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"
}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.
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>.
Optional external end-user identifier forwarded by the API gateway.
GraphRAG store name
1Embedding model ID
1LLM model ID used for entity and relation extraction
1Maximum chunk size in characters
100 <= x <= 10000Chunk overlap in characters
0 <= x <= 5000Maximum graph expansion depth during graph-mode queries
1 <= x <= 4Was this page helpful?