You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I want to build a tool which works in different languages (esp. English, German, French, Dutch and Spanish). Normally the GPT-3-Turbo (which I use) is able to 'speak' all those.
The Documents (context provided in the prompt), as well as the prompts itself are 100% in English.
Currently my prompts looks like this:
const CONDENSE_PROMPT = Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question in the same language as the original question.
Chat History:
{chat_history}
Follow Up Input: {question}
Standalone question:;
const QA_PROMPT = You are a helpful AI assistant. Use the following pieces of context to answer the question at the end.
If you don't know the answer, just say you don't know. DO NOT try to make up an answer.
If the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.
{context}
Question: {question}
Helpful answer (in the same language as the question) in markdown:;
Sometimes it works, sometimes not, I am not able to figure out under what conditions it works best/worst.
I already tried different temperatures.
I would be happy for any Ideas how to tackle this issue.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello,
I want to build a tool which works in different languages (esp. English, German, French, Dutch and Spanish). Normally the GPT-3-Turbo (which I use) is able to 'speak' all those.
The Documents (context provided in the prompt), as well as the prompts itself are 100% in English.
Currently my prompts looks like this:
const CONDENSE_PROMPT =
Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question in the same language as the original question.Chat History:
{chat_history}
Follow Up Input: {question}
Standalone question:
;
const QA_PROMPT =
You are a helpful AI assistant. Use the following pieces of context to answer the question at the end.If you don't know the answer, just say you don't know. DO NOT try to make up an answer.
If the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.
{context}
Question: {question}
Helpful answer (in the same language as the question) in markdown:
;
Sometimes it works, sometimes not, I am not able to figure out under what conditions it works best/worst.
I already tried different temperatures.
I would be happy for any Ideas how to tackle this issue.
Thank you,
Felix
Beta Was this translation helpful? Give feedback.
All reactions