最大边际相关(MMR)
MaxMarginalRelevanceExampleSelector
根据最大边际相关性选择示例,该方法结合了与输入最相似的示例以及优化多样性。它通过找到嵌入与输入具有最大余弦相似度的示例,然后在惩罚已选择示例的近似度的同时迭代地添加它们。
from langchain.prompts import FewShotPromptTemplate, PromptTemplate
from langchain.prompts.example_selector import (
MaxMarginalRelevanceExampleSelector,
SemanticSimilarityExampleSelector,
)
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings
example_prompt = PromptTemplate(
input_variables=["input", "output"],
template="Input: {input}\nOutput: {output}",
)
# Examples of a pretend task of creating antonyms.
examples = [
{"input": "happy", "output": "sad"},
{"input": "tall", "output": "short"},
{"input": "energetic", "output": "lethargic"},
{"input": "sunny", "output": "gloomy"},
{"input": "windy", "output": "calm"},
]
example_selector = MaxMarginalRelevanceExampleSelector.from_examples(
# The list of examples available to select from.
examples,
# The embedding class used to produce embeddings which are used to measure semantic similarity.
OpenAIEmbeddings(),
# The VectorStore class that is used to store the embeddings and do a similarity search over.
FAISS,
# The number of examples to produce.
k=2,
)
mmr_prompt = FewShotPromptTemplate(
# We provide an ExampleSelector instead of examples.
example_selector=example_selector,
example_prompt=example_prompt,
prefix="Give the antonym of every input",
suffix="Input: {adjective}\nOutput:",
input_variables=["adjective"],
)
# Input is a feeling, so should select the happy/sad example as the first one
print(mmr_prompt.format(adjective="worried"))
Give the antonym of every input
Input: happy
Output: sad
Input: windy
Output: calm
Input: worried
Output:
# Let's compare this to what we would just get if we went solely off of similarity,
# by using SemanticSimilarityExampleSelector instead of MaxMarginalRelevanceExampleSelector.
example_selector = SemanticSimilarityExampleSelector.from_examples(
# The list of examples available to select from.
examples,
# The embedding class used to produce embeddings which are used to measure semantic similarity.
OpenAIEmbeddings(),
# The VectorStore class that is used to store the embeddings and do a similarity search over.
FAISS,
# The number of examples to produce.
k=2,
)
similar_prompt = FewShotPromptTemplate(
# We provide an ExampleSelector instead of examples.
example_selector=example_selector,
example_prompt=example_prompt,
prefix="Give the antonym of every input",
suffix="Input: {adjective}\nOutput:",
input_variables=["adjective"],
)
print(similar_prompt.format(adjective="worried"))
Give the antonym of every input
Input: happy
Output: sad
Input: sunny
Output: gloomy
Input: worried
Output: