Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

github.com

Post reply on HN
Print view View original

21–30 of 100 posts

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#21

Post by shagie »

petilon wrote: post #8
swalsh wrote: post #6

Earlier quoted context omitted.

You could probably ask ChatGPT how to get started with GPT, but I think a lot of people are building apps taking advantage of GPT's Fine Tuning ability. https://platform.openai.com/docs/guides/fine-tuning

If I take advantage of this for allowing my customers to ask questions about our product documentation, how do I limit questions to questions about my product documentation? I don't want to be paying Open OPI for questions unrelated to my product.

One idea would be to use a much cheaper (and faster) classifier to come back with a "yes" or "no" if the question asked is about your product documentation.

Using Ada or Babbage is about 1% of the cost of Davinci (and Curie is 10% the cost of Davinci).

Without any real tuning, this responds quite promptly (and the various tests I've done, correctly):

    curl https://api.openai.com/v1/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $OPENAI_API_KEY" \
      -d '{
      "model": "text-ada-001",
      "prompt": "Identify if the following question is about the Olympic Games.  Answer with {yes}, {no}, {maybe}.\n\nWhat category is pole vaulting in?",
      "temperature": 0.7,
      "max_tokens": 38,
      "top_p": 1,
      "frequency_penalty": 0,
      "presence_penalty": 0
    }'

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#24

Post by bongobingo1 »

shagie wrote: post #21
petilon wrote: post #8

Earlier quoted context omitted.

If I take advantage of this for allowing my customers to ask questions about our product documentation, how do I limit questions to questions about my product documentation? I don't want to be paying Open OPI for questions unrelated to my product.

One idea would be to use a much cheaper (and faster) classifier to come back with a "yes" or "no" if the question asked is about your product documentation. Using Ada or Babbage is about 1% of the cost of Davinci (and Curie is 10% the cost of Davinci). Without any real tuning, this responds quite promptly (and the various tests I've done, correctly): curl https://api.openai.com/v1/completions \ -H "Content-Type: appl…

> What category is pole vaulting in?

>> Yes

Well, at least you can't say the documentation is out of date.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#25

Post by kfarr »

grensley wrote: post #22

Seeing https://github.com/arc53/docsgpt/blob/main/application/combi... is just fascinating to me. It's absolutely where this all is headed, but to see it as source code evokes something in me.

It's like the new crud but instead of designing the database tables and columns you're tweaking the prompts.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#26

Post by jesselawson »

bongobingo1 wrote: post #24
shagie wrote: post #21

Earlier quoted context omitted.

One idea would be to use a much cheaper (and faster) classifier to come back with a "yes" or "no" if the question asked is about your product documentation. Using Ada or Babbage is about 1% of the cost of Davinci (and Curie is 10% the cost of Davinci). Without any real tuning, this responds quite promptly (and the various tests I've done, correctly): curl https://api.openai.com/v1/completions \ -H "Content-Type: appl…

> What category is pole vaulting in? >> Yes Well, at least you can't say the documentation is out of date.

Honestly the best comment I've read on here in a long time. Cheers.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#27

Post by eyegor »

This is a cool idea. Right now my goto tends to be https://devdocs.io/, but the idea of a conversational type of layer is fascinating. It's always a struggle in a new set of docs trying to figure out their phrasing for merge/join/combine or how they describe aggregations for example. A lot of the time when you're looking at documentation, you're trying to look up "how to do x (with y)" but most docs are written in a "common language" and end up describing things in jargon you may not be aware of yet.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#28

Post by shagie »

bongobingo1 wrote: post #24
shagie wrote: post #21

Earlier quoted context omitted.

One idea would be to use a much cheaper (and faster) classifier to come back with a "yes" or "no" if the question asked is about your product documentation. Using Ada or Babbage is about 1% of the cost of Davinci (and Curie is 10% the cost of Davinci). Without any real tuning, this responds quite promptly (and the various tests I've done, correctly): curl https://api.openai.com/v1/completions \ -H "Content-Type: appl…

> What category is pole vaulting in? >> Yes Well, at least you can't say the documentation is out of date.

I was just after something simple in its training set to demonstrate the simple classification that could be used as a check before passing the request on to a more expensive fine tuned model.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#29

Post by antiatheist »

bfeynman wrote: post #19

This is really the quality of projects we're upvoting? This is a python script that calls another API.

I agree, the code is pretty average, inconsistently using quotation marks, looks copy pasted and developer comments trying to understand what they're doing. The concept isn't too novel either, LLM usage in knowledge base querying is nothing new, I know some lawyers looking into it for regulatory compliance.

The KnowledgeGPT repo linked by another commenter seems more interesting.

Re: Show HN: DocsGPT, open-source documentation assistant, fully aware of libraries

#30

Post by keithwhor »

shagie wrote: post #21
petilon wrote: post #8

Earlier quoted context omitted.

If I take advantage of this for allowing my customers to ask questions about our product documentation, how do I limit questions to questions about my product documentation? I don't want to be paying Open OPI for questions unrelated to my product.

One idea would be to use a much cheaper (and faster) classifier to come back with a "yes" or "no" if the question asked is about your product documentation. Using Ada or Babbage is about 1% of the cost of Davinci (and Curie is 10% the cost of Davinci). Without any real tuning, this responds quite promptly (and the various tests I've done, correctly): curl https://api.openai.com/v1/completions \ -H "Content-Type: appl…

It's way easier and cheaper to use embeddings for these sorts of use cases.
Post reply on HN