-
Notifications
You must be signed in to change notification settings - Fork 10
feat: web search #119
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
feat: web search #119
Conversation
jcabrero
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please review the comments, if you feel like there is something you don't fully understand, let me know and I can guide you through it.
docs: format PostgreSQL setup instructions in README for clarity
web_search parameter can be set to true or false in the chat endpoint. If true, the first three searches are added to the context. The user can access the sources in the output object
jcabrero
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It looks much better now. There are a couple of comments left unsolved. Please have a look at them before merging.
Add retry logic to reduce failed tests due to source quality
The chat completion endpoint now includes web search functionality. By setting the websearch parameter to true, a web search is performed and the results are incorporated into the context of the LLM before generating the final output. The sources fetched are provided as a list in the output object
Implemented testing for the websearch feature