From e4fc0e750297fed471f871673cca5733c61f35c1 Mon Sep 17 00:00:00 2001
From: Eugene Yurtsev <eyurtsev@gmail.com>
Date: Fri, 5 Apr 2024 10:56:57 -0400
Subject: [PATCH] core[patch]: Document BaseCache abstraction in code (#20046)

Document the base cache abstraction in the cache.
---
 libs/core/langchain_core/caches.py | 57 +++++++++++++++++++++++++++---
 1 file changed, 52 insertions(+), 5 deletions(-)

diff --git a/libs/core/langchain_core/caches.py b/libs/core/langchain_core/caches.py
index b7c02b96c85..4c494c4fbc8 100644
--- a/libs/core/langchain_core/caches.py
+++ b/libs/core/langchain_core/caches.py
@@ -31,28 +31,75 @@ RETURN_VAL_TYPE = Sequence[Generation]
 
 
 class BaseCache(ABC):
-    """Base interface for cache."""
+    """This interfaces provides 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 an async implementations to avoid unnecessary overhead.
+    """
 
     @abstractmethod
     def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string."""
+        """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 Generations (or subclasses).
+        """
 
     @abstractmethod
     def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
-        """Update cache based on prompt and llm_string."""
+        """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 Generations
+                (or subclasses).
+        """
 
     @abstractmethod
     def clear(self, **kwargs: Any) -> None:
         """Clear cache that can take additional keyword arguments."""
 
     async def alookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string."""
+        """Async version of lookup."""
         return await run_in_executor(None, self.lookup, prompt, llm_string)
 
     async def aupdate(
         self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE
     ) -> None:
-        """Update cache based on prompt and llm_string."""
+        """Async version of aupdate."""
         return await run_in_executor(None, self.update, prompt, llm_string, return_val)
 
     async def aclear(self, **kwargs: Any) -> None: