Tatry
Docs
About API

About API

Welcome to the Tatry API reference. Our API is organized around REST principles and uses standard HTTP response codes, authentication, and verbs.

Base URL

https://api.tatry.dev/v1

Authentication

All API requests require authentication using your API key. You can authenticate using either our REST API or Python SDK:

Authorization: Bearer your-api-key
from tatry import TatryRetriever
 
# Initialize the client with your API key
client = TatryRetriever(api_key="your-api-key")

Available Endpoints

CategoryBase PathDocumentationDescription
Authentication/v1/authView DocsAPI key management and validation
Retrieval/v1/retrieveView DocsDocument search and batch processing
Sources/v1/sourcesView DocsContent source management
Usage/v1/usage /v1/feedback /v1/healthView DocsUsage statistics and system health

Integrations

Our Python SDK provides seamless integration with popular frameworks and libraries:

LangChain Integration

The SDK includes several pre-built components that work out-of-the-box with LangChain:

from content_retriever.integrations.langchain import (
   TatryRetrieverLangchain
)
 
# Initialize LLM
llm = ChatOpenAI(temperature=0)
 
# Create a simple QA chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=retriever,
    chain_type="stuff"  # Simple document concatenation
)
 
# Use the chain
response = qa_chain.run("What are the key features of quantum computing?")
print(response)

Read more about the Langchain Integration

Testing

Use our sandbox environment for testing:

curl https://sandbox-api.tatry.dev/v1/health
client = TatryRetriever(
    api_key="your-api-key",
    base_url="https://sandbox-api.tatry.dev/v1"
)

Rate Limits

  • 100 requests per minute per API key
  • 1000 requests per hour per API key
  • Bulk operations count as multiple requests

Next Steps