Knowledge Bases API

Upload documents (PDFs, Word, plain text, web pages) into per-tenant vector stores. AI agents query these stores at run time to ground their responses. Each knowledge base is an independent index — you’d typically have one per topic (“Product manuals”, “HR policies”, “Refund flow”). Base path: /api/v1/knowledge-bases Authentication: API key (X-API-Key) or session JWT. Upload limits: 10 MB per document. PDF, DOCX, TXT, MD, and HTML supported.

Using the SDKs

import { Orbit } from "@devotel-orbit/node";

const orbit = new Orbit({ apiKey: process.env.ORBIT_API_KEY! });

const res = await orbit.knowledgeBases.list();

The Python SDK doesn’t wrap knowledge bases — its client.request escape hatch creates a base and runs the same semantic search (source-only; vendor it from packages/sdk-python):

from orbit_sdk import OrbitClient

client = OrbitClient.from_api_key("dv_test_sk_YOUR_KEY")
kb = client.request(
    "POST",
    "/knowledge-bases",
    json_body={"name": "Returns policy", "description": "Ground-truth for the agent's refund answers."},
)
kb_id = kb["data"]["id"]
search = client.request(
    "POST",
    f"/knowledge-bases/{kb_id}/search",
    json_body={"query": "How long do I have to return an order?", "limit": 5},
)
# search["data"]["results"] — ranked chunks with content, score, document_name

Returns the typed ApiResponse envelope. See the SDK index at SDK quickstart.

Knowledge bases

Method	Path	Purpose
`GET`	`/api/v1/knowledge-bases`	List knowledge bases
`POST`	`/api/v1/knowledge-bases`	Create a knowledge base
`GET`	`/api/v1/knowledge-bases/{id}`	Get a knowledge base
`PUT`	`/api/v1/knowledge-bases/{id}`	Update name / description
`DELETE`	`/api/v1/knowledge-bases/{id}`	Delete (purges all documents)

Documents

Method	Path	Purpose
`GET`	`/api/v1/knowledge-bases/{id}/documents`	List documents
`POST`	`/api/v1/knowledge-bases/{id}/documents`	Upload (multipart)
`DELETE`	`/api/v1/knowledge-bases/{id}/documents/{docId}`	Remove a document
`POST`	`/api/v1/knowledge-bases/{id}/documents/{docId}/retry`	Retry a failed indexing job
`POST`	`/api/v1/knowledge-bases/{id}/documents/{docId}/approve`	Approve a document pending review
`POST`	`/api/v1/knowledge-bases/{id}/documents/{docId}/reject`	Reject a document pending review
`GET`	`/api/v1/knowledge-bases/{id}/documents/{docId}/versions`	List a document’s version history
`GET`	`/api/v1/knowledge-bases/{id}/documents/{docId}/versions/diff`	Diff two versions of a document
`POST`	`/api/v1/knowledge-bases/{id}/documents/{docId}/rollback`	Restore a retained earlier version
`PATCH`	`/api/v1/knowledge-bases/{id}/documents/{docId}/publication`	Publish or unpublish a document on the public help center

Indexing happens asynchronously. A document goes through processing → ready (or failed). Poll GET /:id/documents to track status, and re-run a failed job with POST /:id/documents/{docId}/retry.

Upload

Binary files (PDF, DOCX, images — OCR-extracted) go up as multipart/form-data: send the file bytes plus the name and type fields. Uploading returns 202 immediately because chunking and embedding run after the response ships; the accepted document comes back at processing status.

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -F "file=@manual.pdf" \
  -F "name=Product Manual" \
  -F "type=pdf"

202

{
  "data": {
    "id": "doc_9a1c3e5b7d",
    "knowledge_base_id": "kb_abc",
    "name": "Product Manual",
    "type": "pdf",
    "status": "processing",
    "chunk_count": 42,
    "version": 1,
    "moderation": { "status": "approved", "required_approval": false }
  },
  "meta": {
    "request_id": "req_01H2T4W6YF8E9K3Z0VX5QAB7CJ",
    "timestamp": "2026-09-01T11:41:00.000Z"
  }
}

Poll the list until the status reaches ready (or failed):

curl https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents \
  -H "X-API-Key: dv_live_sk_your_key_here"

200

{
  "data": [
    {
      "id": "doc_9a1c3e5b7d",
      "knowledge_base_id": "kb_abc",
      "name": "Product Manual",
      "type": "pdf",
      "status": "ready",
      "chunk_count": 42,
      "version": 1
    },
    {
      "id": "doc_8b2d4f6c8e",
      "knowledge_base_id": "kb_abc",
      "name": "Refund FAQ",
      "type": "html",
      "status": "failed",
      "error_message": "embedding provider timeout",
      "version": 3
    }
  ],
  "meta": {
    "request_id": "req_01H2T4W9YG0FA4M1VX6TBC8EK",
    "timestamp": "2026-09-01T11:43:00.000Z",
    "pagination": { "has_more": false }
  }
}

Documents that require moderation move through a publish lifecycle: they start as pending, then become approved or rejected. While a document sits in pending its chunks are not retrievable by agents. Approve it with POST /:id/documents/{docId}/approve to promote it to ground-truth and start indexing, or reject it with POST /:id/documents/{docId}/reject to keep it out of retrieval. Both accept an optional body { "notes": "…" } to record a reviewer note on the document, and both require the knowledge:write scope. Approve:

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_9a1c3e5b7d/approve \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "notes": "Reviewed against the 2026-08 returns update." }'

200

{
  "data": {
    "id": "doc_9a1c3e5b7d",
    "knowledge_base_id": "kb_abc",
    "name": "Product Manual",
    "version": 1,
    "moderation": {
      "status": "approved",
      "notes": "Reviewed against the 2026-08 returns update."
    }
  },
  "meta": {
    "request_id": "req_01H2T4X1PF3E9K0ZVX6QCB8DK",
    "timestamp": "2026-09-01T12:10:00.000Z"
  }
}

Reject (same endpoint shape, same response envelope — the moderation.status reads rejected):

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_9a1c3e5b7d/reject \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "notes": "Superseded by the 2026-08 policy revision." }'

200

{
  "data": {
    "id": "doc_9a1c3e5b7d",
    "knowledge_base_id": "kb_abc",
    "name": "Product Manual",
    "version": 1,
    "moderation": {
      "status": "rejected",
      "notes": "Superseded by the 2026-08 policy revision."
    }
  },
  "meta": {
    "request_id": "req_01H2T4X4RG4F9L1ZVY7RDC9EM",
    "timestamp": "2026-09-01T12:12:00.000Z"
  }
}

Every re-upload of a document retains the superseded copy as an immutable snapshot. GET /:id/documents/{docId}/versions returns the current head plus every retained snapshot so you can audit how the RAG ground-truth has changed over time.

curl https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_9a1c3e5b7d/versions \
  -H "X-API-Key: dv_live_sk_your_key_here"

200

{
  "data": {
    "knowledge_base_id": "kb_abc",
    "document_id": "doc_9a1c3e5b7d",
    "version_group_id": "doc_9a1c3e5b7d",
    "current": {
      "version": 2,
      "document_id": "doc_9a1c3e5b7d",
      "name": "Product Manual",
      "type": "pdf",
      "size_bytes": 184320,
      "chunk_count": 42,
      "content_hash": "9f86d081884c7d659a2feaa0c55ad015a3bf4f1b",
      "created_at": "2026-09-01T09:15:00.000Z",
      "is_current": true
    },
    "history": [
      {
        "version": 1,
        "document_id": "doc_9a1c3e5b7d",
        "name": "Product Manual",
        "type": "pdf",
        "size_bytes": 172048,
        "chunk_count": 39,
        "content_hash": "2c26b46b68ffc68ff99b453c1d3045411343d029",
        "created_at": "2026-08-14T14:02:00.000Z",
        "superseded_at": "2026-09-01T09:15:00.000Z",
        "rollback_available": true
      }
    ]
  },
  "meta": {
    "request_id": "req_01H2T4Y2QH5G0M2ZWZ8SED1FN",
    "timestamp": "2026-09-01T12:20:00.000Z"
  }
}

Compare any two retained versions with GET /:id/documents/{docId}/versions/diff?from={n}&to={m} — it returns added / removed / unchanged line counts plus unified-style hunk lines (+ added, - removed, context). A version whose content was not retained (it exceeded the retention size cap) returns 422.

curl "https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_9a1c3e5b7d/versions/diff?from=1&to=2" \
  -H "X-API-Key: dv_live_sk_your_key_here"

200

{
  "data": {
    "knowledge_base_id": "kb_abc",
    "document_id": "doc_9a1c3e5b7d",
    "from_version": 1,
    "to_version": 2,
    "added": 4,
    "removed": 2,
    "unchanged": 61,
    "truncated": false,
    "hunks": [
      " Refund requests are approved in the merchant console.",
      "- Refunds take up to 10 business days.",
      "+ Refunds are processed within 5–7 business days of approval.",
      "+ Enterprise contracts follow the contractual SLA instead."
    ]
  },
  "meta": {
    "request_id": "req_01H2T4Y6RJ6H1N3ZX0ATFE2GQ",
    "timestamp": "2026-09-01T12:26:00.000Z"
  }
}

Restore an earlier version with POST /:id/documents/{docId}/rollback (body { "version": n }). Rollback is non-destructive — the target version’s content is re-uploaded as a new head version (the current head is snapshotted into history first), so the operation is fully reversible. It returns 202 with the freshly-minted head document.

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_9a1c3e5b7d/rollback \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "version": 1 }'

202

{
  "data": {
    "id": "doc_9a1c3e5b7d",
    "knowledge_base_id": "kb_abc",
    "name": "Product Manual",
    "type": "pdf",
    "status": "processing",
    "chunk_count": 39,
    "version": 3
  },
  "meta": {
    "request_id": "req_01H2T5A2TN8K4Q7BYP3RVT5HS",
    "timestamp": "2026-09-01T12:31:00.000Z"
  }
}

Public help-center publication

Publish a document to your public help center with PATCH /:id/documents/{docId}/publication. This toggles whether a single document is exposed on the public help surface, independent of its indexing status for agents.

Field	Type	Description
`is_public`	boolean	Required. `true` exposes the document on the public help center; `false` removes it.
`slug`	string	URL segment the public page routes by. Lowercase letters, digits, and hyphens only (max 200 chars). Required when `is_public` is `true` — the public surface cannot resolve a page without one.
`summary`	string	Optional public-facing summary (max 2000 chars).

The PATCH verb lets the operator UI flip publication with a partial body without re-stating the slug on every change. This is a write action — it requires the knowledge:write scope and an admin, owner, or developer seat, and both publishing and unpublishing are audit-logged, because setting is_public=true exposes the article to the open web. It returns the updated document.

curl -X PATCH https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/documents/doc_123/publication \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "is_public": true, "slug": "international-refunds", "summary": "How refunds work for international orders." }'

200

{
  "data": {
    "id": "doc_123",
    "knowledge_base_id": "kb_abc",
    "name": "Refund FAQ",
    "is_public": true,
    "slug": "international-refunds",
    "summary": "How refunds work for international orders."
  },
  "meta": {
    "request_id": "req_01H2T6B4PQ2L7R3DYT6XWB9KU",
    "timestamp": "2026-09-01T12:45:00.000Z"
  }
}

Freshness

Method	Path	Purpose
`GET`	`/api/v1/knowledge-bases/{id}/staleness`	Freshness scorecard across all documents

Stale ground-truth is a leading cause of wrong agent answers. GET /:id/staleness scans every document in a knowledge base and classifies each one by age into a fresh, stale, or critical bucket, so you can find and re-verify outdated content before agents cite it. A document’s age is measured from its last operator verification (last_verified_at) if present, otherwise its last update (updated_at). A document is stale once its age reaches the threshold, critical once it reaches twice the threshold, and fresh below it. A document with no verifiable timestamp is reported as critical. The default threshold is 90 days; override it for one call with ?default_threshold_days={n} (1–3650). A per-document threshold, when set, always takes precedence over the default. The response is a scorecard:

Field	Description
`knowledge_base_id`	The scanned knowledge base.
`totals.fresh` / `totals.stale` / `totals.critical`	Document counts per bucket.
`totals.documents_scanned`	Total documents classified.
`totals.never_verified`	Documents never operator-verified.
`attention_required`	Documents not in the `fresh` bucket, oldest-first. Each entry carries `id`, `name`, `type`, `status`, `bucket`, `age_days`, `threshold_days`, `last_verified_at`, `last_cited_at`, and `updated_at`.
`default_threshold_days`	The threshold applied to documents without a per-document override.
`scanned_at`	When the scan ran (ISO-8601).

curl https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/staleness?default_threshold_days=30 \
  -H "X-API-Key: dv_live_sk_your_key_here"

200

{
  "data": {
    "knowledge_base_id": "kb_abc",
    "totals": {
      "fresh": 41,
      "stale": 3,
      "critical": 2,
      "documents_scanned": 46,
      "never_verified": 12
    },
    "attention_required": [
      {
        "id": "doc_2b7c91e",
        "name": "Legacy shipping zones",
        "type": "pdf",
        "status": "ready",
        "bucket": "critical",
        "age_days": 214,
        "threshold_days": 30,
        "last_verified_at": null,
        "last_cited_at": "2026-08-31T10:02:00.000Z",
        "updated_at": "2026-02-01T09:40:00.000Z"
      },
      {
        "id": "doc_9a1c3e5b7d",
        "name": "Refund FAQ",
        "type": "html",
        "status": "ready",
        "bucket": "stale",
        "age_days": 34,
        "threshold_days": 30,
        "last_verified_at": null,
        "last_cited_at": "2026-08-30T18:22:00.000Z",
        "updated_at": "2026-07-28T15:04:00.000Z"
      }
    ],
    "default_threshold_days": 30,
    "scanned_at": "2026-09-01T12:50:00.000Z"
  },
  "meta": {
    "request_id": "req_01H2T7C1YU5N9W4FS0KRD2MN",
    "timestamp": "2026-09-01T12:50:00.000Z"
  }
}

Connectors

A connector binds a knowledge base to an external content source (Notion, Confluence, Google Drive, SharePoint, or Zendesk) and keeps it in sync.

Connector management

Method	Path	Purpose
`GET`	`/api/v1/knowledge-bases/{id}/connectors`	List a knowledge base’s connectors
`POST`	`/api/v1/knowledge-bases/{id}/connectors`	Add a connector to a knowledge base
`PATCH`	`/api/v1/knowledge-bases/{id}/connectors/{connectorId}`	Update a connector
`DELETE`	`/api/v1/knowledge-bases/{id}/connectors/{connectorId}`	Remove a connector
`POST`	`/api/v1/knowledge-bases/{id}/connectors/{connectorId}/sync`	Trigger an immediate sync for a connector

Listing connectors needs knowledge:read. Adding, updating, deleting, and syncing a connector each require knowledge:write (admin, owner, or developer seat), since they bind a knowledge base to — or refresh it from — an external source. POST /:id/connectors/{connectorId}/sync runs the connector’s sync immediately instead of waiting for the next scheduled refresh. Create a connector:

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/connectors \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "provider": "google_drive", "display_name": "Support playbooks", "sync_schedule": "daily" }'

201

{
  "data": {
    "id": "kbc_4f2e91ab",
    "provider": "google_drive",
    "connection_id": "org_7p3q8t",
    "display_name": "Support playbooks",
    "scope": {},
    "sync_schedule": "daily",
    "enabled": true,
    "status": "idle",
    "last_synced_at": null,
    "drift_status": "unknown",
    "created_at": "2026-09-01T12:55:00.000Z",
    "updated_at": "2026-09-01T12:55:00.000Z"
  },
  "meta": {
    "request_id": "req_01H2T8D3BX6R0X2KT1YQE4PS",
    "timestamp": "2026-09-01T12:55:00.000Z"
  }
}

Trigger an immediate sync (the returned connector flips to queued and the drain worker picks it up):

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/connectors/kbc_4f2e91ab/sync \
  -H "X-API-Key: dv_live_sk_your_key_here"

202

{
  "data": {
    "id": "kbc_4f2e91ab",
    "provider": "google_drive",
    "status": "queued"
  },
  "meta": {
    "request_id": "req_01H2T9E6GZ2S3B5MU3ZSF7RV",
    "timestamp": "2026-09-01T12:56:00.000Z"
  }
}

Drift report

Method	Path	Purpose
`GET`	`/api/v1/knowledge-bases/{id}/connector-drift-report`	Content-drift scorecard for source connectors

When a knowledge base syncs from external sources, content can drift from the cached copy your agents ground on. GET /:id/connector-drift-report reports which sources have diverged since their last successful sync, so you can trigger a refresh before agents answer from stale content.

curl https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/connector-drift-report \
  -H "X-API-Key: dv_live_sk_your_key_here"

200

{
  "data": {
    "knowledge_base_id": "kb_abc",
    "detection_active": true,
    "totals": {
      "connectors": 2,
      "in_sync": 1,
      "drifted": 1,
      "unknown": 0
    },
    "drifted": [
      {
        "id": "kbc_8j5c1d",
        "provider": "confluence",
        "display_name": "Engineering runbooks",
        "enabled": true,
        "auto_refresh_on_drift": false,
        "drift_status": "drifted",
        "drift_detected_at": "2026-08-30T18:22:00.000Z",
        "last_drift_checked_at": "2026-09-01T12:00:00.000Z",
        "last_synced_at": "2026-08-28T12:00:00.000Z"
      }
    ],
    "connectors": [
      {
        "id": "kbc_8j5c1d",
        "provider": "confluence",
        "display_name": "Engineering runbooks",
        "enabled": true,
        "auto_refresh_on_drift": false,
        "drift_status": "drifted",
        "drift_detected_at": "2026-08-30T18:22:00.000Z",
        "last_drift_checked_at": "2026-09-01T12:00:00.000Z",
        "last_synced_at": "2026-08-28T12:00:00.000Z"
      },
      {
        "id": "kbc_4f2e91ab",
        "provider": "google_drive",
        "display_name": "Support playbooks",
        "enabled": true,
        "auto_refresh_on_drift": true,
        "drift_status": "in_sync",
        "drift_detected_at": null,
        "last_drift_checked_at": "2026-09-01T11:00:00.000Z",
        "last_synced_at": "2026-09-01T11:05:00.000Z"
      }
    ]
  },
  "meta": {
    "request_id": "req_01H2TAF9IV4T6D8NX6PVD9TX",
    "timestamp": "2026-09-01T12:58:00.000Z"
  }
}

Treat the report as meaningful only once detection_active is true — before the worker has run a first drift check, every connector reads unknown and the zero-drift totals are not a clean bill.

Search

Method	Path	Purpose
`POST`	`/api/v1/knowledge-bases/{id}/search`	Semantic search across documents
`GET`	`/api/v1/knowledge-bases/{id}/search-config`	Read the retrieval re-ranking config
`PUT`	`/api/v1/knowledge-bases/{id}/search-config`	Replace the retrieval re-ranking config

curl -X POST https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/search \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "query": "How do refunds work for international orders?", "limit": 4 }'

200

{
  "data": {
    "query": "How do refunds work for international orders?",
    "knowledge_base_id": "kb_abc",
    "results": [
      {
        "content": "International refunds are issued in the original transaction currency once the return clears customs.",
        "score": 0.87,
        "documentId": "doc_9a1c3e5b7d",
        "document_name": "Refund FAQ",
        "knowledge_base_id": "kb_abc",
        "chunkIndex": 2
      },
      {
        "content": "Cross-border refund timelines depend on the destination carrier and the receiving bank.",
        "score": 0.79,
        "documentId": "doc_8b2d4f6c8e",
        "document_name": "Shipping handbook",
        "knowledge_base_id": "kb_abc",
        "chunkIndex": 5
      }
    ]
  },
  "meta": {
    "request_id": "req_01H2TBH2OW1U9E1PZ8QWE2UZ",
    "timestamp": "2026-09-01T13:05:00.000Z"
  }
}

