thinkall / autogen-demos Goto Github PK
View Code? Open in Web Editor NEWDemo code for use cases of AutoGen
License: MIT License
Demo code for use cases of AutoGen
License: MIT License
def chatbot_reply(input_text):
"""Chat with the agent through terminal."""
queue = mp.Queue()
process = mp.Process(
target=initiate_chat_with_agent,
args=(llm_config, input_text, queue),
)
process.start()
try:
# process.join(TIMEOUT+2)
messages = queue.get(timeout=TIMEOUT)
except Exception as e:
messages = [
str(e)
if len(str(e)) > 0
else "Invalid Request to OpenAI, please check your API keys."
]
finally:
try:
process.terminate()
except:
pass
return messages
When I run the code, it shows an error like below. Could you please help me fix this?>
exitcode = _main(fd, parent_sentinel)
self = reduction.pickle.load(from_parent)
AttributeError: Can't get attribute 'initiate_chat_with_agent' on <module 'main' (built-in)>
I just found out about your interesting projects here and try to run the Panel in docker.
The build throws folling error:
132.4 Attempting uninstall: typing-extensions
132.4 Found existing installation: typing_extensions 4.4.0
132.4 Uninstalling typing_extensions-4.4.0:
132.6 ERROR: Could not install packages due to an OSError: [Errno 22] Invalid argument: '/home/autogen/.local/lib/python3.10/site-packages/typing_extensions-4.4.0.dist-info/'
132.6
------
Dockerfile:22
peeking arround, autogen will be installed with local LLM support as well as pytorch-cpu. the latter pulls in typing_extensions 4.4.0
which gives this error.
since in my usecase, I have a litellm.ai API-proxy towards my local running LLMs on another machine, this is unneccessary.
can I just drop torch and LLM and bump autogen to the latest version? will that work?
OT: and what is this ernie-bot about?
Hi, came across the repo and am excited to test it out. I'm unable to get in running and am hoping to have some clarity on what configuration is needed.
Here are the steps I've done:
conda create -n autogen-demo python=3.10
conda activate autogen-demo
pip install "pyautogen[retrievechat]"
python app.py
Here are the results I get, it seems to be issues with the imports:
File "/.../autogen-demo/app.py", line 9, in <module>
from autogen.retrieve_utils import TEXT_FORMATS, get_file_from_url, is_url
File "/Users/.../miniconda3/envs/autogen-poc/lib/python3.10/site-packages/autogen/retrieve_utils.py", line 8, in <module>
from chromadb.api import API
ImportError: cannot import name 'API' from 'chromadb.api' (/Users/.../miniconda3/envs/autogen-poc/lib/python3.10/site-packages/chromadb/api/__init__.py)
Any suggestions?
Thanks!
dsfasfs
werwqesdffsd
asdfsdfsf
sdfafs
sadfasfsdf
When running the following pip install, an error occurs.
pip3 install --no-cache-dir -r requirements.txt
ERROR: Could not find a version that satisfies the requirement pyautogen==0.1.14 (from versions: none)
ERROR: No matching distribution found for pyautogen==0.1.14
Python 3.9 version is installed for this. The AutoGen Docs do not mention anything about the RetrieveAssistantAgent so it appears it was only supported in an older version of AutoGen.
I expect it to work.
No response
No response
Clicked on AutoGen_Playground online demo on HuggingFace. I spun with "Preparing Space" for 10 minutes and nothing else appeared.
See above -- just click "online" in "Group Chat Playground Demo:.
Should start app.
No response
No response
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.