Lochless

By Synoptic Data Ltd.

Get New App Alerts

Open in ChatGPT

Open in Claude

Overview

Every match, not the top 10. Lochless searches your own documents and returns each relevant one, with a quote, its document id and its date. Or it writes a short answer that cites them. Lochless is a hosted text index for teams and their AI agents. You send your documents to your Lochless workspace through its API. Then you ask in plain English, for example "every customer who asked for a refund this quarter", "which contracts auto-renew with under 30 days' notice" or "what did we promise about the SSO rollout". Four read-only tools: - Search documents: every match for a question, page by page, with quotes and sources. - Browse documents: list documents by date. - Read document: open one whole document. - Ask documents: a short written answer that cites its sources as [1], [2], with the quote behind each citation. Each response says how much text was read and whether coverage is complete. You can narrow any question by date or by your own document metadata. Limitations: Lochless reads only the documents already in your connected workspace. It does not search the web, and it cannot add, change or delete documents. You need a Lochless workspace; request access at lochless.io.

Tools

ask_documents

ChatGPT

Answer a question from your own documents (your knowledge base), citing its sources. Reads every matching document across all dates unless from/to narrow it. Returns a short written answer that cites its sources as [1], [2], and the evidence: each cited quote with its document id, metadata and score. Use search_documents instead when you want every match rather than an answer. Takes the same from, to, metadata, dry_run and read_limit_usd as search_documents; the limit includes the answer fee. coverage says how many matching documents the answer read.

browse_documents

ChatGPT

List your own documents (your knowledge base) by date, newest first unless order=asc. No query needed. Each result has its document id, connection id, title, date, metadata and the start of its text. Narrow with from/to (the document's timestamp) and metadata (exact match; a list = any of). Returns results, total_results and next_cursor: pass it back as cursor for the next page. Free: browsing never spends your balance.

read_document

ChatGPT

Read one whole document from your own documents (your knowledge base), by the document_id and connection_id of a search or browse result. Returns its full text, title, date and metadata. A long document comes in parts: when the result has next_content_offset, call again with content_offset set to it. Free: reading never spends your balance.

search_documents

ChatGPT

Search your own documents (your knowledge base) and get every match, not just the top few: a quote from each matching document, with its document id, connection id and date. Returns results, total_results (across all pages), tokens_scanned and next_cursor: pass it back as cursor, with the same query, for the next page. Next pages are free. Narrow with from/to (the document's timestamp) and metadata (exact match; a list = any of). dry_run=true returns documents_matched, tokens_to_scan and the price without searching, for free. read_limit_usd caps what one call may spend: over it, the best-matching documents are read first, and coverage says how many were read of all that match. When coverage.complete is false, pass continue_cursor back to read the next ones.