Re-ranking configuration

Each knowledge base carries a re-ranking config that controls how retrieved chunks are scored and filtered before they ground an agent answer. The config applies to both the agent retrieval path and the POST /:id/search endpoint for that knowledge base. GET /api/v1/knowledge-bases/{id}/search-config returns the current config. Reading requires the knowledge:read scope. PUT /api/v1/knowledge-bases/{id}/search-config replaces it. Every field has a no-op default, so a PUT with {} resets the knowledge base to legacy raw-similarity ordering. Writing requires the knowledge:write scope and an owner, admin, or developer role.

Field	Type	Default	Range	Effect
`min_score`	number	`0`	0–1	Drop chunks whose raw vector similarity is below this floor.
`recency_boost`	number	`0`	0–5	Recency multiplier strength. `0` disables it; fresher documents are boosted up to ×(1 + `recency_boost`).
`recency_half_life_days`	number	`30`	1–3650	Half-life (in days) of the recency decay applied by `recency_boost`.
`source_weights`	object	`{}`	values 0–20	Map of source label → score multiplier. Keys are matched case-insensitively.
`include_categories`	string[]	`[]`	≤ 200 entries	Allow-list of categories. Empty allows all.
`exclude_categories`	string[]	`[]`	≤ 200 entries	Deny-list of categories.

curl -X PUT https://api.orbit.devotel.io/api/v1/knowledge-bases/kb_abc/search-config \
  -H "X-API-Key: dv_live_sk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "min_score": 0.6,
        "recency_boost": 1.5,
        "recency_half_life_days": 14,
        "source_weights": { "product-manual": 2, "community-forum": 0.5 },
        "include_categories": ["refunds", "shipping"],
        "exclude_categories": ["internal"]
      }'

200

{
  "data": {
    "min_score": 0.6,
    "recency_boost": 1.5,
    "recency_half_life_days": 14,
    "source_weights": { "product-manual": 2, "community-forum": 0.5 },
    "include_categories": ["refunds", "shipping"],
    "exclude_categories": ["internal"]
  },
  "meta": {
    "request_id": "req_01H2TCJ5RY2V0F4QA9RTF4XB",
    "timestamp": "2026-09-01T13:07:00.000Z"
  }
}

Retrieval tuning (operator)

When an AI agent grounds a reply, the executor retrieves KB chunks for that turn (see AI Agents API). Two platform environment variables control how many chunks each agent turn retrieves and how aggressively low-relevance chunks are filtered. They are platform-wide defaults set by the operator (not per-request), and matter most for tenants with noisy knowledge bases:

Variable	Default	Range	Effect
`DEVOTEL_KB_TOP_K`	`5`	1–50	Chunks retrieved per agent turn. Bigger = more context but more tokens billed per turn; smaller = tighter signal and faster turns.
`DEVOTEL_KB_SCORE_THRESHOLD`	`0.7`	0–1	Cosine-similarity cutoff; chunks scoring below this are dropped. Raise it to suppress weakly-related noise; lower it if relevant chunks are being filtered out.

These tune the agent retrieval path only. The POST /api/v1/knowledge-bases/{id}/search endpoint above takes its own per-request limit and is unaffected by these variables.

API Reference

All Endpoints

Knowledge Bases API: vector search for AI agent RAG

Knowledge Bases API

Using the SDKs

Knowledge bases

Documents

Upload

Public help-center publication

Freshness

Connectors

Connector management

Drift report

Search

Re-ranking configuration

Retrieval tuning (operator)

See also

​Knowledge Bases API

​Using the SDKs

​Knowledge bases

​Documents

​Upload

​Public help-center publication

​Freshness

​Connectors

​Connector management

​Drift report

​Search

​Re-ranking configuration

​Retrieval tuning (operator)

​See also

Knowledge Bases API

Using the SDKs

Knowledge bases

Documents

Upload

Public help-center publication

Freshness

Connectors

Connector management

Drift report

Search

Re-ranking configuration

Retrieval tuning (operator)

See also