mirror of https://github.com/microsoft/autogen.git synced 2026-02-15 18:15:08 -05:00

Files

Linxin Song e673500129 [AutoBuild] Supporting build agents from library; supporting generating agent descriptions (#1039 )

* try to fix blog

* modify blog

* fix test error in #717; fix blog typo in installation; update blogs with output examples.

* pre-commit

* pre-commit

* Update website/blog/2023-11-26-Agent-AutoBuild/index.mdx

Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>

* add future work

* fix grammar

* update agent_builder

* solve #941; add detailed debug info; support json string config

* pre-commit

* solve #954

* pre-commit

* [new feature] build group chat agents from library.

* pre-commit

* add authors' info in notebook; add a new notebook for build_from_library; reduce prompt effort

* update test and example for build_from_library

* pre-commit

* add notebook; update docs

* change notebook name

* change description for notebook and doc

* remove default value for default_llm_config

* add embedding similarity agent selection

* pre-commit

* update test

* add dependency installation in github workflow

* update test

* pre-commit

* update notebook

* support directly json as library; support customize embedding model

* update test

* pre-commit

* update github test workflow

* Update autobuild_agent_library.ipynb

* add agent description

* refine prompt; update notebook

* pre-commit

* update test example

* update test

* update test

* update test

* change `config_path` to `config_path_or_env`; update test

* pre-commit

* update test

* update test

* update test: add config_file_location

* change `config_path_or_env` to `config_file_or_env`

* update test

* solve noqa

* fix import error for conftest

* fix test error

* pre-commit

* * update error message in `_create_agent`.
* replace `gpt-4-1106-preview` to `gpt-4` in test file.

* add comment on local server creation; modify notebook; update contrib-openai.yml for test; add autobuild option in setup.py; add autotest model name statement

* move import huggingface_hub to _create_agent

* pre-commit

* add uncover comment in the endpoint creation code block

* recover contrib-openai.yml for merge

---------

Co-authored-by: Jieyu Zhang <jieyuz2@cs.washington.edu>
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>

2024-01-06 17:23:23 +00:00

8.5 KiB

Raw Blame History

Examples

Automated Multi Agent Chat

AutoGen offers conversable agents powered by LLM, tool or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation via multi-agent conversation. Please find documentation about this feature here.

Links to notebook examples:

Code Generation, Execution, and Debugging
- Automated Task Solving with Code Generation, Execution & Debugging - View Notebook
- Automated Code Generation and Question Answering with Retrieval Augmented Agents - View Notebook
- Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents - View Notebook
Multi-Agent Collaboration (>3 Agents)
- Automated Task Solving by Group Chat (with 3 group member agents and 1 manager agent) - View Notebook
- Automated Data Visualization by Group Chat (with 3 group member agents and 1 manager agent) - View Notebook
- Automated Complex Task Solving by Group Chat (with 6 group member agents and 1 manager agent) - View Notebook
- Automated Task Solving with Coding & Planning Agents - View Notebook
- Automated Task Solving with agents divided into 2 groups - View Notebook
- Automated Task Solving with transition paths specified in a graph - View Notebook
Applications
- Automated Chess Game Playing & Chitchatting by GPT-4 Agents - View Notebook
- Automated Continual Learning from New Data - View Notebook
- OptiGuide - Coding, Tool Using, Safeguarding & Question Answering for Supply Chain Optimization
Tool Use
- Web Search: Solve Tasks Requiring Web Info - View Notebook
- Use Provided Tools as Functions - View Notebook
- Use Tools via Sync and Async Function Calling - View Notebook
- Task Solving with Langchain Provided Tools as Functions - View Notebook
- RAG: Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent) - View Notebook
- Function Inception: Enable AutoGen agents to update/remove functions during conversations. - View Notebook
- Agent Chat with Whisper - View Notebook
- Constrained Responses via Guidance - View Notebook
Human Involvement
- Simple example in ChatGPT style View example
- Auto Code Generation, Execution, Debugging and Human Feedback - View Notebook
- Automated Task Solving with GPT-4 + Multiple Human Users - View Notebook
- Agent Chat with Async Human Inputs - View Notebook
Agent Teaching and Learning
- Teach Agents New Skills & Reuse via Automated Chat - View Notebook
- Teach Agents New Facts, User Preferences and Skills Beyond Coding - View Notebook
- Agent Optimizer: Train Agents in an Agentic Way - View Notebook
Multi-Agent Chat with OpenAI Assistants in the loop
- Hello-World Chat with OpenAi Assistant in AutoGen - View Notebook
- Chat with OpenAI Assistant using Function Call - View Notebook
- Chat with OpenAI Assistant with Code Interpreter - View Notebook
- Chat with OpenAI Assistant with Retrieval Augmentation - View Notebook
- OpenAI Assistant in a Group Chat - View Notebook
Multimodal Agent
- Multimodal Agent Chat with DALLE and GPT-4V - View Notebook
- Multimodal Agent Chat with Llava - View Notebook
- Multimodal Agent Chat with GPT-4V - View Notebook
Long Context Handling
- Conversations with Chat History Compression Enabled - View Notebook
Evaluation and Assessment
- AgentEval: A Multi-Agent System for Assess Utility of LLM-powered Applications - View Notebook
Automatic Agent Building
- Automatically Build Multi-agent System with AgentBuilder - View Notebook
- Automatically Build Multi-agent System from Agent Library - View Notebook

Enhanced Inferences

Utilities

API Unification - View Documentation with Code Example
Utility Functions to Help Managing API configurations effectively - View Notebook
Cost Calculation - View Notebook

Inference Hyperparameters Tuning

AutoGen offers a cost-effective hyperparameter optimization technique EcoOptiGen for tuning Large Language Models. The research study finds that tuning hyperparameters can significantly improve the utility of them. Please find documentation about this feature here.