LlamaIndex Integration

pip install llama-index-core engram-subnet

from llama_index.core import VectorStoreIndex, Document
from llama_index.core.storage.storage_context import StorageContext
from engram.sdk.llama_index import EngramVectorStore
store = EngramVectorStore(miner_url="http://127.0.0.1:8091")
storage_context = StorageContext.from_defaults(vector_store=store)
documents = [
    Document(text="Bittensor is a decentralised ML network."),
    Document(text="TAO tokens reward miners and validators."),
    Document(text="Engram stores embeddings on Bittensor."),
]
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
)

query_engine = index.as_query_engine()
response = query_engine.query("How does Bittensor distribute rewards?")
print(response)
# Retrieve without generating
retriever = index.as_retriever(similarity_top_k=5)
nodes = retriever.retrieve("TAO tokenomics")