(Constructs): Web RAG - Web Crawler, Chatting with Web Pages and Search #291
Labels
RFC-proposal
RFC Proposal - used for tracking through process on Project board. NOT an "issue" as such.
stale
Describe the feature
Many RAG experiences are built around websites. Users want to crawl one or more websites, retrieve content from pages, schedule periodic updates, and inject results into OpenSearch to enable RAG requests based on website data.
To support this scenario, a WebCrawler construct can be created. It should be capable of creating new OpenSearch indexes or using existing ones.
This construct can also be used to obtain data from websites in real-time. For example, a user could ask a chatbot to summarize a specific webpage. In this case, the web crawler should extract data from the webpage and provide it to the chatbot.
We should also consider web search scenarios, where users want to use a search engine to obtain results. The results found by the search engine should be parsed and returned to the chatbot.
Use Case
RAG over websites
Proposed Solution
No response
Other Information
No response
Acknowledgements
The text was updated successfully, but these errors were encountered: