> ## Documentation Index > Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt > Use this file to discover all available pages before exploring further. # Get the curation ledger > What the last curate recorded: the per-source hash and timestamp map, artifact edges, corpus groups, the live version pin, delete tombstones, artifact-reclaim intents, and the pointer and glossary resume cursors. Chunk ids are tracked too but not served — an internal retrieval unit. ## OpenAPI ````yaml https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/nexus_data_2026-07.oas.yaml get /contexts/{slug}/curate openapi: 3.0.3 info: title: Nexus API description: > Nexus turns a set of sources into a queryable, self-improving knowledge base. A context is **sources + a manifest**: upload sources, **curate** them into a searchable index, then query it. The manifest, one validated JSON document, defines how the context indexes, retrieves and answers. Curate is explicit — nothing is queryable until you run it. `{slug}` accepts a context's slug or its UUID. Query with `POST /api/query`, one turn per call, and read the answer from `output[].content[].text`; multi-turn conversations are sessions. Tasks are project-owned at `/api/tasks`, not nested under contexts. contact: name: Pinecone Support url: https://support.pinecone.io email: support@pinecone.io license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 version: 2026-07 servers: - url: https://{host}/api description: Your Nexus deployment host variables: host: default: api.example.com description: Host of your Nexus deployment. security: - bearerAuth: [] - apiKey: [] tags: - name: Auth description: Login and identity. - name: Project description: The active Pinecone project and its disclosure state. - name: Contexts description: A context is sources + a manifest. Curate it explicitly before querying. - name: Manifest description: Manifest templates and the per-context manifest. - name: Source Files description: >- Per-context source imports (upload, connector, public repo) and the source file tree. - name: Knowledge description: Read-only browse of curated knowledge (chunks + artifacts). - name: Curation description: Curate workflow trigger, curation ledger, and version-pin primitives. - name: Connectors description: >- Project-level links to external source providers (Box, ...). Linked via OAuth or an API key, then used to import source documents into a context. - name: Query description: >- The unified KnowQL Query API: run a query turn (`/query`), fetch a turn (`/queries/{id}`), inspect its trace, manage feedback, comparison flags, and multi-turn sessions (`/sessions`). - name: Tasks description: >- Top-level, project-owned task records for every workflow (optimize, curate, search, work, explore, profile, import, pack, restore, groom). - name: Task Files description: Read, list, and delete files from live or archived task containers. paths: /contexts/{slug}/curate: get: tags: - Curation summary: Get the curation ledger description: >- What the last curate recorded: the per-source hash and timestamp map, artifact edges, corpus groups, the live version pin, delete tombstones, artifact-reclaim intents, and the pointer and glossary resume cursors. Chunk ids are tracked too but not served — an internal retrieval unit. operationId: get_curation_ledger parameters: - in: path name: slug description: Context slug or UUID. required: true schema: type: string style: simple - in: header name: X-Pinecone-Api-Version description: >- Date-based contract version, echoed back on the same header. Omit for the default (`2026-07`); send `unstable` for the in-development surface. An unrecognized value is rejected with `400 unsupported_api_version`. schema: default: 2026-07 x-enum: - 2026-07 - unstable type: string style: simple responses: '200': description: Curation state content: application/json: schema: $ref: '#/components/schemas/CurationState' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: CurationState: description: What the last curate recorded, and what the next one resumes from. type: object properties: manifest: description: Per-source curate ledger, keyed by source path. type: object additionalProperties: $ref: '#/components/schemas/SourceManifestEntry' edges: description: >- Artifact ids each source contributed an edge to, keyed by source path. type: object additionalProperties: description: Artifact ids this source contributed an edge to. type: array items: description: One artifact id. type: string corpus_groups: description: The source groupings the corpus pass reduced over. type: array items: $ref: '#/components/schemas/CorpusGroup' live_version: description: The index version queries read. type: integer format: int64 versions_stamped: description: >- Whether every index entry carries a version stamp, which is what lets a curate flip versions atomically. type: boolean source_removed: description: Delete tombstones awaiting the next curate, keyed by source path. type: object additionalProperties: $ref: '#/components/schemas/SourceRemoved' redispatch_count: description: >- How many times a curate on this context was killed and redispatched. The checkpointed run resumes rather than restarting. type: integer artifact_reclaim: description: Artifact swaps awaiting the next curate. type: array items: $ref: '#/components/schemas/ArtifactReclaim' source_pointers: description: >- The resume cursor a redispatched curate writes, keyed by source path. `{}` for a context whose curates all ran to completion. type: object additionalProperties: description: Mentions recorded for this source. type: array items: $ref: '#/components/schemas/PointerEntry' source_glossary: description: >- The glossary resume cursor, keyed by source path. `{}` for a context whose curates all ran to completion. type: object additionalProperties: description: Terms read verbatim out of the named file. type: array items: $ref: '#/components/schemas/GlossaryEntry' required: - manifest - edges - corpus_groups - live_version - versions_stamped - source_removed - redispatch_count - artifact_reclaim - source_pointers - source_glossary Error: description: The error envelope every non-2xx response uses. type: object properties: message: description: >- Human-readable explanation. Not stable — branch on `code`, not on this. type: string code: description: >- Stable machine-readable code, present only on errors a client must branch on. x-enum: - unsupported_api_version - preview_not_enabled - preview_file_limit - preview_byte_limit - workspace_host_required - workspace_not_found type: string required: - message SourceManifestEntry: description: >- What curate recorded about one source. The hash is what makes an incremental curate possible — a source whose hash is unchanged is skipped. type: object properties: hash: description: Content hash of the source as curated. type: string curated_at: description: When this source was last curated. type: string format: date-time size: description: Byte size at curate time. type: integer format: int64 mtime: nullable: true description: >- Source modification time at curate time. Null when the store reported none. type: string format: date-time required: - hash - curated_at - size CorpusGroup: description: >- A set of sources the corpus pass treats as one subject, so their mentions reduce into a single artifact. type: object properties: group_key: description: Stable identifier the reduce pass groups on. type: string member_sources: description: Source paths in the group. type: array items: description: One source path in the group. type: string canonical_name: description: The name the group's artifact is written under. type: string membership_hash: description: >- Hash of the membership. A change here means the group must be re-reduced. type: string added_version: description: Index version the group was added in. type: integer format: int64 required: - group_key - member_sources - canonical_name - membership_hash - added_version SourceRemoved: description: >- A deferred whole-source delete tombstone. The source's index entries are dropped on the next curate rather than at delete time. type: object properties: removed_version: description: Index version the delete was recorded against. type: integer format: int64 removed_at: nullable: true description: When the delete was requested. type: string format: date-time required: - removed_version ArtifactReclaim: description: >- An intent to swap one artifact for its replacement, recorded so the old one is dropped only once the new one is live. type: object properties: removed_id: description: The artifact being superseded. type: string added_id: description: The artifact replacing it. type: string version: description: Index version the swap belongs to. type: integer format: int64 required: - removed_id - added_id - version PointerEntry: description: >- One recorded mention — what a single source said about a subject, held until the corpus pass reduces every mention of that subject into one artifact. type: object properties: type: description: Artifact-type name type: string name: description: The subject mentioned. type: string mention: description: What this source says about it. type: string seq: description: Ordinal of the mention within the source. type: integer required: - type - name GlossaryEntry: description: >- One term read verbatim out of a source by a `glossary`-kind artifact type. type: object properties: type: description: Artifact-type name. type: string name: description: The term. type: string clause: description: The source text defining it. type: string required: - type - name - clause securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Session token from `POST /auth/login`, sent as `Authorization: Bearer `. apiKey: type: apiKey in: header name: Api-Key description: Pinecone API key, accepted as an alternative to the bearer token. ````