FY2027 Growth PlanSection 4
4.3 FY2027 projection
Net revenue retention is 128%.
Revenue reaches $48.2M, 12% ahead of plan and up 31%.
EBITDA guidance rises to $10.6M.
12
Send any file in. Get back the passage, the file and the page it came from.
DocSlurp does three jobs: it extracts any file into page-by-page Markdown and structured fields, searches the result for RAG context, and answers questions through a configurable chat endpoint. Every passage and answer cites the page it came from. The CLI, SDK, HTTP API, MCP server and embeds all read and write the same projects.
Start with the job you need. Each one reads the same project, so documents you ingest are searchable and answerable without extra setup.
Any file in: PDF, Office, EPUB, HTML, images, audio and video. Out come page-by-page Markdown, page images, chunks and, with your JSON schema, structured fields.
Upload files and follow each run until it is indexed.
Plain REST and JSON, from any language.
Extract fields with your own schema and check each one against its page.
Hybrid search returns ranked passages or ready-to-paste RAG context, each citing its document and page.
Illustrated explainers for RAG, embeddings, HyDE, ranking and citations.
Inputs, filters, retrieval controls and response contracts.
Format hits as numbered context for any LLM.
Let coding agents search your projects and cite pages.
Keep your Algolia, Meilisearch, Typesense or Pagefind calls.
Cited answers over a project, with streaming. Set instructions, answer style and context mode per project; pick the model, retrieval and filters per request.
Point an existing Chat Completions client at a project.
Cited answers and follow-up turns from code or a terminal.
React components or custom elements for your product.
You need Node.js 20+ and a DocSlurp account. Create a server key with the ingest and search:deep scopes, then run these four lines. Without a project ID, both commands use your organization's default project.
npm install --global @docslurp/cli
export DOCSLURP_API_KEY='dslp_priv_…'
docslurp upload ./growth-plan-2027.pdf --watch
docslurp search 'Are we on track to beat our FY2027 earnings?'docslurp command. The SDK and HTTP API do the same job from code.ingest and search:deep scopes. It stays on your machine or backend. To sign in with your browser instead, skip this line and run docslurp login --scopes "search:deep read ingest".--watch, upload returns once the file is accepted. With it, the command follows processing until the run finishes, for up to five minutes.docslurp chat does.Outputdocslurp search 'Are we on track to beat our FY2027 earnings?'
FY2027 Growth PlanSection 4
4.3 FY2027 projection
Net revenue retention is 128%. Revenue reaches $48.2M, 12% ahead of plan. Margin lands at 24%.
12
growth-plan-2027.pdfp. 12 cited by result 1
Pass --context for numbered passages to paste into your own model, --json for the full response, or use docslurp chat for a generated answer with the same citations.
Upload from a script, search from your app, ask from your agent. Everything reads and writes the same projects, so you can mix them freely.
docslurp upload ./docs/*.pdf --watchawait client.upload(file)POST /v1/uploads/bulkYour project
Upload, wait for indexing, and search from TypeScript or a terminal.
Plain REST and JSON, from any language.
Extract JSON fields with your own schema and check them against the source page.
Every SDK, adapter, CMS target and language client, with status.
Illustrated explainers for every idea behind document search: OCR, embeddings, HyDE, ranking, citations.
Let Claude Code, Codex, Cursor or VS Code search your projects and cite pages.
Point an existing chat client at a project.
Add search and chat with citations to your product with React components or custom elements.
Keep your Algolia, Pagefind, Meilisearch or Typesense code and swap the engine.
Keep your Algolia client calls and import settings, synonyms and rules.
SDK methods, errors, retries and upload recipes.
Search inputs, response contracts and retrieval controls.
Pick fastest, balanced or smart; DocSlurp manages the models.
CLI commands, JSON output and CI usage.
Every package, with source and npm links.
Run DocSlurp on your own host with Docker Compose.
How the server, workers, Postgres, object storage and Temporal fit together.
Host, memory and disk needs, and what is measured.
Initialize, check, start and verify a single-host stack.
Edit .env.selfhost: storage, models, limits and secrets.
One versioned JSON file for extraction tuning knobs and model overrides.
Put a TLS reverse proxy in front of the server.
Parser sandbox, malware scanning, secrets and network exposure.
Separate Postgres roles for migrations, the API, workers and backups.
DOCSLURP_PROFILE, the VM-only floor and DOCSLURP_DISABLE kill switches.
Bubblewrap, landlock and Modal: where untrusted parsers run.
What each hosting platform isolates and which sandbox mode to pick.
Optional spatial database setup and migration boundaries.
Validate application ownership without taking ownership of extension objects.
Publish and invalidate tenant-scoped spatial projections.
Logs, upgrades, backups, restore and troubleshooting.
Glossary
Open the explainer →