Skip to main content
All Vrin SDK exceptions inherit from VRINError. You can catch VRINError to handle any SDK error, or catch specific subclasses for fine-grained control.

​
Exception hierarchy

VRINError
  +-- AuthenticationError
  +-- RateLimitError
  +-- ValidationError
  +-- ServiceUnavailableError
  +-- JobFailedError
  +-- TimeoutError
  +-- InsufficientCoverageError
  +-- StreamingError

​
VRINError

Base exception for all SDK errors. 
from vrin import VRINError

try:
    result = client.query("What is ACME's revenue?")
except VRINError as e:
    print(f"Vrin error: {e}")

​
AuthenticationError

Raised when authentication fails (HTTP 401). The API key is invalid, expired, or missing. 
from vrin import AuthenticationError

try:
    client = VRINClient(api_key="invalid_key")
    client.query("test")
except AuthenticationError:
    print("Invalid API key")

​
RateLimitError

Raised when rate limits are exceeded (HTTP 429). Back off and retry after a delay. 
from vrin import RateLimitError

try:
    result = client.query("test")
except RateLimitError:
    print("Rate limit hit -- wait before retrying")

​
ValidationError

Raised when input validation fails. Check the error message for details.

​
ServiceUnavailableError

Raised when the Vrin service is unavailable (HTTP 5xx). The client retries automatically based on max_retries before raising this exception.

​
JobFailedError

Raised by wait_for_job() when a processing job fails. 
from vrin import JobFailedError

try:
    result = client.insert("content", title="Test")
except JobFailedError as e:
    print(f"Job failed: {e}")

​
TimeoutError

Raised when an operation exceeds its timeout. For async jobs, use get_job_status() to check if the job is still running. 
from vrin import TimeoutError

try:
    result = client.insert("very long document...", max_wait=60.0)
except TimeoutError:
    print("Job still processing -- check status manually")
This is vrin.TimeoutError, not Python’s built-in TimeoutError. Import it from vrin to avoid confusion.

​
InsufficientCoverageError

Raised when the knowledge base has zero coverage for a query. This means no relevant entities or facts were found.

​
StreamingError

Raised during SSE streaming when the backend sends an error event. 
from vrin import StreamingError

try:
    for token in client.query("test", stream=True):
        print(token, end="")
except StreamingError as e:
    print(f"Stream error: {e}")

​
Error handling patterns

See the Error Handling guide for recommended patterns including retry logic and graceful degradation.