Guilherme Ramos
Guilherme Ramos
You have to use python3.10
@KillianLucas I've been trying to keep this PR as much updated as possible. The last MERGE from main resulted in an conflict in both `respond.py` and `setup_openai_coding_llm` as they are...
Merged with main branch now. It's getting harder and harder to maintain this. Please help incorporate such functionality.
Also, if possible, the OpenInterpreter is defaulting to "gpt-4" which is the most expensive model. Can we provide tha as an argument? @Arrendy @KillianLucas
@Notnaton , cost limit is one different than how much it did cost the last interaction with the chat. Programatically, this is basically unreacheable, after you call interpreter.chat()
The `Interpreter.llm.max_budget` is reachable, what is not reachable is the cost of the last interaction with the chat. We can see in the logs a line like this: `final cost:...
@jordanbtucker @KillianLucas Yes, I am already doing that, but through changing the code of interpreter.py which is not ideal because every time there's an official code change in the main...
Thanks! I was able to add the maven dependency.
Which version contains this fix? @assafelovic @regismesquita
@regismesquita I tried to add this version to my pyproject (poetry) and it did not find. Currently I have: ``` gpt-researcher = "^0.10.3" ```