Context Layer - Prometheux

The Context Layer is the AI agent’s knowledge base. It stores context notes — discrete facts, observations, and document chunks — that the agent retrieves at inference time to reason over your data. Notes are scoped either global (workspace-wide) or project (tied to a single project via a scope_id).

This scope model (global | project + scope_id) is distinct from the user/organization scope used by the rest of the API. A note scoped to project with a given scope_id is invisible to the agent when it operates on a different project, even within the same organization.

All paths are relative to the base URL and require authentication. All responses use the standard envelope.

The platform also ships an onboarding interview wizard that populates context notes interactively. Those endpoints (GET /knowledge/interview/template, POST /knowledge/interview) are UI-internal and not documented here.

Context notes

List notes

Return all context notes for the given scope, optionally filtered by kind.

GET /knowledge/context

Parameter	In	Required	Default	Description
`scope`	query	yes	—	`global` or `project`.
`scope_id`	query	no	—	Project UUID. Required when `scope` is `project`.
`kinds`	query	no	—	Comma-separated list of note kinds to include (e.g. `fact,observation`). Omit to return all kinds.

curl "$BASE_URL/knowledge/context?scope=project&scope_id=$PROJECT_ID" \
  -H "Authorization: Bearer $TOKEN"

{
  "status": "success",
  "message": "Context notes listed",
  "data": [
    {
      "id": "note_a1b2...",
      "scope": "project",
      "scope_id": "proj_123",
      "kind": "fact",
      "text": "The `orders` table has a composite primary key on (order_id, tenant_id).",
      "source": "user",
      "pinned": false,
      "superseded_by": null,
      "created_at": "2026-06-20T09:15:00+00:00"
    }
  ]
}

Create a note

Write a single context note into the knowledge base.

POST /knowledge/context

Parameter	In	Required	Default	Description
`scope`	body	yes	—	`global` or `project`.
`scope_id`	body	no	—	Project UUID. Required when `scope` is `project`.
`kind`	body	yes	—	Free-form note type, e.g. `fact`, `observation`, `constraint`, `document_chunk`.
`text`	body	yes	—	The note content.
`source`	body	no	`"user"`	Originator label: `user`, `agent`, `auto_seed`, etc.
`pinned`	body	no	`false`	Pinned notes are always included in retrieval regardless of relevance score.
`supersedes`	body	no	`[]`	List of note IDs that this note replaces. Superseded notes are excluded from future retrieval.

curl -X POST "$BASE_URL/knowledge/context" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "scope": "project",
    "scope_id": "proj_123",
    "kind": "fact",
    "text": "Revenue figures are always in USD unless the currency column is populated.",
    "pinned": true
  }'

{
  "status": "success",
  "message": "Context note created",
  "data": {
    "id": "note_c3d4...",
    "scope": "project",
    "scope_id": "proj_123",
    "kind": "fact",
    "text": "Revenue figures are always in USD unless the currency column is populated.",
    "source": "user",
    "pinned": true,
    "superseded_by": null,
    "created_at": "2026-06-25T11:00:00+00:00"
  }
}

Get a note

Retrieve a single context note by ID.

GET /knowledge/context/{note_id}

Parameter	In	Required	Default	Description
`note_id`	path	yes	—	Context note UUID.

curl "$BASE_URL/knowledge/context/note_c3d4..." \
  -H "Authorization: Bearer $TOKEN"

{
  "status": "success",
  "message": "Context note retrieved",
  "data": {
    "id": "note_c3d4...",
    "scope": "project",
    "scope_id": "proj_123",
    "kind": "fact",
    "text": "Revenue figures are always in USD unless the currency column is populated.",
    "source": "user",
    "pinned": true,
    "superseded_by": null,
    "created_at": "2026-06-25T11:00:00+00:00"
  }
}

Update a note

Partially update a context note. Only fields present in the request body are modified. Omitting scope or scope_id entirely leaves those fields unchanged; passing them explicitly (even as null) overwrites them.

PATCH /knowledge/context/{note_id}

Parameter	In	Required	Default	Description
`note_id`	path	yes	—	Context note UUID.
`text`	body	no	—	Replacement note content.
`kind`	body	no	—	Replacement kind label.
`pinned`	body	no	—	`true` or `false`.
`scope`	body	no	—	Move the note to a different scope (`global` or `project`).
`scope_id`	body	no	—	Move the note to a different project. Pass `null` together with `scope: "global"` to clear the project binding.

curl -X PATCH "$BASE_URL/knowledge/context/note_c3d4..." \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "pinned": false, "text": "Revenue figures are in USD (pre-2025) or EUR (2025+)." }'

{
  "status": "success",
  "message": "Context note updated",
  "data": {
    "id": "note_c3d4...",
    "scope": "project",
    "scope_id": "proj_123",
    "kind": "fact",
    "text": "Revenue figures are in USD (pre-2025) or EUR (2025+).",
    "source": "user",
    "pinned": false,
    "superseded_by": null,
    "created_at": "2026-06-25T11:00:00+00:00"
  }
}

Delete a note

Permanently delete a context note.

