Skip to main content
POST
/
api
/
v1
/
search
/
graphrag
/
stores
Python (SDK)
from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.search.graphrag.create_graph_rag_store(store_name="vendor_network", embedding_model="auto", extraction_model="auto", chunk_size=800, chunk_overlap=120, max_hops=2)

    # Handle response
    print(res)
{
  "message": "GraphRAG store created successfully",
  "store_name": "vendor_network"
}

Documentation Index

Fetch the complete documentation index at: https://docs.mka1.com/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Headers

​
X-On-Behalf-Of
string

Optional external end-user identifier forwarded by the API gateway.

Body

application/json
​
store_name
string
required

GraphRAG store name

Minimum string length: 1
​
embedding_model
string
required

Embedding model ID

Minimum string length: 1
​
extraction_model
string
required

LLM model ID used for entity and relation extraction

Minimum string length: 1
​
chunk_size
integer
default:800

Maximum chunk size in characters

Required range: 100 <= x <= 10000
​
chunk_overlap
integer
default:120

Chunk overlap in characters

Required range: 0 <= x <= 5000
​
max_hops
integer
default:2

Maximum graph expansion depth during graph-mode queries

Required range: 1 <= x <= 4

Response

Successful Response

​
store_name
string
required
​
message
string
required