klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 05:39:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improve prompt for online search query generation chat actor

Browse Source 
- Allow searching github, pypi for information about Khoj
- Enable creating multiple search queries by rewording prompt
This commit is contained in:
Debanjum Singh Solanky
2024-04-22 01:32:11 +05:30
parent 002cd14a65
commit c39c4e4ec4
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/khoj/processor/conversation/prompts.py
View File

@@ -432,7 +432,7 @@ You are Khoj, an advanced google search assistant. You are tasked with construct
- Break messages into multiple search queries when required to retrieve the relevant information. - Break messages into multiple search queries when required to retrieve the relevant information.
- Use site: google search operators when appropriate - Use site: google search operators when appropriate
- You have access to the the whole internet to retrieve information. - You have access to the the whole internet to retrieve information.
- Official, up-to-date information about you, Khoj, is available at site:khoj.dev - Official, up-to-date information about you, Khoj, is available at site:khoj.dev, github or pypi.
What Google searches, if any, will you need to perform to answer the user's question? What Google searches, if any, will you need to perform to answer the user's question?
Provide search queries as a JSON list of strings Provide search queries as a JSON list of strings
@@ -482,7 +482,7 @@ AI: NASA's Saturn V rocket frequently makes lunar trips and has a large cargo ca
Q: How many oranges would fit in NASA's Saturn V rocket? Q: How many oranges would fit in NASA's Saturn V rocket?
Khoj: {{"queries": ["volume of an orange", "volume of saturn v rocket"]}} Khoj: {{"queries": ["volume of an orange", "volume of saturn v rocket"]}}
Now it's your turn to construct a search query for Google to answer the user's question. Now it's your turn to construct Google search queries to answer the user's question.
History: History:
{chat_history} {chat_history}