Index a Document
Upload a document URL and wait for its searchable state.
Upload [file URL] as [filename], then wait for the file to become ready for retrieval.
Leina connects to OOMOL RAG to help you index documents and answer questions from your team knowledge base. Ask in your team chat. Leina does the work and brings back the result.
Connect OOMOL RAG, choose what to share, and hand off your first task.
You
From our team knowledge base, find the supplier onboarding requirements. Summarize the required documents and next steps, naming the source files and anything not stated.
Leina
The retrieved guide asks for a company profile and product catalog. It also calls for a sample review after approval, but gives no approval timeline.
OOMOL RAG · Knowledge summary
Supplier onboarding requirements
Evidence retrieved from supplier-guide.pdf.
AI can use OOMOL RAG to index documents and retrieve relevant passages, then answer questions with source filenames and gaps in the evidence.
You specify the source and the destination. Leina uses the content available to your connection and returns the result for you to review.
OOMOL RAG is a team knowledge base for document indexing and semantic retrieval.
Visit Provider Website ↗Query the current team knowledge base for supplier onboarding requirements.
Identify requirements and next steps in the returned text.
Name source files and distinguish missing information from stated requirements.
Copy a prompt, add your details, and send it to Leina in your connected team chat.
Upload a document URL and wait for its searchable state.
Upload [file URL] as [filename], then wait for the file to become ready for retrieval.
Retrieve relevant text chunks for a supplied question.
Retrieve knowledge chunks about [question], then answer using the returned evidence and identify gaps.
Read file metadata and obtain a temporary public download URL.
Get file [ID], then obtain its download URL for review.
Keep findings from team documents in a project page with source filenames.
Retrieve passages about [question] from the OOMOL team knowledge base. Summarize the findings, keep source filenames and unanswered questions, and create a note under Notion page [page ID].
Your next OOMOL RAG task can start with a message.
Tell Leina what you need in your team chat. Include the source, destination, and expected result.
Use the current OOMOL team context; no separate third-party credential is required.
Share the source material, say where the result belongs, and describe what you need.
Review the result and any changes in the connected app.
Hand off these everyday tasks to your AI employee.
Atomically update, insert or delete BlockNote blocks by ID without replacing the article. Updates merge properties and replace only explicitly supplied block content, preserving other blocks, children, images and formatting. Operations run in order; a missing ID or invalid operation rolls back the entire batch. Requires format version 3 and the expected revision. Retry with identical saveId, revision and operations. Saves a draft; does not publish.
Create and save an editable article from Markdown as an unpublished draft. Requires stable articleId and saveId. Creation then saving are two requests: if saving fails, a blank draft may remain; retry the identical IDs and payload to resume. Never overwrites an existing edited article; a revision conflict requires inspection.
Replace the entire article body and title from Markdown, saving a BlockNote draft at the expected revision. This is full replacement, not append or patch; blocks and private images absent from Markdown are removed from the draft. Read and reconcile before saving; on 409 never blindly retry with a new revision. Does not publish.
Create an empty editable knowledge article as a draft. A caller-stable articleId prevents duplicate creation on retries; an existing ID returns its article without overwriting it.
List knowledge articles with draft and synchronization metadata, without document bodies.
Read the full editable article, its format version, revision and knowledge-base synchronization state.
Save BlockNote content and title with optimistic revision checking. This only saves a draft; publish_article updates retrieval. Retry an uncertain request with the identical saveId, revision and body.
Publish an exact saved revision to the knowledge base, replacing its previous index asynchronously. Retry uncertain transport outcomes with the same publishId and revision. Stop and inspect failed or uncertain synchronization states.
Poll the latest article publication once. Ready means its syncRevision is indexed; a newer draft can still be unpublished. Compare syncRevision with your requested revision when tracking a particular publication.
Delete an article and exclude its index from retrieval. Underlying index cleanup is asynchronous; any original converted file is preserved.
Upload a publicly reachable file URL to the current OOMOL team's knowledge base and start asynchronous indexing.
List files in the current OOMOL team's knowledge base.
Get metadata and processing status for a knowledge-base file.
Get a file's ingestion state while waiting for it to become searchable.
Download a knowledge-base file through OOMOL file transit and return a temporary public URL.
Start asynchronous deletion of a knowledge-base file.
Get a file's deletion state while waiting for deletion to finish.
Retrieve the most relevant text chunks from the current OOMOL team's knowledge base.
Tell Leina which sources to use and where the result belongs.
Connect the Apps your work depends on, and give Leina the context to carry the task forward.
Hand off a task while your team is discussing it. Leina uses your connected tools and brings the result back to the conversation.
See How Leina Works in SlackThe retrieved guide asks for a company profile and product catalog. It also calls for a sample review after approval, but gives no approval timeline.
Uploading starts asynchronous indexing. Wait for the ready state before retrieving text chunks from the file.
Use the current OOMOL team context; no separate third-party credential is required.
Upload publicly reachable file URLs and wait until indexing is ready before retrieval. Retrieval returns relevant chunks rather than a complete document.
Start with one task you already need to do. Tell Leina what a finished result should look like.
Connect OOMOL RAG, choose what to share, and hand off your first task.