Pulp comments

Results 132 comments of


                                            Pulp

Added script arguments to disable printing of LLM stdout Stream and source documents

BTW, @imartinez thank you very much for working on this project.

File "pydantic/main.py", line 331, in pydantic.main.BaseModel.init pydantic.error_wrappers.ValidationError: 1 validation error for GPT4All n_ctx none is not an allowed value (type=type_error.none.not_allowed)

See https://github.com/imartinez/privateGPT/issues/78#issuecomment-1545977382 You have to rename `example.env` to `.env` like explained in the `README` file.

File "pydantic/main.py", line 331, in pydantic.main.BaseModel.init pydantic.error_wrappers.ValidationError: 1 validation error for GPT4All n_ctx none is not an allowed value (type=type_error.none.not_allowed)

If this is solved please close this issue.

refactor: Update document loading and vectorstore creation process

I'm not entirely convinced about this change, not sure if it's necessary and I can see benefits with as is on master. Let's wait to see what plans @imartinez has...

No input for the question: "Enter a query:" NEVER shows

This is a duplicate of https://github.com/imartinez/privateGPT/issues/281 and https://github.com/imartinez/privateGPT/issues/295

No input for the question: "Enter a query:" NEVER shows

@AngelTs Your `.env` file was good before. See the other issues I linked above, it's probably a problem with your hardware, your CPU is too old.

No input for the question: "Enter a query:" NEVER shows

Maybe they use the GPU or something? Or some online API? In any event, if you think there's still an issue, it's better if you close this one and comment...

Multilanguage (translation) support + support for local OpenAI server realizations

If this is doing external `http` requests to Google or any other server, I'm quite a bit against this (totally against if it's default on). The point of this repo...

Multilanguage (translation) support + support for local OpenAI server realizations

> IMO the decision should be left to the end user, yet I doubt that this solution is THE solution. I very much agree with this, but I thought this...

Time from prompt to response is too long! Very Slow?

@laihenyi See https://github.com/imartinez/privateGPT/issues/276#issuecomment-1554262627