Create ingest

Unified RAG ingest: parse + chunk + embed documents and pipe them to BOTH Hanzo Vector (semantic) AND Hanzo Search (keyword) under the tenant index {owner}-{store}-docs — the same index /v1/chat retrieval reads.

POST /v1/ai/rag/ingest

Addresshttps://api.hanzo.ai/v1/ai/rag/ingest
MethodPOST
Operationpost_ai_rag_ingest
AuthAuthorization: Bearer $HANZO_API_KEY

Unified RAG ingest: parse + chunk + embed documents and pipe them to BOTH Hanzo Vector (semantic) AND Hanzo Search (keyword) under the tenant index {owner}-{store}-docs — the same index /v1/chat retrieval reads. The source is pluggable: "upload" (inline files/documents), "github" (index a repo), "crawl" (web), or "s3" (the store's object-storage space). The owner is bound to the authenticated principal; the client-supplied owner is never trusted.

Request

The document declares no body for POST /v1/ai/rag/ingest. The handler is typed in cloud but its shape is not yet emitted, so the fields are not listed here — ask MCP's describe for post_ai_rag_ingest, which answers from the running route.

Response

StatusBodyMeaning
200Success.
401—No credential, or one this service does not accept.
403—A valid credential that may not do this.

200 body — 14 fields.

FieldInTypeAlwaysDescription
databodyany—The operation's own result.
data2bodyany—A second result the operation defines, when it has one.
msgbodystringyesEmpty on success, the reason on failure.
statusbodystringyesOne of ok, error.
data.asyncbodyboolean—
data.documentsIndexedbodyinteger—
data.errorsbodystring[]—
data.filesIngestedbodyinteger—
data.filesSkippedbodyinteger—
data.indexNamebodystring—
data.skippedbodystring[]—
data.sourcebodystring—
data.storebodystring—
data.workflowIdbodystring—

Failure carries the platform error shape — see Errors.

Examples

hanzo ai rag ingest
import { Configuration, AiApi } from 'hanzoai';

const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postAiRagIngest();
from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AiApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AiApi(client).post_ai_rag_ingest()
cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.AiAPI.PostAiRagIngest(context.Background()).Execute()
if err != nil {
	return err
}
use hanzo_client::apis::{configuration::Configuration, ai_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = ai_api::post_ai_rag_ingest(&cfg, Default::default()).await?;
import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AiApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new AiApi(client).postAiRagIngest();
curl -X POST https://api.hanzo.ai/v1/ai/rag/ingest \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP declares no tool for ai — tools/list on https://api.hanzo.ai/v1/mcp names the products it does reach. Use HTTP or an SDK.


AI API · All Hanzo APIs · Interactive reference

Was this page useful?