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

v0.2.0 — Sessions, Knowledge Graph, Entities & Namespaces

Version 0.2.0 adds four new classes for advanced memory management. All are importable from llama_index_dakera.

Session management

Group related memories into sessions. Track which memories were created during a specific agent run.

from llama_index_dakera import DakeraSessionManager

sessions = DakeraSessionManager(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="my-agent",
)

# Use as a context manager
with sessions.start(metadata={"task": "research"}) as session:
    # Run your agent — all memories are grouped under this session
    response = agent.chat("Research AI memory architectures")

# List active sessions
active = sessions.list(active_only=True)

# Get memories from a specific session
memories = sessions.memories(session_id=session.id)

Knowledge graph

Build and query a knowledge graph from your agent's stored memories.

from llama_index_dakera import DakeraKnowledgeGraph

kg = DakeraKnowledgeGraph(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="my-agent",
)

# Build the graph from stored memories
kg.build()

# Query the knowledge graph
results = kg.query(query="What has the agent learned?")

# Find paths between entities
path = kg.find_path(from_id="entity-1", to_id="entity-2")

# Export the full graph
graph = kg.export(format="json")

Entity extraction

Extract named entities from text and link them to memories.

from llama_index_dakera import DakeraEntityExtractor

extractor = DakeraEntityExtractor(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="my-agent",
)

# Extract entities from text
found = extractor.extract(
    text="Alice from Acme Corp discussed the Q4 roadmap.",
    entity_types=["person", "organization"],
)

# Get entities linked to a memory
linked = extractor.memory_entities(memory_id="mem_abc123")

Namespace management

Create and manage vector namespaces for organizing document collections.

from llama_index_dakera import DakeraNamespaceManager

ns = DakeraNamespaceManager(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
)

# Create a namespace
ns.create(name="agent-docs", dimension=1024)

# List all namespaces
all_ns = ns.list_namespaces()

# Get namespace details and stats
info = ns.get(name="agent-docs")
stats = ns.stats(name="agent-docs")

Enhanced DakeraMemoryStore (v0.2.0)

The existing DakeraMemoryStore class gained new parameters in v0.2.0:

New methods: hybrid_search(query, top_k) for combined BM25 + vector search, batch_get(queries) for parallel queries, and batch_delete(memory_ids) for bulk removal.

Related integrations

Links

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

Frequently Asked Questions