=https://customsearch.googleapis.com/
google_api_key=******
google_cse_id=******

# serpapi api
serpapi_server_url=https://serpapi.com/
serpapi_key=******

# tavily api
tavily_api_key=******

alibaba-langengine-adbpg

# adbpg db
adbpg_datasource_endpoint=******
adbpg_datasource_databasename=******
adbpg_datasource_u=******
adbpg_datasource_p=******

alibaba-langengine-azure

# azure api
azure_openai_server_url=******
azure_deployment_name=******
azure_openai_api_version=******
azure_openai_api_timeout=100

alibaba-langengine-claude

# claude api
anthropic_server_url=https://api.anthropic.com/
anthropic_api_key=******
anthropic_api_timeout=120

alibaba-langengine-gemini

# gemini api
gemini_api_key=******
gemini_api_timeout=120

alibaba-langengine-hologres

# hologres db
hologres_datasource_endpoint=******
hologres_datasource_databasename=knowledge_center
hologres_datasource_u=******
hologres_datasource_p=******

alibaba-langengine-huggingface

# huggingface api
huggingface_api_key=******

alibaba-langengine-milvus

# milvus
milvus_server_url=******

alibaba-langengine-minimax

#minimax api
minimax_api_key=******
minimax_group_id=******
minimax_api_timeout=120

alibaba-langengine-moonshot

# moonshot api
moonshot_server_url=https://api.moonshot.cn
moonshot_api_key=******
moonshot_api_version=v1
moonshot_server_timeout=120

alibaba-langengine-msearch

#msearch api
msearch_api_key=******
msearch_api_timeout=120

alibaba-langengine-opensearch

# opensearch vector
opensearch_datasource_instance_id=ha-cn-*****
opensearch_datasource_endpoint=ha-cn-*****
opensearch_datasource_swift_server_root=http://*****
opensearch_datasource_swift_topic=ha-cn-******

alibaba-langengine-pinecone

# pinecone vector
pinecone_api_key=******
pinecone_environment=us-west4-gcp-free
pinecone_project_name=******

alibaba-langengine-polardb

# polardb postgres
polardb_datasource_endpoint=******
polardb_datasource_databasename=******
polardb_datasource_u=******
polardb_datasource_p=******

alibaba-langengine-redis

# redis
redis_host=r-******.redis.rds.aliyuncs.com
redis_port=6379
redis_p=******
redis_session_expire_second=60

alibaba-langengine-tair

# tair vector
tair_host=r-******.redis.rds.aliyuncs.com
tair_port=6379
tair_p=******

alibaba-langengine-vertexai

# vertexai
vertexai_server_url=https://us-central1-aiplatform.googleapis.com/
vertexai_api_key=******
vertexai_project_id=******
vertexai_api_timeout=120

alibaba-langengine-xingchen

# xingchen
xingchen_api_key=lm-******
xingchen_api_timeout=120

alibaba-langengine-xinghuo

# xinghuo
xinghuo_server_url=https://spark-api.xf-yun.com/v2.1/chat
xinghuo_app_id=******
xinghuo_api_key=******
xinghuo_api_secret=******

License

This project is licensed under Apache License Version 2 (https://www.apache.org/licenses/LICENSE-2.0.txt, SPDX-License-identifier: Apache-2.0).