DELETE /knowledge/context/{note_id}

Parameter	In	Required	Default	Description
`note_id`	path	yes	—	Context note UUID.

curl -X DELETE "$BASE_URL/knowledge/context/note_c3d4..." \
  -H "Authorization: Bearer $TOKEN"

{
  "status": "success",
  "message": "Context note deleted",
  "data": null
}

Search

Semantic search

Run a vector similarity search over context notes. Returns notes ranked by semantic relevance to the query string, each annotated with a similarity score.

POST /knowledge/context/search

Parameter	In	Required	Default	Description
`scope`	query	yes	—	`global` or `project`.
`scope_id`	query	no	—	Project UUID. Required when `scope` is `project`.
`kinds`	query	no	—	Comma-separated kind filter.
`top_k`	query	no	`10`	Maximum number of results to return (1–100).
`query`	body	yes	—	The natural-language search string to embed and match against.

curl -X POST "$BASE_URL/knowledge/context/search?scope=project&scope_id=$PROJECT_ID&top_k=5" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "query": "currency handling for revenue columns" }'

{
  "status": "success",
  "message": "Context notes searched",
  "data": [
    {
      "id": "note_c3d4...",
      "kind": "fact",
      "text": "Revenue figures are in USD (pre-2025) or EUR (2025+).",
      "score": 0.91,
      "pinned": false,
      "source": "user"
    }
  ]
}

Ingestion

Ingest a file as context

Parse and chunk an already-uploaded file into context notes. The file must first be uploaded via POST /data/files/upload, which returns a disk/<name> path to pass here. The ingestion pipeline extracts text, splits it into chunks, embeds each chunk, and persists them as document_chunk notes tied back to a shared document_id. If the embedding service is unavailable the file is still stored as a single un-vectorized note.

POST /knowledge/context/from-file

Parameter	In	Required	Default	Description
`scope`	body	no	`"global"`	`global` or `project`.
`scope_id`	body	no	—	Project UUID. Required when `scope` is `project`.
`file_path`	body	yes	—	The `disk/<name>` path returned by the file-upload endpoint.

curl -X POST "$BASE_URL/knowledge/context/from-file" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "scope": "project",
    "scope_id": "proj_123",
    "file_path": "disk/data_dictionary_v3.pdf"
  }'

{
  "status": "success",
  "message": "File ingested as context notes",
  "data": {
    "document_id": "doc_e5f6...",
    "filename": "data_dictionary_v3.pdf",
    "chunk_count": 14,
    "persisted": 14,
    "scope": "project",
    "scope_id": "proj_123"
  }
}

Returns 422 Unprocessable Entity when the file is readable but no text can be extracted — the most common cause is a scanned PDF without an OCR layer.

Auto-seed from data sources

Profile connected data sources and automatically write observation notes into the Context Layer. The platform inspects schemas, samples, and statistics for each source and uses the LLM to generate structured observations. This endpoint returns a streaming NDJSON response. Each line is a JSON object with a type field describing the event.

POST /knowledge/auto-seed

Parameter	In	Required	Default	Description
`scope`	body	no	`"project"`	`global` or `project`.
`scope_id`	body	no	—	Project UUID. Required when `scope` is `project`.
`datasource_ids`	body	no	—	Array of data source IDs to profile. Omit to profile all connected sources.

curl -X POST "$BASE_URL/knowledge/auto-seed" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "scope": "project",
    "scope_id": "proj_123",
    "datasource_ids": ["ds_aaa", "ds_bbb"]
  }'

Each NDJSON line follows this shape:

// Source profiling started
{ "type": "source_started", "data": { "datasource_id": "ds_aaa", "name": "prod_warehouse" } }

// A note was written to the Context Layer
{ "type": "note_written", "data": { "note_id": "note_g7h8...", "kind": "observation", "text": "..." } }

// All sources processed
{ "type": "done", "data": { "notes_written": 12 } }

// Error (stream remains open; partial results may have been written)
{ "type": "error", "data": { "error": "Connection to ds_bbb timed out" } }

Project document

Render project document

Return a combined document view for a project: an LLM-generated natural-language summary alongside the full executable Vadalog program assembled from all concepts. The summary is cached and is automatically invalidated when concepts or context notes change. Pass refresh=true to force regeneration regardless of the cache state.

GET /knowledge/project/{project_id}/text

Parameter	In	Required	Default	Description
`project_id`	path	yes	—	The project ID.
`scope`	query	no	`"user"`	Workspace scope of the project.
`refresh`	query	no	`false`	Bypass the summary cache and regenerate unconditionally.

curl "$BASE_URL/knowledge/project/$PROJECT_ID/text?scope=user" \
  -H "Authorization: Bearer $TOKEN"

{
  "status": "success",
  "message": "Project document rendered",
  "data": {
    "summary": "This project computes monthly revenue by region...",
    "vadalog_text": "@input(\"orders\").\n@output(\"revenue_by_region\").\nrevenue_by_region(R, sum<V>) <- orders(_, R, V, _).",
    "cached": true,
    "generated_at": "2026-06-24T08:30:00+00:00"
  }
}

​Context notes

​List notes

​Create a note

​Get a note

​Update a note

​Delete a note

​Search

​Semantic search

​Ingestion

​Ingest a file as context

​Auto-seed from data sources

​Project document

​Render project document

Context notes

List notes

Create a note

Get a note

Update a note

Delete a note

Search

Semantic search

Ingestion

Ingest a file as context

Auto-seed from data sources

Project document

Render project document