Feature Requests

Is there a way to pin the summary window so it does not disappear after clicking away from that window?

My left window, where the tags are, is getting really cluttery. Can we get a solution where the user can choose between "Show Tags + Cards" or "Show Tags Only"? In the "Show Tags Only" view, the users will be able to view the cards once a tag is clicked.

Select multiple cards and perform actions on them at once.

REQUEST: It would be great if we could edit the summarized cards created by the Chrome extension in our browsers, before saving. UX ISSUE: Right now, you have to save the card, then leave the browser, go into the app, make the edits there, exit the app, reopen the browser, and then continue browsing there. You quickly realize that realistically, you can't do this for every page. And suddenly, without each page, this app & extension can't really capture your browsing experience, and serve as "a second brain." So you don't use it all the time (because you're not being consistent and so it's kind empty,) and quickly, you've forgotten about it and never use it. (Which is such a shame; this app is seriously the best concept I've seen in years.) RESULT: If, instead, in that moment in the browser, you could edit and annotate before clicking "save," this would feel soo much more intuitive and natural that you could easily find yourself automatically clicking on the extension, jotting a note, and saving, on literally (and I do mean literally lol) every page you need to remember something from, just because of how fluid and integrated the experience is. The app & extension would soon become indispensable. Thanks, RM

During testing, large PDF documents (NIST IR 8428 or other research articles for example) exceed the token output window of the LLM that's in use. I suggest one of two recursive solutions: separate large documents into smaller parts and create individual cards for each part. a. Bad: may create section headers that don't make sense when attempting to determine the original document those section headers were created from. Goes against what appears to be the general theory behind Recall. b. Good: Summaries themselves maintain the maximum output token window for each section. Page and summary separation and ultimate compression to a maximum token output window. a. Bad: Maximum token output requires total compression of all previous summaries into one condensed summary. Substantial context may be lost due to the lack of reference back to the original source material when compressing summaries. b. Document is kept in one card. An example pseudo-function for option 2 is as follows: FUNCTION summarizeLargePDF(pdfFilePath, maxInputTokens, maxOutputTokens, llm): Initialization currentPage = 1 totalTokens = 0 currentSummary = "" allSummaries = [] # Array to hold section summaries sectionStartPage = 1 Recursive Page Processing Function (Nested) FUNCTION processPage(pageNumber): pageText = extractTextFromPage(pdfFilePath, pageNumber) pageTokens = countTokens(pageText) Check if adding this page exceeds input token limit IF (totalTokens + pageTokens) > maxInputTokens: Summarize the section sectionEndPage = pageNumber - 1 sectionText = extractTextFromPages(pdfFilePath, sectionStartPage, sectionEndPage) sectionSummary = llm.summarize(sectionText, maxOutputTokens) Add summary to the list and reset section allSummaries.append(sectionSummary) sectionStartPage = pageNumber totalTokens = 0 totalTokens += pageTokens currentPage += 1 Recursive call for the next page processPage(currentPage) Main Function Logic processPage(currentPage) # Start recursive processing Final Summarization of all Section Summaries WHILE allSummaries.length > 1: Combine and re-summarize in pairs newSummaries = [] FOR i = 0 TO allSummaries.length - 1 STEP 2: combinedText = allSummaries[i] + allSummaries[i+1] newSummary = llm.summarize(combinedText, maxOutputTokens) newSummaries.append(newSummary) allSummaries = newSummaries The single remaining summary is the final result finalSummary = allSummaries[0] RETURN finalSummary

It would be nice to have a desktop application and more self editing features like backlinks etc.

Dark mode is sometimes hard to read for me. I'd like a light mode.

Have the option to adjust the number of questions asked in the recall test.

A delete all questions button would be handy so you don't have to do so one by one.

This feature will give the user more control over the length of the summary. They will be able to choose between a concise and detailed summary.