langchain-keiro 0.1.0

An integration package connecting Keiro and LangChain

langchain-keiro

Official LangChain integration for the Keiro deep search API with embeddings.

All components use deep mode with embeddings enabled — no configuration needed. Every request returns full content plus 768-dimensional embedding vectors (configurable to 384/512/1024 via Matryoshka).

Installation

pip install langchain-keiro

Quick Start

Retriever

Use Keiro as a LangChain retriever for RAG pipelines:

from langchain_keiro.retrievers import KeiroRetriever

retriever = KeiroRetriever(
    keiro_api_key="keiro_...",
    max_results=3,
)

# Sync
docs = retriever.invoke("What is artificial intelligence?")

# Async
docs = await retriever.ainvoke("What is artificial intelligence?")

# Each doc includes embeddings in metadata:
# doc.metadata["query_embedding"]  — 768-dim vector for the query
# doc.metadata["chunk_embeddings"]  — per-chunk embeddings with text
# doc.metadata["tldr"], ["tags"], ["entities"], etc.

# Use in a RAG chain
from langchain_openai import ChatOpenAI
from langchain.chains import create_retrieval_chain

llm = ChatOpenAI(model="gpt-4")
chain = create_retrieval_chain(retriever, llm)
response = chain.invoke({"input": "What is AI?"})

Embeddings

Generate embedding vectors directly:

from langchain_keiro.embeddings import KeiroEmbeddings

embeddings = KeiroEmbeddings(
    keiro_api_key="keiro_...",
    dimensions=768,  # Matryoshka: 384, 512, 768, or 1024
)

# Single query
vec = embeddings.embed_query("What is AI?")
# vec is a list of 768 floats

# Batch documents
vecs = embeddings.embed_documents(["doc 1", "doc 2", "doc 3"])

# Async
vec = await embeddings.aembed_query("What is AI?")
vecs = await embeddings.aembed_documents(["doc 1", "doc 2"])

Tool (for Agents)

Use Keiro as a tool in LangChain agents:

from langchain_keiro.tools import KeiroSearchTool

tool = KeiroSearchTool(keiro_api_key="keiro_...")

# Direct invocation
result = tool.invoke({"query": "latest AI research"})

# With an agent
from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4")
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a research assistant. Use the keiro_search tool to find information."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, [tool], prompt)
agent_executor = AgentExecutor(agent=agent, tools=[tool])
response = agent_executor.invoke({"input": "What are the latest AI trends?"})

Configuration

KeiroRetriever

Parameter	Type	Default	Description
keiro_api_key	SecretStr	required	Your Keiro API key
base_url	str	https://kierolabs.space/api	API base URL
max_results	int	3	Number of results (1-5)
embedding_dimensions	int	768	Vector dimensions (384, 512, 768, 1024)

Always uses mode="deep" with embeddings.enabled=true.

KeiroEmbeddings

Parameter	Type	Default	Description
keiro_api_key	SecretStr	required	Your Keiro API key
base_url	str	https://kierolabs.space/api	API base URL
model	str	"pplx-embed-v1-0.6b"	Embedding model identifier
dimensions	int	768	Vector dimensions (384, 512, 768, 1024)

KeiroSearchTool

Parameter	Type	Default	Description
keiro_api_key	SecretStr	required	Your Keiro API key
base_url	str	https://kierolabs.space/api	API base URL

Always uses mode="deep" with embeddings.enabled=true.

Embedding Dimensions (Matryoshka)

The Keiro API supports Matryoshka embedding dimensions, allowing you to trade off vector size for precision:

• 384: Smallest, fastest, least precise
• 512: Good balance for lightweight use
• 768 (default): Standard precision
• 1024: Maximum precision

Response Enrichment

The deep mode response includes rich metadata beyond just content:

Field	Description
query_embedding	768-dim embedding vector for the search query
chunk_embeddings	Per-chunk embeddings with text and offset
tldr	AI-generated summary of the page
tags	Extracted topic tags
entities	Named entities found in the content
readingTime	Estimated reading time
wordCount	Word count of the content
credibility	Source credibility score
quality	Content quality score

API Key

Get your API key at keirolabs.cloud. The Explorer plan includes 500 free credits.

Development

# Install for development
pip install -e ".[test]"

# Run unit tests
pytest tests/unit_tests/

# Run integration tests (requires KEIRO_API_KEY)
KEIRO_API_KEY=keiro_... pytest tests/integration_tests/

License

MIT