# January 10: Support for conversation message images, email filtering, Diffbot API key, bug fixes ### New Features * :bulb: Graphlit now supports sending Base64-encoded images with user messages to the `prompt`mutation. You can provide the user `prompt`, with an optional `mimeType`and `data`property to have the LLM prompt use the image in its prompt completion. This applies to the conversation `messages`parameter as well. Also, now the user `prompt`parameter is optional, and you are able to just provide the conversation messages array only, if desired. * Graphlit now supports email filtering for Microsoft and Google email. We have added flags in the email feed properties for `includeSpam`, `includeDeletedItems`, and `excludeSentItems`which all default to False. We have also added `inboxOnly`which you can set to True to only read emails from the Inbox folder (applies to reading Past emails; reading new emails already reads just from the Inbox folder). * We have added a `disableInheritance`flag into the `ContentFilter`object, which will disable the default inheritance of content from project-scope to tenant-scope. By setting this to True, and querying contents within a tenant, you will only get back tenant contents, and nothing from the parent project. * We have added support for bringing your own Diffbot API key. You can assign `key`to the `diffbot`property in the `EntityEnrichmentConnectorInput`object, when creating your workflow ### Bugs Fixed * GPLA-3723: Failing to ingest DOCX from Google Drive, with multitenancy * GPLA-3706: Handle Microsoft Graph resync required properly --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://changelog.graphlit.dev/january-2025/readme-2.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.