Guru Devanla comments

Results 8 comments of


                                            Guru Devanla

Error using python3.8 and also service factory uses python2.7

I see the same error. Any tips on resolving this would be much appreciated. I am on emacs-26.3 ``` anaconda_mode port 42597 127.0.0.1 - - [19/Aug/2020 11:08:25] ================================================================================ Traceback (most...

Error using python3.8 and also service factory uses python2.7

Wanted to leave a note on how I resolved this issue: I removed anaconda installation from ~/.emacs.d. (Not sure why this folder was retained inspite of me deleting the package...

Support history_file configuration per dsn, and --history option.

I like this feature and would love this PR to come through. @laixintao are you still working on this. Is there something I can do to help?

Unable to provide llm_chain (instead of llm) to initialize_agent() while initializing the agent

That seems to have eliminated the initialization issue. But, then the OutputParse is failing. Wonder, if I need to set up an OutputParse expicitly for the llm_chain. Perhaps, the llm_chain...

Unable to provide llm_chain (instead of llm) to initialize_agent() while initializing the agent

@RamlahAziz I found a workaround for the time being. I took the original prompt and updated it to the way I wanted. Then, after constructing the agent, updated the prompt....

Is it possible to use gpt-3.5-turbo or gpt-4 as the LLM model for agents?

I tried this approach. But, with this approach I am not able to use the tools, due to parsing error: ``` OutputParserException: Could not parse LLM output: `I need to...

Add automatic python style checks

We can use `black` instead. It gives consistent formatting given that it is opinionated.

Support projects

@phadej For my personal projects I am using the /projects endpoints which is still in Github preview mode (`inertia`). Therefore, I have decided to extend the support here. Is this...