I've added a document loader that will read and parse MS office file types, .doc, .docx, .xls, .xlsx, .ppt, .pptx. Turns out it's a bit more complicated than I expected so I didn't extract the texts but all the doc data and parse it in the schema.Document.PageContent.
For excel files there is metadata that will extract sheets and numerate them. The docx and pptx are just xml so I didn't extract the text just dumped the xml into PageContent, so at later date maybe somehow who understands the file formats better than me can build a decent document structure into schema.Document{}.
At the same time I think there are some advantages of llm having access to entire document structure not just the text strings.
[x] Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
[x] Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
[x] Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
I've added a document loader that will read and parse MS office file types, .doc, .docx, .xls, .xlsx, .ppt, .pptx. Turns out it's a bit more complicated than I expected so I didn't extract the texts but all the doc data and parse it in the schema.Document.PageContent.
For excel files there is metadata that will extract sheets and numerate them. The docx and pptx are just xml so I didn't extract the text just dumped the xml into PageContent, so at later date maybe somehow who understands the file formats better than me can build a decent document structure into schema.Document{}.
At the same time I think there are some advantages of llm having access to entire document structure not just the text strings.
PR Checklist
memory: add interfaces for X, Yorutil: add whizzbang helpers).Fixes #123).golangci-lintchecks.