Skip to main content
Enable caching to store and reuse task responses for similar inputs, reducing API costs and improving performance.

​
Quick Start

task = Task(
    description="Summarize this article",
    enable_cache=True
)

​
Cache Methods

​
Vector Search (Default)

Uses semantic similarity to find cached responses for similar inputs. 
task = Task(
    description="Analyze this text",
    enable_cache=True,
    cache_method="vector_search",
    cache_threshold=0.8  # Higher = stricter matching
)

​
LLM Call

Uses an LLM to determine if cached responses are applicable. 
task = Task(
    description="Analyze this text",
    enable_cache=True,
    cache_method="llm_call"
)

​
Configuration Options

ParameterTypeDefaultDescription
enable_cacheboolFalseEnable/disable caching
cache_methodstr"vector_search""vector_search" or "llm_call"
cache_thresholdfloat0.7Similarity threshold (0.0-1.0)
cache_duration_minutesint60Cache expiration time
cache_embedding_providerAnyAuto-detectedCustom embedding provider

​
Full Example

from upsonic import Task, Agent

task = Task(
    description="Explain quantum computing",
    enable_cache=True,
    cache_method="vector_search",
    cache_threshold=0.75,
    cache_duration_minutes=120
)

agent = Agent()
result = agent.run(task)

# Check if response came from cache
if task.cache_hit:
    print("Response retrieved from cache!")

​
Task Cache Methods

​
set_cache_manager(cache_manager)

Set a custom cache manager for the task. 
task.set_cache_manager(my_cache_manager)

​
get_cached_response(input_text, llm_provider=None)

Retrieve cached response for given input (async). 
cached = await task.get_cached_response("Explain quantum computing")
if cached:
    print("Found cached response:", cached)

​
store_cache_entry(input_text, output)

Store a new cache entry (async). 
await task.store_cache_entry("Explain quantum computing", response)

​
get_cache_stats()

Get cache statistics including hit rate and configuration. 
stats = task.get_cache_stats()
print(f"Hit rate: {stats['hit_rate']}")
print(f"Total entries: {stats['total_entries']}")
Returns:
  • total_entries: Number of cached entries
  • cache_hits: Number of cache hits
  • cache_misses: Number of cache misses
  • hit_rate: Cache hit rate (0.0-1.0)
  • cache_method: Current cache method
  • cache_threshold: Current threshold
  • cache_hit: Whether last request was a cache hit
  • session_id: Current session ID

​
clear_cache()

Clear all cache entries. 
task.clear_cache()

​
Best Practices

  • Threshold Tuning: Start with 0.7, increase for stricter matching
  • Duration: Set based on how often your data changes
  • Method Choice: Use vector_search for speed, llm_call for accuracy
  • Embedding Provider: Auto-detected if not specified