langchain-core 0.3.79__py3-none-any.whl → 1.0.0__py3-none-any.whl

langchain_core/caches.py

@@ -1,31 +1,22 @@
-"""Cache classes.
+"""`caches` provides an optional caching layer for language models.
 
-.. warning::
-  Beta Feature!
+!!! warning
+    This is a beta feature! Please be wary of deploying experimental code to production
+    unless you've taken appropriate precautions.
 
-**Cache** provides an optional caching layer for LLMs.
+A cache is useful for two reasons:
 
-Cache is useful for two reasons:
-
-- 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.
-- It can speed up your application by reducing the number of API calls you make
-  to the LLM provider.
-
-Cache directly competes with Memory. See documentation for Pros and Cons.
-
-**Class hierarchy:**
-
-.. code-block::
-
-    BaseCache --> <name>Cache  # Examples: InMemoryCache, RedisCache, GPTCache
+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.
 """
 
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from collections.abc import Sequence
-from typing import Any, Optional
+from typing import Any
 
 from typing_extensions import override
 
@@ -40,8 +31,8 @@ class BaseCache(ABC):
 
     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.
+    - 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.
@@ -52,15 +43,15 @@ class BaseCache(ABC):
     """
 
     @abstractmethod
-    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string.
+    def lookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
+        """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
+            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
@@ -69,27 +60,27 @@ class BaseCache(ABC):
                 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).
+            On a cache miss, return `None`. On a cache hit, return the cached value.
+            The cached value is a list of `Generation` (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 lookup method.
 
         Args:
-            prompt: a string representation of the prompt.
-                In the case of a Chat model, the prompt is a non-trivial
+            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
+            return_val: The value to be cached. The value is a list of `Generation`
                 (or subclasses).
         """
 
@@ -97,15 +88,15 @@ class BaseCache(ABC):
     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]:
-        """Async look up based on prompt and llm_string.
+    async def alookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
+        """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).
 
         Args:
-            prompt: a string representation of the prompt.
-                In the case of a Chat model, the prompt is a non-trivial
+            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
@@ -114,29 +105,29 @@ class BaseCache(ABC):
                 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).
+            On a cache miss, return `None`. On a cache hit, return the cached value.
+            The cached value is a list of `Generation` (or subclasses).
         """
         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:
-        """Async update cache based on prompt and llm_string.
+        """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 look up method.
 
         Args:
-            prompt: a string representation of the prompt.
-                In the case of a Chat model, the prompt is a non-trivial
+            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
+            return_val: The value to be cached. The value is a list of `Generation`
                 (or subclasses).
         """
         return await run_in_executor(None, self.update, prompt, llm_string, return_val)
@@ -149,17 +140,16 @@ class BaseCache(ABC):
 class InMemoryCache(BaseCache):
     """Cache that stores things in memory."""
 
-    def __init__(self, *, maxsize: Optional[int] = None) -> None:
+    def __init__(self, *, maxsize: int | None = None) -> None:
         """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 `None`, the cache has no maximum size.
                 If the cache exceeds the maximum size, the oldest items are removed.
-                Default is None.
 
         Raises:
-            ValueError: If maxsize is less than or equal to 0.
+            ValueError: If `maxsize` is less than or equal to `0`.
         """
         self._cache: dict[tuple[str, str], RETURN_VAL_TYPE] = {}
         if maxsize is not None and maxsize <= 0:
@@ -167,29 +157,29 @@ class InMemoryCache(BaseCache):
             raise ValueError(msg)
         self._maxsize = maxsize
 
-    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string.
+    def lookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
+        """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
+            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.
+            On a cache miss, return `None`. On a cache hit, return the cached value.
         """
         return self._cache.get((prompt, llm_string), None)
 
     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`.
 
         Args:
-            prompt: a string representation of the prompt.
-                In the case of a Chat model, the prompt is a non-trivial
+            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 Generations
+            return_val: The value to be cached. The value is a list of `Generation`
                 (or subclasses).
         """
         if self._maxsize is not None and len(self._cache) == self._maxsize:
@@ -201,31 +191,31 @@ class InMemoryCache(BaseCache):
         """Clear cache."""
         self._cache = {}
 
-    async def alookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Async look up based on prompt and llm_string.
+    async def alookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
+        """Async 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
+            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.
+            On a cache miss, return `None`. On a cache hit, return the cached value.
         """
         return self.lookup(prompt, llm_string)
 
     async def aupdate(
         self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE
     ) -> None:
-        """Async update cache based on prompt and llm_string.
+        """Async 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
+            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 Generations
+            return_val: The value to be cached. The value is a list of `Generation`
                 (or subclasses).
         """
         self.update(prompt, llm_string, return_val)

langchain_core/callbacks/__init__.py

@@ -1,11 +1,4 @@
-"""**Callback handlers** allow listening to events in LangChain.
-
-**Class hierarchy:**
-
-.. code-block::
-
-    BaseCallbackHandler --> <name>CallbackHandler  # Example: AimCallbackHandler
-"""
+"""**Callback handlers** allow listening to events in LangChain."""
 
 from typing import TYPE_CHECKING