Filter Raw Embeddings

Retrieve embeddings for specific chunk IDs. Use this when you already know the chunk IDs and need their corresponding embeddings.

POST /embeddings/filter-raw-embeddings

Error

A valid request URL is required to generate request examples

200

[
  {
    "source_id": "CortexDoc1234",
    "embedding": {
      "chunk_id": "<chunk_id>",
      "embedding": []
    },
    "score": 1,
    "distance": 1,
    "metadata": {}
  }
]

Hit the Try it button to try this API now in our playground. It’s the best way to check the full request and response in one place, customize your parameters, and generate ready-to-use code snippets.

Examples

API Request

curl -X 'POST' \
'https://api.usecortex.ai/embeddings/filter-raw-embeddings' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"tenant_id": "string",
"sub_tenant_id": "string",
"source_id": "string",
"chunk_ids": [
"string"
],
"output_fields": [
"string"
],
"limit": 100
}'

TypeScript

const embeddings = await client.embeddings.getByChunkIds({
  tenant_id: "tenant_1234",
  sub_tenant_id: "sub_tenant_4567",
  chunk_ids: ["chunk_001", "chunk_002", "chunk_003"]
});

Python (Sync)

# Async usage is similar, just use async_client and await
embeddings = client.embeddings.get_by_chunk_ids(
    tenant_id="tenant_1234",
    sub_tenant_id="sub_tenant_4567",
    chunk_ids=["chunk_001", "chunk_002", "chunk_003"]
)

Retrieve embedding vectors for specific chunk IDs that you previously obtained from uploading embeddings or searching.

Requirements

• chunk_ids: Array of valid chunk ID strings (cannot be empty)
• tenant_id: Required for multi-tenancy support
• sub_tenant_id: Optional, defaults to tenant_id if not provided

Response Details

• embeddings: Dictionary mapping chunk IDs to their embedding vectors
• not_found_chunk_ids: Array of chunk IDs that were not found in the system

Sample Response

{
  "embeddings": {
    "CortexEmbeddings123_0": [
      21.0,
      22.0,
      23.0,
      24.0,
      25.0,
      26.0
    ],
    "CortexEmbeddings123_1": [
      20.100000381469727,
      20.200000762939453,
      20.299999237060547,
      20.399999618530273,
      20.5,
      20.600000381469727
    ],
    "CortexEmbeddings456_0": [
      1.5,
      2.5,
      8.5,
      8.5,
      8.5,
      6.5
    ]
  },
  "not_found_chunk_ids": [
    "CortexEmbeddings789_2"
  ]
}

Error Responses

All endpoints return consistent error responses following the standard format. For detailed error information, see our Error Responses documentation.

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

tenant_id · string · required

Unique identifier for the tenant/organization

Example:

"tenant_1234"

sub_tenant_id · string · required

Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.

Example:

"sub_tenant_4567"

source_id · string | null

Optional source ID to filter by (mutually exclusive with chunk_ids)

Example:

"CortexDoc1234"

chunk_ids · string[] | null

Optional list of chunk IDs to filter by (mutually exclusive with source_id)

Example:

[
  "CortexEmbeddings123_0",
  "CortexEmbeddings123_1"
]

output_fields · string[] | null

Optional list of fields to return in results (default: chunk_id, source_id, metadata)

limit · integer · default: 100

Maximum number of results to return

Required range: 1 <= x <= 10000

Example:

1

Response

200

application/json

Successful Response

source_id · string · required

Source identifier

Example:

"CortexDoc1234"

embedding · RawEmbeddingVector · object | null

Embedding payload with chunk id and vector (if set)

Show child attributes

score · number · default: 0

Similarity score

Example:

1

distance · number · default: 0

Vector distance

Example:

1

metadata · Metadata · object | null

Metadata associated with the embedding