Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

core: docstrings example_selectors (#23542)

Browse Source 
Added missed docstrings. Formatted docstrings to the consistent form.
This commit is contained in:
Leonid Ganeline 2024-06-26 14:10:40 -07:00 committed by GitHub
parent 3bf1d98dbf
commit 1141b08eb8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 108 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libs/core/langchain_core/example_selectors/__init__.py
View File

@ -2,6 +2,7 @@
in prompts.
This allows us to select examples that are most relevant to the input.
"""
from langchain_core.example_selectors.base import BaseExampleSelector
from langchain_core.example_selectors.length_based import (
LengthBasedExampleSelector,

27
libs/core/langchain_core/example_selectors/base.py
View File

@ -1,4 +1,5 @@
"""Interface for selecting examples to include in prompts."""
from abc import ABC, abstractmethod
from typing import Any, Dict, List
@ -10,16 +11,34 @@ class BaseExampleSelector(ABC):
@abstractmethod
def add_example(self, example: Dict[str, str]) -> Any:
"""Add new example to store."""
"""Add new example to store.
Args:
example: A dictionary with keys as input variables
and values as their values."""
async def aadd_example(self, example: Dict[str, str]) -> Any:
"""Add new example to store."""
"""Async add new example to store.
Args:
example: A dictionary with keys as input variables
and values as their values."""
return await run_in_executor(None, self.add_example, example)
@abstractmethod
def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Select which examples to use based on the inputs."""
"""Select which examples to use based on the inputs.
Args:
input_variables: A dictionary with keys as input variables
and values as their values."""
async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Select which examples to use based on the inputs."""
"""Async select which examples to use based on the inputs.
Args:
input_variables: A dictionary with keys as input variables
and values as their values."""
return await run_in_executor(None, self.select_examples, input_variables)

37
libs/core/langchain_core/example_selectors/length_based.py
View File

@ -1,4 +1,5 @@
"""Select examples based on length."""
import re
from typing import Callable, Dict, List
@ -27,15 +28,27 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
"""Max length for the prompt, beyond which examples are cut."""
example_text_lengths: List[int] = [] #: :meta private:
"""Length of each example."""
def add_example(self, example: Dict[str, str]) -> None:
"""Add new example to list."""
"""Add new example to list.
Args:
example: A dictionary with keys as input variables
and values as their values.
"""
self.examples.append(example)
string_example = self.example_prompt.format(**example)
self.example_text_lengths.append(self.get_text_length(string_example))
async def aadd_example(self, example: Dict[str, str]) -> None:
"""Add new example to list."""
"""Async add new example to list.
Args:
example: A dictionary with keys as input variables
and values as their values.
"""
self.add_example(example)
@validator("example_text_lengths", always=True)
@ -51,7 +64,15 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
return [get_text_length(eg) for eg in string_examples]
def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Select which examples to use based on the input lengths."""
"""Select which examples to use based on the input lengths.
Args:
input_variables: A dictionary with keys as input variables
and values as their values.
Returns:
A list of examples to include in the prompt.
"""
inputs = " ".join(input_variables.values())
remaining_length = self.max_length - self.get_text_length(inputs)
i = 0
@ -67,5 +88,13 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
return examples
async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Select which examples to use based on the input lengths."""
"""Async select which examples to use based on the input lengths.
Args:
input_variables: A dictionary with keys as input variables
and values as their values.
Returns:
A list of examples to include in the prompt.
"""
return self.select_examples(input_variables)

61
libs/core/langchain_core/example_selectors/semantic_similarity.py
View File

@ -1,4 +1,5 @@
"""Example selector that selects examples based on SemanticSimilarity."""
from __future__ import annotations
from abc import ABC
@ -14,7 +15,15 @@ if TYPE_CHECKING:
def sorted_values(values: Dict[str, str]) -> List[Any]:
"""Return a list of values in dict sorted by key."""
"""Return a list of values in dict sorted by key.
Args:
values: A dictionary with keys as input variables
and values as their values.
Returns:
A list of values in dict sorted by key.
"""
return [values[val] for val in sorted(values)]
@ -58,14 +67,30 @@ class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
return examples
def add_example(self, example: Dict[str, str]) -> str:
"""Add new example to vectorstore."""
"""Add a new example to vectorstore.
Args:
example: A dictionary with keys as input variables
and values as their values.
Returns:
The ID of the added example.
"""
ids = self.vectorstore.add_texts(
[self._example_to_text(example, self.input_keys)], metadatas=[example]
)
return ids[0]
async def aadd_example(self, example: Dict[str, str]) -> str:
"""Add new example to vectorstore."""
"""Async add new example to vectorstore.
Args:
example: A dictionary with keys as input variables
and values as their values.
Returns:
The ID of the added example.
"""
ids = await self.vectorstore.aadd_texts(
[self._example_to_text(example, self.input_keys)], metadatas=[example]
)
@ -76,7 +101,14 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
"""Select examples based on semantic similarity."""
def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Select examples based on semantic similarity."""
"""Select examples based on semantic similarity.
Args:
input_variables: The input variables to use for search.
Returns:
The selected examples.
"""
# Get the docs with the highest similarity.
vectorstore_kwargs = self.vectorstore_kwargs or {}
example_docs = self.vectorstore.similarity_search(
@ -87,7 +119,14 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
return self._documents_to_examples(example_docs)
async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
"""Asynchronously select examples based on semantic similarity."""
"""Asynchronously select examples based on semantic similarity.
Args:
input_variables: The input variables to use for search.
Returns:
The selected examples.
"""
# Get the docs with the highest similarity.
vectorstore_kwargs = self.vectorstore_kwargs or {}
example_docs = await self.vectorstore.asimilarity_search(
@ -118,7 +157,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
examples: List of examples to use in the prompt.
embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls: A vector store DB interface class, e.g. FAISS.
k: Number of examples to select
k: Number of examples to select. Default is 4.
input_keys: If provided, the search is based on the input variables
instead of all variables.
example_keys: If provided, keys to filter examples to.
@ -154,7 +193,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
vectorstore_kwargs: Optional[dict] = None,
**vectorstore_cls_kwargs: Any,
) -> SemanticSimilarityExampleSelector:
"""Create k-shot example selector using example list and embeddings.
"""Async create k-shot example selector using example list and embeddings.
Reshuffles examples dynamically based on query similarity.
@ -162,7 +201,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
examples: List of examples to use in the prompt.
embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls: A vector store DB interface class, e.g. FAISS.
k: Number of examples to select
k: Number of examples to select. Default is 4.
input_keys: If provided, the search is based on the input variables
instead of all variables.
example_keys: If provided, keys to filter examples to.
@ -249,8 +288,9 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
examples: List of examples to use in the prompt.
embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls: A vector store DB interface class, e.g. FAISS.
k: Number of examples to select
k: Number of examples to select. Default is 4.
fetch_k: Number of Documents to fetch to pass to MMR algorithm.
Default is 20.
input_keys: If provided, the search is based on the input variables
instead of all variables.
example_keys: If provided, keys to filter examples to.
@ -297,8 +337,9 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
examples: List of examples to use in the prompt.
embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls: A vector store DB interface class, e.g. FAISS.
k: Number of examples to select
k: Number of examples to select. Default is 4.
fetch_k: Number of Documents to fetch to pass to MMR algorithm.
Default is 20.
input_keys: If provided, the search is based on the input variables
instead of all variables.
example_keys: If provided, keys to filter examples to.