kyb3r / emergent Goto Github PK

We have to prevent the same information to be provided multiple times

Right now we are just saving data in a json file as a stopgap solution while we are developing the system. But support for vector DBs is vital for scalability.

Having issues creating new tools and implementing
I want a web scraper that can save output to a json
when I try and run and call the function i defined it kees saying that as a ai they cant execute etc etc

not sure if its the safeguards or prompting help

basically if we can get this to work we haev plugins??

Just let me know where I can help. I am currently reading the code. Also, the ChatAgent never trims the chat log during the conversation(self.messages). If I understood the code correctly. I can fix that if you want.

I think that the agent should speak to itself and reason what topics would be helpful for him to know right now. We can then provide the closest match for each topic. In this internal chat the bot could later on also access various functions like searching the web.

The function that searches a kB article that is similar to the prompt, could also include an variable that defines a minimum distance in the embedded space so that any article is returned. Sometimes and even very often, the closest article might have absolutely no relationship with the topic. This will greatly reduce token use. Not only when providing kb articles but also when we want to identify how many articles to update. This could be done dynamically instead of trying to update the closest three.

From my first testing, they are just summaries and don't represent individual ideas or people. They should contain concise information of what was learned about the topic during the chat.

Hi, I just installed this with pip, but I'm getting this error when I try to use it.

AttributeError: partially initialized module 'emergent' has no attribute 'ChatAgent' (most likely due to a circular import)

I'd really appreciate it if someone could help me out. I'm using Python 3.11 for reference.

When using "response = agent.send(message)", I'm getting "Object of type generator is not JSON serializable".

I noticed that handle_message in ToolManager has been updated quite a bit and I'm trying to understand how it returns a response to the agent (e.g.: for use in tests/main.py).

I had a lengthy discussion with GPT using Emergent (great job btw) and fed it small segments of a story I'm writing, but when saving its memories to json, I got the error response from the OpenAI API that I broke the token limit. The discussion itself was fine; it wasn't until agent.end_conversation(memory_path) was called that I had issues with the token limit.

openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 4940 tokens. Please reduce the length of the messages.

Adding some sort of token limit handler would be great. Please let me know if I'm doing something wrong, lol.