Import PDFs, images and documents
Biosphere extracts proposed facts from documents using its available record types. Documents can describe contacts, catalog, stock or orders; extraction does not execute payments, receiving, fulfillment or provider actions.
Read a document
Upload a supported document in Inbox or receive it through email. Processing runs in the queue, page by page, with the original retained separately. Open the arrival for coverage and Inspect processing details for its job.
After successful extraction, read Scout’s plan or select Manual. Choose who issued the records, the destination record type, stable IDs and field meanings. Review page evidence and uncertain values before approving. A guessed value or incomplete extraction cannot silently become an approved fact.
Originals remain downloadable through Import options, then Download original. Unsupported or rejected content has its actual retention state shown; rejected bytes are not promised as a retained original.
Recover or read again
Biosphere retries failed pages within their attempt budget. Retry failed pages repeats failed work with attempts left. Successful pages remain retained.
Open Details, then Processing details, expand the new-extraction controls, choose the record types to extract, then select Start new extraction. A new version reads every page again and may incur provider cost. Earlier versions stay. A running extraction must finish or be cancelled before starting another.
Review and automate
Inspect the proposed changes and resolve uncertainty, then select Approve import. Coverage and the future-arrival policy are part of the same review. Recognized documents and email can process automatically under the same source, validation and ownership rules as every other format.
Supported documents include PDF, PNG, JPEG, DOCX, DOC, PPTX, PPT, RTF and text. Office formats are normalized before extraction; the original stays unchanged. See Upload files for size and safety limits.
Review part of an arrival
The changes table counts new, updated and unchanged records. The note describes the proposed business changes; only specific choices can block approval. Open Details, then Source records, to choose a smaller selection. After the new changes are ready, Approve 40 of 42, for example, applies those 40 and leaves the other two in Inbox for later. Some problems need a field or match corrected before a batch can be separated safely.
Use Approve & next to save the reviewed changes and open another arrival that needs attention. Approval must succeed before Biosphere moves on.
Retry failed pages
Biosphere retries a failed page on its own first. The source shows when the next try is scheduled and which attempt it is.
If pages still fail, the coverage reads “Processing stopped. Your original and completed pages are retained.”
- Use the Retry failed pages button (Retry failed slides for a presentation). Only the failed pages are read again.
- If the retry limit was reached, read the whole document again instead.
Use the Inspect processing details link for the full attempt history on the Background jobs page.
Read a document again
- Open the source in Inbox. If its details are already in review, open Processing details to find the page coverage.
- Open Read document again and choose the record types to read.
- Select Start new extraction.
Biosphere reads every page again from the original and creates a new extraction version. It may use paid cloud processing if fallback is enabled. Earlier versions and their results stay. You can’t start one while another extraction is running.
What to know
- Each file can be up to 100 MiB and 100 pages or slides. Images can be up to 25 megapixels.
- Locked PDFs, and PDFs with scripts, active content or embedded files, are refused. Upload an unlocked copy without them.
- DOCX, DOC, PPTX, PPT and RTF files are turned into pages before reading. The original stays as it was uploaded.
- Approving document details goes through the same review as any other import. Nothing changes until you approve. Scout can read the original email behind an attachment, including who sent it, who received it, its message and attachment names. Ask Scout to find the sender’s contact and examine related records you have access to. Matching an email address does not approve an import or establish who owns the incoming data.