{"name":"knowledge","stage":"ga","description":"Package knowledge is your team's wiki and your agents' memory, searchable by meaning.","operations":[{"operationId":"get_knowledge_connectors","method":"GET","href":"/v1/knowledge/connectors","summary":"Returns every supported knowledge connector with THIS org's connection state and the REAL number of documents each has ingested into the org's store."},{"operationId":"get_knowledge_connectors_catalog","method":"GET","href":"/v1/knowledge/connectors/catalog","summary":"Returns the ONE catalog of everything a caller can connect: every first-party connector and every long-tail one, in a single list sorted by provider."},{"operationId":"delete_knowledge_connectors_by_provider","method":"DELETE","href":"/v1/knowledge/connectors/{provider}","summary":"Revokes a connection: it tombstones the stored credential so a later sync cannot reuse it, removes this provider's passages from the org's store, and marks the connector disconnected."},{"operationId":"get_knowledge_connectors_by_provider_callback","method":"GET","href":"/v1/knowledge/connectors/{provider}/callback","summary":"CompleteConnectorOAuth finishes an OAuth connection: it exchanges the provider's code for a token, seals that token in KMS, and records the connection."},{"operationId":"get_knowledge_connectors_by_provider_connect","method":"GET","href":"/v1/knowledge/connectors/{provider}/connect","summary":"StartConnectorOAuth returns the provider authorize URL the console opens to connect this org's account."},{"operationId":"post_knowledge_connectors_by_provider_sync","method":"POST","href":"/v1/knowledge/connectors/{provider}/sync","summary":"Pulls the provider's documents for the caller's org and files them as knowledge sources, which the store's own hook then indexes — so a synced document is retrievable exactly like a hand-written page."},{"operationId":"get_knowledge_files","method":"GET","href":"/v1/knowledge/files","summary":"Answers the caller's org files, most recently changed first, each with its status and stage — optionally only those in one bucket, which is how Drive shows a folder's files with their index state."},{"operationId":"post_knowledge_files","method":"POST","href":"/v1/knowledge/files","summary":"Makes an object in one of the caller's org buckets a workspace file."},{"operationId":"post_knowledge_files_retrieve","method":"POST","href":"/v1/knowledge/files/retrieve","summary":"Grounds an answer in the caller's org files, table of contents first: candidate documents are found by searching their passages; a model reads their tables of contents — titles and one-line summaries — and picks the sections the answer is in; hybrid search drills into the passages of those sections; and the graph expands to the sections they link to or name the same entities as, in any file of the workspace."},{"operationId":"post_knowledge_files_search","method":"POST","href":"/v1/knowledge/files/search","summary":"Answers the passages of the caller's org files that match a query, each citing its file › section › paragraph: the search behind Drive's box, and the first step an agent takes across a workspace."},{"operationId":"delete_knowledge_files_by_id","method":"DELETE","href":"/v1/knowledge/files/{id}","summary":"Removes one of the caller's org files from the index — its table of contents, passages, full-text rows, mentions and links — and its record."},{"operationId":"get_knowledge_files_by_id","method":"GET","href":"/v1/knowledge/files/{id}","summary":"Answers one of the caller's org files: what it is, where its bytes are, and how far its ingest has got."},{"operationId":"get_knowledge_files_by_id_graph","method":"GET","href":"/v1/knowledge/files/{id}/graph","summary":"Answers one of the caller's org files' place in the org's graph: the files it links to and is linked from (a hyperlink, a citation by name), the files that name the same entities, and the entities it names."},{"operationId":"get_knowledge_files_by_id_sections_by_section","method":"GET","href":"/v1/knowledge/files/{id}/sections/{section}","summary":"Answers one section of one of the caller's org files: its own text, its subsections, the sections it links to or shares entities with — in this file or another — and the entities it names."},{"operationId":"get_knowledge_files_by_id_toc","method":"GET","href":"/v1/knowledge/files/{id}/toc","summary":"Answers one of the caller's org files' table of contents: every section in document order with its depth, its parent and a one-line summary."},{"operationId":"get_knowledge_graph","method":"GET","href":"/v1/knowledge/graph","summary":"Returns the caller org's knowledge as a node/edge graph shaped for a force-directed renderer: pages, memories and synced sources as nodes; the page parent tree, the wikilinks between pages, and each source's connector provenance as edges."},{"operationId":"post_knowledge_import","method":"POST","href":"/v1/knowledge/import","summary":"Import an Obsidian, Notion, Roam or Evernote export into the org's knowledge base"},{"operationId":"post_knowledge_reindex","method":"POST","href":"/v1/knowledge/reindex","summary":"Rebuilds the caller org's retrieval from its documents: every passage is removed, and every page, memory and source is cut into passages and embedded again with the configured model; the lexical index is reconciled to the same documents."},{"operationId":"post_knowledge_search","method":"POST","href":"/v1/knowledge/search","summary":"Runs a hybrid search over the caller org's own knowledge — its wiki pages, its agent memories and everything its connectors have synced."}],"_links":{"describedby":{"href":"/v1/openapi.json?capability=knowledge"},"self":{"href":"/v1/knowledge"},"up":{"href":"/v1"}}}