RAG issue: HTML source documents show up in the chat with their path instead of HTML page title

[flang-ls1]

My RAG flow is based on the web-scrape-qna template by Flowise https://docs.flowiseai.com/use-cases/web-scrape-qna so I use HTML Splitter, Cheerio, Pinecone and Conversational Retrieval QA Chain. I use a seperate flow to upsert to Pinecone and I don't use Redis at the moment. The problem is now that when I return source documents to the chat, they show up in the chat window with their relative URLs instead of the page title as is nicely seen in the screenshot in Flowise's web-scrape-qna example. When I upsert the way as shown in the example I don't even have a metadata key in Pinecone that contains the page title... I even added a title metadata key in Pinecone with a python script but now I don't know how I get Flowise to use these titles when displaying source documents. Do you have any idea why that is? Is there any solution to make this work? Many thanks!!

[flang-ls1]

Any help is much appreciated!

[flang-ls1]

I figured it out. If there's a valid URL in the "source" metadata key of the source it will display the first chars of the path in the source bubble, which most likely do not make much sense to the user. For example if the source is https://www.example.com/en/subpath/subpath/folder/filename.html the source bubble label will display a truncated relative path such as "/en/subpath/s..." or something like that. Ideally, we can display html page titles in the source bubble but as a workaround, I fixed the line of code in the embed widget and now it will at least display the filename.html which COULD make sense to the user. I hope Flowise devs fix this and provide a way for us to display html page titles as the source label.