Trait BaseCache

pub trait BaseCache: Send + Sync {
    // Required methods
    fn lookup(
        &self,
        prompt: &str,
        llm_string: &str,
    ) -> Result<Option<CachedGenerations>>;
    fn update(
        &self,
        prompt: &str,
        llm_string: &str,
        return_val: CachedGenerations,
    ) -> Result<()>;
    fn clear(&self) -> Result<()>;
    fn alookup<'life0, 'life1, 'life2, 'async_trait>(
        &'life0 self,
        prompt: &'life1 str,
        llm_string: &'life2 str,
    ) -> Pin<Box<dyn Future<Output = Result<Option<CachedGenerations>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait,
             'life2: 'async_trait;
    fn aupdate<'life0, 'life1, 'life2, 'async_trait>(
        &'life0 self,
        prompt: &'life1 str,
        llm_string: &'life2 str,
        return_val: CachedGenerations,
    ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait,
             'life2: 'async_trait;
    fn aclear<'life0, 'async_trait>(
        &'life0 self,
    ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait;
}

Interface for a caching layer for LLMs and Chat models.

The cache interface consists of the following methods:

• lookup: Look up a value based on a prompt and llm_string.
• update: Update the cache based on a prompt and llm_string.
• clear: Clear the cache.

In addition, the cache interface provides an async version of each method.

The default implementation of the async methods is to run the synchronous method in an executor. It’s recommended to override the async methods and provide async implementations to avoid unnecessary overhead.

Required Methods

fn lookup( &self, prompt: &str, llm_string: &str, ) -> Result<Option<CachedGenerations>>

Look up based on prompt and llm_string.

A cache implementation is expected to generate a key from the 2-tuple of prompt and llm_string (e.g., by concatenating them with a delimiter).

Arguments

• prompt - A string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.
• llm_string - A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.

Returns

On a cache miss, return None. On a cache hit, return the cached value. The cached value is a list of Generations (or subclasses).

fn update( &self, prompt: &str, llm_string: &str, return_val: CachedGenerations, ) -> Result<()>

Update cache based on prompt and llm_string.

The prompt and llm_string are used to generate a key for the cache. The key should match that of the lookup method.

Arguments

• prompt - A string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.
• llm_string - A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.
• return_val - The value to be cached. The value is a list of Generations (or subclasses).

fn clear(&self) -> Result<()>

Clear cache that can take additional keyword arguments.

fn alookup<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, llm_string: &'life2 str, ) -> Pin<Box<dyn Future<Output = Result<Option<CachedGenerations>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Async look up based on prompt and llm_string.

A cache implementation is expected to generate a key from the 2-tuple of prompt and llm_string (e.g., by concatenating them with a delimiter).

Arguments

• prompt - A string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.
• llm_string - A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.

Returns

On a cache miss, return None. On a cache hit, return the cached value. The cached value is a list of Generations (or subclasses).

fn aupdate<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, llm_string: &'life2 str, return_val: CachedGenerations, ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Async update cache based on prompt and llm_string.

The prompt and llm_string are used to generate a key for the cache. The key should match that of the lookup method.

Arguments

• prompt - A string representation of the prompt. In the case of a Chat model, the prompt is a non-trivial serialization of the prompt into the language model.
• llm_string - A string representation of the LLM configuration. This is used to capture the invocation parameters of the LLM (e.g., model name, temperature, stop tokens, max tokens, etc.). These invocation parameters are serialized into a string representation.
• return_val - The value to be cached. The value is a list of Generations (or subclasses).

fn aclear<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Async clear cache that can take additional keyword arguments.

Implementors

impl BaseCache for InMemoryCache

impl BaseCache for TtlCache