LlamaIndex Integration

Drop-in LlamaIndex components backed by Dakera — persistent agent memory and server-side vector indexing with no local embedding model.

Quick Start

docker run -d \
  --name dakera \
  -p 3300:3300 \
  -e DAKERA_ROOT_API_KEY=dk-mykey \
  ghcr.io/dakera-ai/dakera:latest

curl http://localhost:3300/health

pip install llamaindex-dakera

from llama_index_dakera import DakeraMemoryStore, DakeraIndexStore

# Agent memory
memory = DakeraMemoryStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="my-agent",
)

# RAG index — server handles embedding
vector_store = DakeraIndexStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="my-docs",
)

DakeraMemoryStore

Persistent conversation memory for LlamaIndex agents. Drop-in replacement for the default in-memory chat store.

ReAct agent with persistent memory

from llama_index.core.agent import ReActAgent
from llama_index.core.memory import ChatMemoryBuffer
from llama_index.llms.openai import OpenAI
from llama_index_dakera import DakeraMemoryStore

store = DakeraMemoryStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="react-agent",
)

memory = ChatMemoryBuffer.from_defaults(
    token_limit=3000,
    chat_store=store,
    chat_store_key="user-1",
)

agent = ReActAgent.from_tools(
    tools=[...],
    llm=OpenAI(model="gpt-4o"),
    memory=memory,
    verbose=True,
)

# First session
response = agent.chat("My project is called NeuralBridge.")

# Later session — memory persists
response = agent.chat("What's the name of my project?")
print(response)  # "Your project is called NeuralBridge."

DakeraMemoryStore options

DakeraIndexStore

Server-side embedded vector store for RAG. Dakera embeds documents on the server — no local model, no OpenAI embeddings API needed.

Indexing documents

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext
from llama_index_dakera import DakeraIndexStore

documents = SimpleDirectoryReader("./docs").load_data()

vector_store = DakeraIndexStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="product-docs",
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
)

query_engine = index.as_query_engine(similarity_top_k=4)
response = query_engine.query("How does the billing work?")
print(response)

Chat over your documents

from llama_index.core.chat_engine import CondensePlusContextChatEngine
from llama_index.core.memory import ChatMemoryBuffer
from llama_index_dakera import DakeraIndexStore, DakeraMemoryStore

vector_store = DakeraIndexStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="product-docs",
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_defaults(storage_context=storage_context)

memory_store = DakeraMemoryStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="doc-chat",
)

chat_engine = CondensePlusContextChatEngine.from_defaults(
    retriever=index.as_retriever(similarity_top_k=4),
    memory=ChatMemoryBuffer.from_defaults(chat_store=memory_store),
)

response = chat_engine.chat("What are the pricing tiers?")
print(response)

DakeraIndexStore options

Related integrations

Links

• GitHub — dakera-llamaindex
• Dakera deploy — Docker Compose setup
• Dakera full documentation
• All integrations