o +i%@sdZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z ddlmZee ZGd d d eZGd d d eZd S)atOptional caching layer for language models. Distinct from provider-based [prompt caching](https://docs.langchain.com/oss/python/langchain/models#prompt-caching). !!! warning "Beta feature" This is a beta feature. Please be wary of deploying experimental code to production unless you've taken appropriate precautions. A cache is useful for two reasons: 1. It can save you money by reducing the number of API calls you make to the LLM provider if you're often requesting the same completion multiple times. 2. It can speed up your application by reducing the number of API calls you make to the LLM provider. ) annotations)ABCabstractmethod)Sequence)Any)override) Generation)run_in_executorc@sXeZdZdZedddZedd d ZedddZdddZdddZ dddZ dS) BaseCacheaJInterface 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. promptstr llm_stringreturnRETURN_VAL_TYPE | NonecCdS)aLook 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). Args: 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 `Generation` (or subclasses). Nselfr r rrR/var/www/html/psymed-ai/venv/lib/python3.10/site-packages/langchain_core/caches.pylookup/zBaseCache.lookup return_valRETURN_VAL_TYPENonecCr)a]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. Args: 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 `Generation` (or subclasses). Nrrr r rrrrupdateFrzBaseCache.updatekwargsrcKr)z7Clear cache that can take additional keyword arguments.Nrrrrrrclear\rzBaseCache.clearcstd|j||IdHS)aAsync 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). Args: 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 `Generation` (or subclasses). N)r rrrrralookup`szBaseCache.alookupcstd|j|||IdHS)adAsync 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 look up method. Args: 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 `Generation` (or subclasses). N)r rrrrraupdatexszBaseCache.aupdatecstd|jfi|IdHS)z=Async clear cache that can take additional keyword arguments.N)r rrrrraclearszBaseCache.aclearNr r r r rrr r r r rrrrrrrr) __name__ __module__ __qualname____doc__rrrrrr r!rrrrr s     r c@sdeZdZdZddddd ZdddZd ddZed!ddZdddZ d ddZ ed!ddZ dS)" InMemoryCachez#Cache that stores things in memory.N)maxsizer* int | NonerrcCs,i|_|dur|dkrd}t|||_dS)a_Initialize with empty cache. Args: maxsize: The maximum number of items to store in the cache. If `None`, the cache has no maximum size. If the cache exceeds the maximum size, the oldest items are removed. Raises: ValueError: If `maxsize` is less than or equal to `0`. Nrzmaxsize must be greater than 0)_cache ValueError_maxsize)rr*msgrrr__init__s   zInMemoryCache.__init__r r r rcCs|j||fdS)aLook up based on `prompt` and `llm_string`. Args: 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. Returns: On a cache miss, return `None`. On a cache hit, return the cached value. N)r,getrrrrrs zInMemoryCache.lookuprrcCs>|jdurt|j|jkr|jtt|j=||j||f<dS)aUpdate cache based on `prompt` and `llm_string`. Args: 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. return_val: The value to be cached. The value is a list of `Generation` (or subclasses). N)r.lenr,nextiterrrrrrs zInMemoryCache.updaterrcKs i|_dS)z Clear cache.N)r,rrrrrs zInMemoryCache.clearcs|||S)aAsync look up based on `prompt` and `llm_string`. Args: 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. Returns: On a cache miss, return `None`. On a cache hit, return the cached value. )rrrrrrs zInMemoryCache.alookupcs||||dS)aAsync update cache based on `prompt` and `llm_string`. Args: 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. return_val: The value to be cached. The value is a list of `Generation` (or subclasses). N)rrrrrr s zInMemoryCache.aupdatecs|dS)zAsync clear cache.N)rrrrrr!s zInMemoryCache.aclear)r*r+rrr"r#r$) r%r&r'r(r0rrrrrr r!rrrrr)s     r)N)r( __future__rabcrrcollections.abcrtypingrtyping_extensionsrlangchain_core.outputsrlangchain_core.runnablesr rr r)rrrrs      v