Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Get a longer answer #16

Open
thvi opened this issue Jun 15, 2023 · 2 comments
Open

Get a longer answer #16

thvi opened this issue Jun 15, 2023 · 2 comments

Comments

@thvi
Copy link

thvi commented Jun 15, 2023

Hello,

Is it possible to get longer answers?
Because the answers are too vague.

Question: is Langchain to have a larger database so that it can provide more relevant answers? Let me explain: I'd like him to go beyond a simple summary of the content, but to provide his understanding so that his answer can guide us in understanding the document. Of course, LLMs can have hallucinations, so we need to be aware of this.

Thanks.

@almahdibakkali96
Copy link

almahdibakkali96 commented Jun 28, 2023

I believe you should ask your question the other way around: Are LLMs able to take large databases?
Yes, thanks to Langchain as a tool, and because OpenAI LLM can now ingest up to tens of thousands of tokens, the answer is yes.
Also, you can tell the LLM to be less random with your prompt. A low temperature will also help (many examples I saw use 0.2)

Edit: I hope this helps

@eyesuk
Copy link

eyesuk commented Sep 13, 2023

if you are using LLAMA2 you can pass it the -n flag and it will provide longer answers

-n N, --n-predict N: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants