amadad / agentcy Goto Github PK

View Code? Open in Web Editor NEW

301.0 15.0 50.0 627 KB

Multi-Agent Creative Collaboration with AutoGen

Home Page: https://scty.org

Python 100.00%

agentcy's Introduction

Agentcy

Multi-Agent Creative Collaboration

Overview • Agents • Tools • Setup • Conclusion Roadmap • License

A small team autonomous of agents help you unlock, uncover or explore the potential of your business. Agentcy takes two simple inputs to generate a plan, research and deliverables to help you gain a competitive advantage.

📖 Overview

Modeled on advertising and creative agencies, you'll move from problem space to solution space with successive steps of research, writing, ideation and strategic planning. Agentcy uses the AutoGen framework to orchestrate multiple agents to ensure that tasks are handled by the most qualified agent, leading to more efficient and accurate outcomes.

🕵🏽 Agents

The agents involved in the collaboration include:

Agency Manager: Creates a plan and approach to tackle the problem or opportunity.
Agency Researcher: Conducts research on user pain points, market opportunities, and prevailing market conditions.
Writing Assistant: Utilizes research and content writing functions to generate content.
Agency Strategist: Drafts strategic briefs for effective brand positioning in the market.
Agency Copywriter: Crafts compelling narratives and messages that align with the brand's strategy.
Agency Media Planner: Identifies the best mix of media channels for advertising.
Agency Marketer: Transforms strategy and insights into marketable ideas.
Agency Director: Guides the creative vision of the project.
User Proxy: Acts as an intermediary between the human user and the agents.

🛠️ Tools Used

Serper for realtime web search
Browserless for web scrape
Langchain for content summarization

⚙️ Setup & Configuration

Ensure required libraries are installed:

pip install pyautogen

Set up the OpenAI configuration list by either providing an environment variable OAI_CONFIG_LIST or specifying a file path.

[
    {
        "model": "gpt-3.5-turbo", #or whatever model you prefer
        "api_key": "INSERT_HERE"
    }
]

Setup api keys in .env:

OPENAI_API_KEY="XXX"
SERPAPI_API_KEY="XXX"
SERPER_API_KEY="XXX"
BROWSERLESS_API_KEY="XXX"

Launch in CLI:

python3 main.py

⏯️ Conclusion

In the realm of creative agencies, the multi-agent collaboration approach revolutionizes the way projects are handled. By tapping into the distinct expertise of various agency roles, from strategists to media planners, we can guarantee that each facet of a project is managed by those best suited for the task. This methodology not only ensures precision and efficiency but also showcases its versatility, as it can be tailored to suit diverse project requirements, whether it's brand positioning, content creation, or any other creative endeavor.

Credit to Jason Zhou's RAG example.

📈 Roadmap

Refine workflow and data pass through to agents
Reduce unnecessary back and forth
Modularize code
Implement alternative and local LLM models
Save files to local folder
Implement other agents, see commented out agents
Create and train fine-tuned agents for each domain specific task
Add more tools for agents to utilize
Create UI for project

📝 License

MIT License. See LICENSE for more information.

agentcy's People

Contributors

Stargazers

Watchers

Forkers

richardwhiteii bloodfi5h originalgrubbsy francyjglisboa jan-karsten-kuhnke bukhanka adriangalilea zipajopa naixingwang lgs rahulchopra-dev npokemon soxunlocks taner45 bellyfat franciscoabenza mexicanamerican ddwinhzy m0bstarx ashish-op ngisvold jscorrea21 ashleyjkell gordienco eltociear dmaturana81 georgestrakhov octag0no dolife foolafroos yestechgroup daoxuejb ianmenethil havsqa heliosprimeone stevew00ds ilyamk dibop ajaysi mdwoicke kaydo-g mivanovitch chunchi031 regireis7 codingcuriosities fordlean j182razor mrdavtan mukseq marienaq

agentcy's Issues

best implementation of web search?

What are the recommended strategies for connecting to the web our agents?

