-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Agent can think once but not twice. #205
Comments
Hey @roberthartmann can you elaborate the issue? |
Also, do try checking out the updated readme if it helps. |
Hey dude, what I did is to go to pinecone and create my own custom index of dimensions 10000 and then past that in the agent executor. Just give it your own name and replace both reference in the python file |
Hi, I composed it (yet again)... here are the logs of it. C:\Users\Robert\Desktop\SuperAGI> docker compose up --build next.config.js /** @type {import('next').NextConfig} */ module.exports = nextConfig there is another interesting message: superagi-gui-1 | - wait compiling /_error (client and server)... |
@CodeManMike how can i rename the pinecone index name while having a free account? if i knew that having subscription would solve the problem i'd be in for that |
@luciferlinx101 the agent was named "say hi" the comment was "say hi" and the task was "say "hi"" |
Hey mate, so don't rename the index, delete any index that you might have on pincone. I had one from autogpt, and then create a new index |
@roberthartmann is this issue still persisting? |
Hi,
I need your help.
I've been reading the topics #165 #184 #160 #192 and #200
but I still seem to be to blind to find the mistake.
My agent manages to define the tasks, write down what time it is and then starts thinking.
The 172.18.0.1 is hammered, and nothing happens.
Sure enough I looked at the PineCone Environment and API Key in the config.yaml they are correct.
The entry point.sh and wait-for-it.sh are set to LF since I run it in Win 10 with Docker
The agent_executor.py in the SuperAPI/Jobs sub folder shows
try:
if parsed_config["LTM_DB"] == "Pinecone":
memory = VectorFactory.get_vector_storage("PineCone", "super-agent-index1", OpenAiEmbedding())
else:
memory = VectorFactory.get_vector_storage("PineCone", "super-agent-index1", OpenAiEmbedding())
except:
print("Unable to setup the pincone connection...")
memory = None
As it is supposed to be with the free version of PineCone.
The ChatGPT ist 3.5 Turbo sice I don't have the Version 4.
So the only question that remains is: what did I not see?
There is something mentioned about the test.py but I really don't get it. I even changed the "LTM_DB:
To "super-agent-index1"
I really hope someone can help me.
The text was updated successfully, but these errors were encountered: