langchain/libs/partners/elasticsearch/tests/fake_embeddings.py
Max Jakob 5ab69f907f
partners: add Elasticsearch package (#17467)
### Description
This PR moves the Elasticsearch classes to a partners package.

Note that we will not move (and later remove) `ElasticKnnSearch`. It
were previously deprecated.
`ElasticVectorSearch` is going to stay in the community package since it
is used quite a lot still.

Also note that I left the `ElasticsearchTranslator` for self query
untouched because it resides in main `langchain` package.

### Dependencies
There will be another PR that updates the notebooks (potentially pulling
them into the partners package) and templates and removes the classes
from the community package, see
https://github.com/langchain-ai/langchain/pull/17468

#### Open question
How to make the transition smooth for users? Do we move the import
aliases and require people to install `langchain-elasticsearch`? Or do
we remove the import aliases from the `langchain` package all together?
What has worked well for other partner packages?

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-26 23:19:47 +00:00

56 lines
2.0 KiB
Python

"""Fake Embedding class for testing purposes."""
from typing import List
from langchain_core.embeddings import Embeddings
fake_texts = ["foo", "bar", "baz"]
class FakeEmbeddings(Embeddings):
"""Fake embeddings functionality for testing."""
def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""Return simple embeddings.
Embeddings encode each text as its index."""
return [[float(1.0)] * 9 + [float(i)] for i in range(len(texts))]
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
return self.embed_documents(texts)
def embed_query(self, text: str) -> List[float]:
"""Return constant query embeddings.
Embeddings are identical to embed_documents(texts)[0].
Distance to each text will be that text's index,
as it was passed to embed_documents."""
return [float(1.0)] * 9 + [float(0.0)]
async def aembed_query(self, text: str) -> List[float]:
return self.embed_query(text)
class ConsistentFakeEmbeddings(FakeEmbeddings):
"""Fake embeddings which remember all the texts seen so far to return consistent
vectors for the same texts."""
def __init__(self, dimensionality: int = 10) -> None:
self.known_texts: List[str] = []
self.dimensionality = dimensionality
def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""Return consistent embeddings for each text seen so far."""
out_vectors = []
for text in texts:
if text not in self.known_texts:
self.known_texts.append(text)
vector = [float(1.0)] * (self.dimensionality - 1) + [
float(self.known_texts.index(text))
]
out_vectors.append(vector)
return out_vectors
def embed_query(self, text: str) -> List[float]:
"""Return consistent embeddings for the text, if seen before, or a constant
one if the text is unknown."""
return self.embed_documents([text])[0]