Error: Invalid parameter: only messages with role 'assistant' can have a function call.

When the writing assistant tries to call the research function, there is an error:
"openai.error.InvalidRequestError: Invalid parameter: only messages with role 'assistant' can have a function call."

This happens with both gpt-4 and 3.5-turbo.

I codified the most important parts like this box

Agency_Copywriter (to chat_manager):

Great work, Agency Strategist! The strategic brief provides a clear roadmap for the development of the Experimental Bass Music Database. It effectively outlines the brand's positioning, target audience, and unique value proposition. The key messages and emotional appeal are well-defined, and the strategic initiatives align with the goal of building a comprehensive and trusted resource.

Next, let's collaborate with the Agency Designer to ensure that the visual elements and user experience complement the brand's voice and strategic direction. By aligning the text and visuals, we can create a cohesive brand story that resonates with the target audience. Let's continue working together to bring the Experimental Bass Music Database to life!

[autogen.oai.completion: 11-01 17:10:44] {223} INFO - retrying in 10 seconds...
Traceback (most recent call last):
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\oai\completion.py", line 209, in _get_response
response = openai_completion.create(request_timeout=request_timeout, **config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 155, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 299, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 710, in _interpret_response
self._interpret_response_line(
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 775, in _interpret_response_line
raise self.handle_error_response(
openai.error.APIError: The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 3a48ccdd1f5a96586718e2f31f005694 in your email.) {
"error": {
"message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 3a48ccdd1f5a96586718e2f31f005694 in your email.)",
"type": "server_error",
"param": null,
"code": null
}
}
500 {'error': {'message': 'The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 3a48ccdd1f5a96586718e2f31f005694 in your email.)', 'type': 'server_error', 'param': None, 'code': None}} {'Date': 'Thu, 02 Nov 2023 00:10:14 GMT', 'Content-Type': 'application/json', 'Content-Length': '366', 'Connection': 'keep-alive', 'access-control-allow-origin': '', 'openai-model': 'gpt-3.5-turbo-0613', 'openai-organization': 'zenchant', 'openai-processing-ms': '852', 'openai-version': '2020-10-01', 'strict-transport-security': 'max-age=15724800; includeSubDomains', 'x-ratelimit-limit-requests': '5000', 'x-ratelimit-limit-tokens': '90000', 'x-ratelimit-remaining-requests': '4999', 'x-ratelimit-remaining-tokens': '84399', 'x-ratelimit-reset-requests': '12ms', 'x-ratelimit-reset-tokens': '3.733s', 'x-request-id': '3a48ccdd1f5a96586718e2f31f005694', 'CF-Cache-Status': 'DYNAMIC', 'Server': 'cloudflare', 'CF-RAY': '81f82738a9ab6a04-SMF', 'alt-svc': 'h3=":443"; ma=86400'}
[autogen.oai.completion: 11-01 17:11:03] {223} INFO - retrying in 10 seconds...
Traceback (most recent call last):
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\oai\completion.py", line 209, in _get_response
response = openai_completion.create(request_timeout=request_timeout, **config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 155, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 299, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 710, in _interpret_response
self._interpret_response_line(
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 775, in _interpret_response_line
raise self.handle_error_response(
openai.error.APIError: The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 09955dfb9dc7289f412373a1dc8d3255 in your email.) {
"error": {
"message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 09955dfb9dc7289f412373a1dc8d3255 in your email.)",
"type": "server_error",
"param": null,
"code": null
}
}
500 {'error': {'message': 'The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 09955dfb9dc7289f412373a1dc8d3255 in your email.)', 'type': 'server_error', 'param': None, 'code': None}} {'Date': 'Thu, 02 Nov 2023 00:10:33 GMT', 'Content-Type': 'application/json', 'Content-Length': '366', 'Connection': 'keep-alive', 'access-control-allow-origin': '', 'openai-model': 'gpt-3.5-turbo-0613', 'openai-organization': 'zenchant', 'openai-processing-ms': '8412', 'openai-version': '2020-10-01', 'strict-transport-security': 'max-age=15724800; includeSubDomains', 'x-ratelimit-limit-requests': '5000', 'x-ratelimit-limit-tokens': '90000', 'x-ratelimit-remaining-requests': '4999', 'x-ratelimit-remaining-tokens': '87783', 'x-ratelimit-reset-requests': '12ms', 'x-ratelimit-reset-tokens': '1.477s', 'x-request-id': '09955dfb9dc7289f412373a1dc8d3255', 'CF-Cache-Status': 'DYNAMIC', 'Server': 'cloudflare', 'CF-RAY': '81f8277ebdb26a04-SMF', 'alt-svc': 'h3=":443"; ma=86400'}
writing_assistant (to chat_manager):

