langchain-dakera

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

DakeraMemory gives your chains conversation memory that survives restarts. DakeraVectorStore powers RAG with Dakera's built-in embedding engine — no OpenAI embeddings needed.

Quick Start

Step 1 — Run Dakera

Dakera is a self-hosted memory server. Spin it up with Docker:

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

For a production setup with persistent storage, use Docker Compose:

# Download and start
curl -sSfL https://raw.githubusercontent.com/Dakera-AI/dakera-deploy/main/docker-compose.yml \
  -o docker-compose.yml
DAKERA_API_KEY=dk-mykey docker compose up -d

# Verify it's running
curl http://localhost:3300/health

Full deployment guide: github.com/Dakera-AI/dakera-deploy

Step 2 — Install the integration

pip install langchain-dakera

Step 3 — Use it

from langchain_dakera import DakeraMemory, DakeraVectorStore

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

# RAG vector store — no local embedding model needed
vectorstore = DakeraVectorStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="my-docs",
)

Installation

pip install langchain-dakera

Requirements: Python ≥ 3.10, a running Dakera server (see Step 1 above)

DakeraMemory

Persistent semantic memory for LangChain conversation chains. Stores and recalls conversation history using Dakera's hybrid search.

Usage

from langchain.chains import ConversationChain
from langchain_openai import ChatOpenAI
from langchain_dakera import DakeraMemory

memory = DakeraMemory(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    agent_id="chat-agent",
    recall_k=5,      # memories to recall per turn
    importance=0.7,  # importance score for stored memories
)

chain = ConversationChain(
    llm=ChatOpenAI(model="gpt-4o"),
    memory=memory,
)

# First session
response = chain.predict(input="My name is Alice and I'm building a chatbot.")
print(response)

# Later session — memory persists across restarts
response = chain.predict(input="What was I building?")
print(response)  # "You mentioned you were building a chatbot."

Options

DakeraVectorStore

Server-side embedded vector store for RAG. Dakera handles embeddings — no OpenAI or Hugging Face API calls needed for indexing.

Indexing documents

from langchain_community.document_loaders import DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_dakera import DakeraVectorStore

# Load and split documents
loader = DirectoryLoader("./docs", glob="**/*.md")
docs = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(docs)

# Index into Dakera (server handles embedding)
vectorstore = DakeraVectorStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="my-docs",
)
vectorstore.add_documents(chunks)

RAG chain

from langchain.chains import RetrievalQA
from langchain_openai import ChatOpenAI
from langchain_dakera import DakeraVectorStore

vectorstore = DakeraVectorStore(
    api_url="http://localhost:3300",
    api_key="dk-mykey",
    namespace="my-docs",
)

qa_chain = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-4o"),
    retriever=vectorstore.as_retriever(search_kwargs={"k": 4}),
)

answer = qa_chain.run("How does Dakera handle memory decay?")
print(answer)

Options

Related packages

Links

• Dakera Server — self-hosted memory server
• Dakera Python SDK — low-level API client
• Integration guide — full setup walkthrough
• All integrations

License

MIT © Dakera AI