autopackai / beebot Goto Github PK
View Code? Open in Web Editor NEWAn Autonomous AI Agent that works
License: MIT License
An Autonomous AI Agent that works
License: MIT License
I think the title is clear enough but feel free to ask if you don't understand.
Hi, guys.
This is Roman - CTO from Sinai RnD.
I played for several weeks with different GPT Agents. And I'm really interested in BeeBot's potential, approach and tools-focusing.
Thank you a lot for your outstanding work!
During my tries with BeeBot, I mentioned interesting behaviour. Sometimes AI decides to choose a command that does not exist in the list of available commands but is close to it. For example:
save_data(data="Important data", file_name="data.txt")
instead of write_file(filename="data.txt", text_content="Important data")
python(function_call="google_search", question="How much is the fish?")
instead of google_search (query="How much is the fish")
Finally, I wrote and tested a very small fix that asks AI to map a non-exited command to an exited one if such behaviour occurs.
Do you think that this approach makes sense and is it worse to make a PR for it?
I am going to fix the code to address the agent protocol issue and commit but i had to say it, this is very good. I am stealing your folder structure because it is the only one ive seen so far that i can look at and know precisely what everything does, I can take that and draw basically a tree that is roughly equivalent to an anatomy for an Autonomous AI Agent. Been trying to work that out for the entire time ive been crash coursing so thank you and I am watching hoping ya'all geet back on the project.
regardless I'll be adopting the organizational structure when I start coding my own from scratch.
Issues related to prompts that are known and will be fixed will be listed in this issue. Contributions to fix these issues are welcome.
read_file
output is usually not parsed correctly from history such that it will attempt to read the same file over and over. Consider document embedding again and maybe disabling read_file
as a result.I am getting the following error while testing out beebot. I have run the ./setup.sh script after getting into venv
and got this:
(beebot) unitythemaker@blazingfast ~/TMP/beebot (main) [1]
❯ poetry install
Installing dependencies from lock file
Package operations: 19 installs, 0 updates, 0 removals
• Installing agent-protocol (0.2.4): Failed
RuntimeError
Unable to find installation candidates for agent-protocol (0.2.4)
at lib/python3.11/site-packages/poetry/installation/chooser.py:73 in choose_for
69│
70│ links.append(link)
71│
72│ if not links:
→ 73│ raise RuntimeError(f"Unable to find installation candidates for {package}")
74│
75│ # Get the best link
76│ chosen = max(links, key=lambda link: self._sort_key(package, link))
77│
• Installing agent-protocol-client (0.2.2): Failed
RuntimeError
Unable to find installation candidates for agent-protocol-client (0.2.2)
at lib/python3.11/site-packages/poetry/installation/chooser.py:73 in choose_for
69│
70│ links.append(link)
71│
72│ if not links:
→ 73│ raise RuntimeError(f"Unable to find installation candidates for {package}")
74│
75│ # Get the best link
76│ chosen = max(links, key=lambda link: self._sort_key(package, link))
77│
<coroutine object main at 0x1034b0f40>
sys:1: RuntimeWarning: coroutine 'main' was never awaited
RuntimeWarning: Enable tracemalloc to get the object allocation traceback
Dear BeeBotTeam,
I hope this message finds you well. As we work on enhancing our project's performance and optimizing our AI system, we believe that your valuable log data can provide valuable insights. To that end, we kindly request your assistance in sharing relevant log files with us.
Your logs could help us better understand system behavior, identify areas for improvement, and enhance our AI interactions. Rest assured that we will handle your data with the utmost care and in compliance with all applicable data privacy regulations.
Please let us know if you are willing to share your log files and, if so, the preferred method for sharing them. Your contribution will be greatly appreciated and will contribute to the success of our project.
Thank you for your support and collaboration.
Best regards,
Mike
Users want access to as much AI as they can get, they dont want to manage 50 accounts, they want the fastest AI they want the cheapest AI, and you can provide all of that for them with this update.
in addition to or in place of integrating with any aggregators - Please integrate APIpie so devs can access them all from one place/subscription and plus it also provides:
-The most affordable, reliable and fastest AI available
-One API to access ~500 Models and growing
-Language, embedding, voice, image, vision and more
-Global AI load balancing, route queries based on price or latency
-Redundancy for major models providing the greatest up time possible
-Global reporting of AI availability, pricing and performance
Its the same API format as openai, just change the domain name and your API key and enjoy a plethora of models without changing any of your code other than how you handle the models list.
This is a win win for everyone, any new AI's from any providers will be automatically integrated into your stack with this one integration. Not to mention all the other advantages.
poetry run beebot
<coroutine object main at 0x7fa467bfd4e0>
sys:1: RuntimeWarning: coroutine 'main' was never awaited
RuntimeWarning: Enable tracemalloc to get the object allocation traceback
INFO 09:00:38.380 decomposer.py:58- [
raise OperationalError(exc)
tortoise.exceptions.OperationalError: relation "body" does not exist
I'm running in ubuntu via wsl2 in windows 11. Not sure if this is a supported environment.
What would you like me to do?
> get the css styling information from https://www.flaotplane.com
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "/home/*****/beebot/beebot/initiator/cli.py", line 35, in main
initialize_db(config.database_url)
File "/home/*****/beebot/beebot/models/database_models.py", line 88, in initialize_db
database = connect(db_url)
File "/home/*****/.cache/pypoetry/virtualenvs/beebot-gxFpor5K-py3.10/lib/python3.10/site-packages/playhouse/db_url.py", line 102, in connect
raise RuntimeError('Unrecognized or unsupported scheme: "%s".' %
RuntimeError: Unrecognized or unsupported scheme: "".
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.