******* Suggested function Call: research *****
Arguments:
{
  "query": "Experimental Bass Music"
}
***********************************************

Traceback (most recent call last):
File "C:\Users\Zenchant\Documents\agentcy\main.py", line 448, in
user_proxy.initiate_chat(
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 521, in initiate_chat
self.send(self.generate_init_message(**context), recipient, silent=silent)
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 324, in send
recipient.receive(message, self, request_reply, silent)
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 452, in receive
reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 764, in generate_reply
final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\groupchat.py", line 116, in run_chat
speaker = groupchat.select_speaker(speaker, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\groupchat.py", line 45, in select_speaker
final, name = selector.generate_oai_reply(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 596, in generate_oai_reply
response = oai.ChatCompletion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\oai\completion.py", line 773, in create
response = cls.create(
^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\oai\completion.py", line 804, in create
return cls._get_response(params, raise_on_ratelimit_or_timeout=raise_on_ratelimit_or_timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\autogen\oai\completion.py", line 209, in _get_response
response = openai_completion.create(request_timeout=request_timeout, **config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 155, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 299, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 710, in _interpret_response
self._interpret_response_line(
File "C:\Users\Zenchant\Documents\agentcy\myenv\Lib\site-packages\openai\api_requestor.py", line 775, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: Invalid parameter: only messages with role 'assistant' can have a function call.

Timeout error

I always have this problem when running this repo with a valid API key , GPT 3.5 16k


File "/Users/jlcases/codigo/agentcy/venv/lib/python3.10/site-packages/openai/api_requestor.py", line 617, in request_raw
    raise error.Timeout("Request timed out: {}".format(e)) from e
openai.error.Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60)

I reviewed the code and timeout is set at 600s

Any thought?

Want to contribute

Hi Amadad would like to collaborate with me to make this next level product. I have team of frontend engineers and a team who can deploy this at this scale. Just contact me on discord drdoggo im in the auto gen discord

ImportError: please install openai and diskcache to use the autogen.oai subpackage.

Please enter the your goal, brief, or problem statement: project management
User_proxy (to chat_manager):

project management

Traceback (most recent call last):
File "/home/specific/Dokumente/dws/agentcy/main.py", line 443, in
user_proxy.initiate_chat(
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/conversable_agent.py", line 521, in initiate_chat
self.send(self.generate_init_message(**context), recipient, silent=silent)
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/conversable_agent.py", line 324, in send
recipient.receive(message, self, request_reply, silent)
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/conversable_agent.py", line 452, in receive
reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/conversable_agent.py", line 764, in generate_reply
final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/groupchat.py", line 116, in run_chat
speaker = groupchat.select_speaker(speaker, self)
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/groupchat.py", line 45, in select_speaker
final, name = selector.generate_oai_reply(
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/agentchat/conversable_agent.py", line 596, in generate_oai_reply
response = oai.ChatCompletion.create(
File "/home/specific/Dokumente/dws/agentcy/venv/lib/python3.9/site-packages/autogen/oai/completion.py", line 761, in create
raise ERROR
ImportError: please install openai and diskcache to use the autogen.oai subpackage.

Process finished with exit code 1

Python 3.11.6
pip 21.3.1

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.